agentera 3.0.0-dev.4 → 3.0.0-dev.5

package/dist/capabilities/inspektera/instructions.js

@@ -0,0 +1,6 @@
+// Source: skills/agentera/capabilities/inspektera/instructions.md (relocated D65)
+// Markdown body lifted verbatim; the JSON literal below round-trips to byte-for-byte
+// equivalence with the deleted file (whitespace allowed to differ at line endings only).
+export const instructions = JSON.parse(String.raw `"# INSPEKTERA\n\n**Integrity Navigation: Systematic Pattern Evaluation, Knowledge Tracing. Examine, Report, Advise.**\n\nCodebase health audit: multi-dimensional structural quality evaluation with evidence-based findings, confidence scores, and trajectory tracking. The retrospective counterpart to realisera's forward motion: is the codebase getting better or just bigger?\n\nEach invocation = one audit. Findings feed realisera's work selection via TODO.md. Skill introduction: \u0060─── ⛶ inspektera · audit ───\u0060\n\n---\n\n## Visual identity\n\nGlyph: **⛶** (protocol ref: SG3). Used in the mandatory exit marker.\n\n---\n\n## State artifacts\n\nOne file in \u0060.agentera/\u0060, bootstrapped if absent.\n\n| File | Purpose | Bootstrap |\n|------|---------|-----------|\n| \u0060HEALTH.md\u0060 | Canonical health artifact, stored as \u0060.agentera/health.yaml\u0060 unless mapped otherwise. Findings, dimension grades, trajectory. | First audit entry in YAML form. |\n\nUse \u0060agentera describe --format json\u0060 and its \u0060artifact_schemas\u0060 entry for \u0060health\u0060 to locate the active installed schema; do not search Agentera directories manually. Existing health artifacts provide repository-local examples of the shape.\n\n### Artifact path resolution\n\nBefore reading or writing any artifact, check if \u0060.agentera/docs.yaml\u0060 exists. If it has an Artifact Mapping section, use the path specified for each canonical filename. If \u0060.agentera/docs.yaml\u0060 doesn't exist or has no mapping for a given artifact, use the default layout: TODO.md, CHANGELOG.md, and DESIGN.md at the project root; canonical VISION.md at \u0060.agentera/vision.yaml\u0060; other agent-facing artifacts at \u0060.agentera/*.yaml\u0060. This applies to all artifact references in this capability, including cross-capability reads (VISION.md, \u0060.agentera/decisions.yaml\u0060, TODO.md, \u0060.agentera/progress.yaml\u0060).\n\n### Contract\n\nBefore starting, read \u0060references/contract.md\u0060 (at v2 skill location \u0060skills/agentera/references/contract.md\u0060) for authoritative values: token budgets, severity levels, format contracts, and other shared conventions referenced in the steps below. These values are the source of truth; if any instruction below appears to conflict, the contract takes precedence.\n\n### health.yaml\n\nOpen with your read on the codebase before the structured data: what's improving, what's sliding, what surprised you. 1-2 sentences of interpretation, then the grades and findings back it up. The colleague says what they think, then shows the evidence.\n\n\u0060\u0060\u0060yaml\naudits:\n  - number: 1\n    date: YYYY-MM-DD\n    dimensions: [architecture_alignment, test_health]\n    findings_summary: \"X critical, Y warnings, Z info\"\n    overall: stable\n    dimension_grades:\n      - dimension: architecture_alignment\n        grade: B\n    findings:\n      - severity: degraded\n        title: Finding title\n        confidence: 80\n        location: file:line\n        evidence: What was observed.\n        impact: Why this matters.\n        suggested_action: Specific fix or investigation.\n    trends: What improved, degraded, or changed.\n    patterns_observed: De facto architecture patterns.\n\u0060\u0060\u0060\n\n---\n\nStep markers: display \u0060── step N/7: verb\u0060 before each step.\nSteps: orient, select, assess, distill, audit, report, connect.\n\n### Evidence context startup\n\nBefore Step 1, start evaluation state gathering with:\n\n\u0060\u0060\u0060bash\nagentera prime --context inspektera --format json\n\u0060\u0060\u0060\n\nUse the returned \u0060evidence_context\u0060 before raw plan, progress, docs, health, TODO, or decisions artifacts. If \u0060evidence_context.source_contract.complete_for_evidence_context\u0060 is true, do not read raw PLAN, PROGRESS, DOCS, HEALTH, TODO, or DECISIONS artifacts merely to reconstruct evaluation target, plan criteria, progress verification, docs state, health state, TODO state, protected-state checks, version checks, residual risks, fallback commands, caveats, provenance, or non-empty evidence flags.\n\nIf \u0060evidence_context\u0060 is absent, incomplete, or caveated for a state family you need, run the listed \u0060evidence_context.fallback_commands\u0060 first. If those are unavailable, use \u0060capability_context.state.fallback_commands\u0060 from the same prime response. Raw artifact reads are last-resort diagnostics after listed CLI fallbacks, not normal evaluation startup behavior.\n\nPreserve caveats from \u0060evidence_context.state_family_caveats\u0060, \u0060evidence_context.residual_risks.attributed_items\u0060, \u0060decision_context.caveats\u0060, \u0060protected_state_checks.caveats\u0060, and \u0060version_checks.caveats\u0060 when reporting evaluation results. Do not hide, flatten, or reconstruct stale app/profile state, compacted decisions, protected-state boundaries, unavailable version evidence, absent publication or remote evidence, manual-check states, or residual risks. These caveats calibrate confidence; they are not approval to refresh installed apps, refresh profile state, read or edit \u0060.agentera/vision.yaml\u0060, read or edit objective state, contact remotes or registries, or invent missing history.\n\n### Decision satisfaction authority\n\nWhen an audit touches decision satisfaction, agents may mark provisional\nsatisfaction with evidence only. Inspektera must not mark, infer, or\nuser-confirm final satisfaction; only the user confirms final satisfaction. If\ndecisions are compacted, missing satisfaction state, open, provisional, or\nreview-needed, preserve the caveat and review pressure in findings and residual\nrisks instead of reconstructing hidden outcomes or claiming automation proved\nintent.\n\n## Step 1: Orient\n\nUse complete \u0060evidence_context\u0060 first for the evaluated target, current plan criteria, latest progress verification, docs state, health state, TODO state, decision caveats, protected-state checks, version checks, and residual risks. Only run listed CLI fallbacks before raw artifact reads when the context is incomplete for the state needed.\n\n1. **Health state**: use \u0060evidence_context.health_state\u0060 for prior audit findings, grades, current-state status, and caveats.\n2. **Protected-state boundary**: use \u0060evidence_context.protected_state_checks\u0060 and preserve any not-checked-by-design caveats instead of reading protected state.\n3. **Decision context**: use \u0060evidence_context.decision_context\u0060 for decision caveats. Findings contradicting deliberate decisions are not findings.\n4. **TODO state**: use \u0060evidence_context.todo_state\u0060 for known problems. Don't re-report unless worsened.\n5. **Progress verification**: use \u0060evidence_context.progress_verification\u0060 for recent-cycle verification and caveats.\n5b. **Change magnitude**: run \u0060git log --stat\u0060 on commits since the last health audit timestamp to estimate total change volume. If the audit timestamp is unavailable, skip; default depth applies.\n5c. **Plan context** (for artifact current-state review): use \u0060evidence_context.evaluation_target\u0060 and \u0060evidence_context.plan_criteria\u0060 for the plan-relative baseline. If the evidence context reports no target, missing criteria, or missing current-state baseline, preserve that caveat; do not reconstruct it from raw plan state during normal startup.\n6. **Decision profile**: use profile/app caveats already attributed in \u0060evidence_context.residual_risks\u0060; stale or unavailable profile state calibrates confidence but is not approval to refresh profile state or read profile directly during startup.\n7. **Project discovery**: map directory structure, read dependency manifests, README, CLAUDE.md, AGENTS.md, identify language/stack/build commands, \u0060git log --oneline -20\u0060\n\nBefore proceeding: in your response, list the key structural facts (module boundaries, dependency patterns, test coverage gaps) you observed. These survive context compaction.\n\n**Exit-early stop condition**: If \u0060git diff\u0060 since the last \u0060evidence_context.health_state\u0060 audit timestamp shows no file changes, report exit signal \u0060complete: no changes since last audit\u0060 and stop.\n\n---\n\n## Step 2: Select dimensions\n\nChoose dimensions based on the codebase and user request. Not every dimension applies; a 200-line CLI doesn't need the same audit as a monorepo.\n\n### Available dimensions\n\n| Dimension | What it evaluates | When to include |\n|-----------|-------------------|-----------------|\n| **Architecture alignment** | Does the code match the stated architecture? Pattern mismatches, module boundary violations, layering breaks. | VISION.md or README describes architecture |\n| **Pattern consistency** | Are patterns used consistently? Naming, error handling, structure, abstractions. | Any codebase with 5+ modules or files |\n| **Coupling health** | Hidden dependencies, circular imports, god modules, inappropriate intimacy. | Any codebase with multiple modules |\n| **Complexity hotspots** | Functions too long, deeply nested, high fan-out, accumulated conditionals. | Any codebase |\n| **Test health** | Coverage gaps, test quality, test-to-code ratio, tests testing behavior vs implementation. | Project has tests |\n| **Dependency health** | Outdated deps, security advisories, unused deps, dep sprawl, pinning discipline. | Project has external dependencies |\n| **Version health** | Unreleased significant changes: \u0060feat\u0060/\u0060fix\u0060 commits since the last version bump. | DOCS.md has a \u0060versioning\u0060 convention block |\n| **Artifact freshness** | Are state artifacts current relative to plan activity or recent development? Protected health dimension label; current prose should call the work artifact current-state review. Detects artifacts that should have been updated but weren't. | Plan context available (PLAN.md with \u0060Created\u0060 date) or PROGRESS.md has entries |\n| **Prose health** | Do artifact entries respect the writing rules? Checks verbosity overruns, abstraction creep, and filler accumulation across all project artifacts. | Project has 3+ artifact files |\n| **Security hygiene** | Hardcoded secrets, dangerous function calls, basic injection patterns. Lightweight regex-based scan, not a replacement for dedicated security tooling. | Any codebase |\n\n### Depth guidance\n\nWhen change magnitude was derived in Step 1, apply advisory depth scaling:\n\n- **Light changes** (roughly ≤5 files, ≤200 lines since last audit): prioritize dimensions most relevant to the changed areas. Skip dimensions with no intersection.\n- **Standard changes** (default): assess all applicable dimensions at normal depth.\n- **Heavy changes** (roughly ≥20 files or architectural-scope commits): assess all applicable dimensions and increase evidence collection depth. Read more files per dimension, trace more dependency paths, check more edge cases.\n\nThese thresholds are guidelines, not hard rules. Use judgment: a 6-file change touching a critical security module warrants thorough depth, while a 25-file rename is light.\n\n**User specified dimensions**: audit only those.\n**Full audit or unspecified**: auto-select all applicable. Report selections before proceeding.\n\n---\n\n## Step 3: Assess\n\nLead the assessment with your overall interpretation: what stands out, what's changed, where attention should go. Then the per-dimension breakdown provides the evidence.\n\nLaunch parallel agents, one per dimension. Each receives the dimension definition, language-specific commands from \u0060references/audit-commands.md\u0060 (at v2 skill location \u0060skills/agentera/references/audit-commands.md\u0060), relevant context files, the confidence scoring rubric, and instructions to return structured findings.\n\n**Before deep analysis**: run the quick checklist for a rapid pass/fail sweep. Dimensions passing all items can be audited at lower priority.\n\n\u0060\u0060\u0060\nYou are auditing the [dimension] health of [project].\n\n## What to evaluate\n[Dimension-specific instructions from below]\n\n## Evidence standard\nEvery finding MUST include:\n- Specific file and line references\n- Quoted code showing the issue\n- Explanation of why it matters\n- Confidence score (0-100)\n\n### Citation standard (WARN and FAIL findings)\nEvery warning or critical finding MUST carry a reproducible anchor:\n- **Health audit findings**: \u0060location: <file>:<line>\u0060 in health.yaml (or \u0060not-applicable: <reason>\u0060 when no file anchor exists)\n- **Orkestrera evaluation reports**: \u0060citation: <file>:<line>\u0060 per row (schema: \u0060agentera.inspekteraEvaluationReport.v1\u0060 in \u0060references/cli/capability-instruction-contract.yaml#evaluator_handoff\u0060)\n- **WARN rows with file:line citations**: include \u0060verify_command\u0060 with the exact \u0060grep\u0060 or \u0060git show\u0060 invocation that reproduces the evidence at the cited line when re-run\n\nProse-only evidence for WARN/FAIL findings is incomplete. The orchestrator treats missing or invalid citations as evaluation failures.\n\n## Presenting findings\nIntroduce each finding conversationally before the structured evidence. The colleague\nsays \"hey, I noticed this\" instead of just dumping a finding card. Lead with why it caught your eye and what it means, then back it up with the evidence block.\n\n## Confidence scoring (protocol: CS1-CS5)\n- 90-100 (CS1): Definitely a real issue. Verified by reading the code. Clear impact.\n- 70-89 (CS2): Very likely a real issue. Strong evidence, but some context might justify it.\n- 50-69 (CS3): Possibly an issue. The pattern is suspicious but could be intentional.\n- 30-49 (CS4): Uncertain. Might be an issue, might be a reasonable tradeoff.\n- 0-29 (CS5): Speculative. Flagging it but wouldn't be surprised if it's fine.\n\n## What is NOT a finding\n- Pre-existing patterns that are consistent and deliberate\n- Things a linter or type checker would catch (assume CI handles those)\n- Subjective style preferences not grounded in stated project principles\n- Known issues already tracked in TODO.md\n- Intentional decisions documented in DECISIONS.md\n\u0060\u0060\u0060\n\n### Architecture alignment\n\nCompare codebase to stated architecture:\n\n- Read VISION.md (or README.md architecture section) for intended structure\n- Map actual module boundaries, dependency graph, data flow\n- Identify mismatches from stated architecture\n- Check layering and boundary cleanliness\n- Extract \"Patterns Observed\": de facto architecture independent of documentation\n\nNo documented architecture? Extract and report de facto; note absence as a finding.\n\n### Pattern consistency\n\nCheck consistency across the codebase:\n\n- Error handling (returns vs throws vs error types)\n- Naming (singular vs plural, prefixes, casing)\n- Module structure and layout similarity\n- Competing abstractions for the same concept\n- Duplicated logic that should be shared\n- Config handling (env vars vs files vs flags)\n\nFocus on inconsistencies between similar things, not whether the chosen pattern is \"best.\"\n\n### Coupling health\n\nEvaluate coupling and dependency structure:\n\n- Map import graphs, identify circular dependencies\n- Find god modules (too many dependents or dependencies)\n- Check for inappropriate intimacy (reaching into internals)\n- Evaluate interface width: narrow boundaries or exposing everything?\n- Check hidden coupling via shared mutable state, global config, side effects\n\nUse language tools (\u0060go list\u0060, \u0060madge\u0060, import analysis). If unavailable, trace imports manually on highest-risk modules.\n\n### Complexity hotspots\n\nFind accumulating complexity:\n\n- Long functions (generally 50+ lines), deep nesting (3+ levels)\n- High fan-out, growing switch/match statements, many parameters (5+)\n- Files growing cycle over cycle (check git history)\n\nPrioritize high-change files: frequently modified + complex = high risk.\n\n### Test health\n\nEvaluate test suite quality and coverage:\n\n- Run coverage tools if available, otherwise estimate from file analysis\n- Identify critical paths with no coverage\n- Check: testing behavior or implementation? Excessive mocking? Brittle assertions?\n- Evaluate test naming: can you understand what failed from the name alone?\n- Check test-to-code ratio per major module\n- Check test proportionality against contract: default is one pass + one fail per testable unit. Flag under-testing and over-testing.\n\nDon't just report a number. Identify the *highest-risk* coverage gaps.\n\n### Dependency health\n\nEvaluate dependency management:\n\n- Outdated deps (package manager audit/outdated commands)\n- Known security vulnerabilities (npm audit, safety check, govulncheck)\n- Unused deps (installed but not imported)\n- Dep sprawl relative to project scope\n- Pinning discipline (pinned or floating?)\n- Vendored vs remote consistency\n\n### Version health\n\nOnly run this dimension if DOCS.md exists and contains a \u0060versioning\u0060 convention block. Skip entirely if the convention is absent.\n\n- Read DOCS.md \u0060Conventions.versioning\u0060 to identify the version file(s) and bump trigger rules\n- Run \u0060git log --oneline\u0060 to find \u0060feat\u0060 and \u0060fix\u0060 commits since the last modification date of the version file(s)\n- Count unbumped \u0060feat\u0060/\u0060fix\u0060 commits and note the age of the oldest one\n- Severity: warning (SF2) if 1-4 unbumped commits or age ≤ 7 days; critical (SF1) if 5+ unbumped commits or age > 7 days\n- If no \u0060feat\u0060/\u0060fix\u0060 commits have landed since the last bump, this dimension is healthy with no finding\n\n### Artifact current-state review\n\nEvaluates whether state artifacts are current relative to plan activity or recent development. The persisted health dimension label remains \u0060Artifact freshness\u0060; current prose should call the work artifact current-state review. Uses the staleness convention from contract.\n\n**With plan context** (PLAN.md has a created date and task execution history):\n\n- Read the plan's \u0060Created\u0060 date from its HTML comment metadata\n- Identify which capabilities were dispatched during the plan by scanning task entries and PROGRESS.md cycle logs\n- For each dispatched capability, look up its expected artifacts in the contract staleness detection mapping\n- Check each expected artifact's last modification date: \u0060git log -1 --format=%aI -- <path>\u0060\n- An artifact is **stale** if its last modification predates the plan's creation date AND the capability that owns it was dispatched at least once during the plan\n- Severity: warning (SF2, confidence 70+). Plan-relative staleness carries causal evidence.\n- Artifacts that a capability reads but does not produce are not staleness candidates\n\n**Without plan context** (no PLAN.md, or PLAN.md has no created date):\n\n- Fall back to PROGRESS.md recency: an artifact is potentially stale if it was not modified since the most recent PROGRESS.md cycle entry date\n- If PROGRESS.md has no entries (fresh project), no staleness check applies\n- Severity: info (SF3, confidence 50-60). The fallback is advisory, not authoritative.\n\n**Handling**: stale artifact findings are reported like any other dimension finding but noted as context for the next plan cycle, not as blocking errors.\n\n### Prose health\n\nEvaluate artifact prose quality against the three Self-Audit Protocol rules. Use routine CLI state first for artifact-backed context, including \u0060agentera decisions --format json\u0060 for DECISIONS.md. Preserve returned decision \u0060missing_fields\u0060, \u0060compacted\u0060, \u0060caveats\u0060, and \u0060satisfaction.review_needed\u0060 pressure; raw decision artifact reads are for artifact-quality inspection, corruption diagnostics, or CLI defects, not normal post-CLI context recovery. Read all project artifacts (PROGRESS.md, DECISIONS.md, PLAN.md, HEALTH.md, TODO.md, CHANGELOG.md, VISION.md, DESIGN.md, DOCS.md) and check each entry when the prose-health audit explicitly requires raw artifact prose.\n\n**Rule 1: Verbosity overrun**: approximate word count per entry. Compare against per-entry budgets. Entries exceeding their budget by 50%+ are findings.\n\n**Rule 2: Abstraction creep**: scan each entry for ≥1 concrete anchor (file path with extension, line number, commit hash with 7+ hex chars, metric value with unit, identifier such as function/class/variable name, direct quote in quotes attributed to a source). Entries with zero concrete anchors are findings.\n\n**Rule 3: Filler accumulation**: scan each entry against banned verbosity patterns. Flag entries containing: meta-commentary about writing, hedging qualifiers, redundant transitions, self-referential process narration, filler introductions, summary preambles, excessive justification.\n\n### Security hygiene\n\nLightweight regex-based scan for common security anti-patterns. This is a surface-level check, not a replacement for dedicated security analysis. Always recommend specialized tools for comprehensive coverage.\n\n**What to scan**:\n\n- **Hardcoded secrets**: API key patterns, password assignments, token strings in source, private keys in files\n- **Dangerous function calls**: \u0060eval()\u0060 on variables or user input, \u0060exec()\u0060 with string concatenation, subprocess/os.system with unsanitized input\n- **Basic injection patterns**: SQL string concatenation, unsanitized shell command construction\n\n**How to scan**: Use Grep with targeted patterns across the codebase. Focus on source files, not vendored dependencies, build artifacts, or lock files. Exclude \u0060.git/\u0060, \u0060node_modules/\u0060, \u0060vendor/\u0060, \u0060__pycache__/\u0060, and similar directories.\n\n**Severity assignment**:\n\n- Hardcoded secrets: warning (SF2, confidence 75-90)\n- Dangerous function calls: warning (SF2) or critical (SF1) depending on user input flow\n- Injection patterns: warning (SF2, confidence 60-80)\n\n**Scope limitation notice**: every security hygiene finding MUST include a footer recommending dedicated security tools for comprehensive analysis.\n\n---\n\n## Step 4: Distill\n\nAfter all agents complete:\n\n1. **Filter**: discard findings below 50 confidence. Mark 50-69 as \"info\" (SF3) regardless of apparent severity.\n2. **Deduplicate**: merge by preference: (1) fullest context, (2) most evidence-rich dimension, (3) most recent. Preserve complementary evidence from discarded findings.\n3. **Cross-reference** against DECISIONS.md and TODO.md using \u0060agentera decisions --format json\u0060 for normal decision context:\n   - Matches known decision → discard or downgrade to info (SF3)\n   - Matches known issue → \"already tracked\", skip\n   - Genuinely new → include at full severity\n4. **Grade** each dimension:\n   - **A**: No critical/warning findings. **B**: No critical, some warnings.\n   - **C**: 1-2 critical or many warnings. **D**: Multiple critical.\n   - **F**: Pervasive critical findings.\n5. **Trajectory**: compare to prior HEALTH.md: improved (VT12), degraded (VT13), stable dimensions. Calculate overall trajectory.\n\n---\n\n## Step 5: Pre-write self-audit\n\nPre-write self-audit: run \u0060agentera lint --artifact <ARTIFACT> --text \"<DRAFT>\"\u0060 (or \u0060--file <PATH>\u0060; schema names such as \u0060decisions\u0060 auto-resolve the artifact file when no input is given) on the draft entry to check verbosity overruns (per-artifact budget), abstraction creep (>=1 concrete anchor), and filler accumulation (banned patterns table).\nMax 3 revision attempts. Flag with [post-audit-flagged] if still failing.\n\nNarration voice (riff, don't script):\n\"Tightening this up...\" · \"Cutting the filler first...\" · \"One more pass...\"\n\n---\n\n## Step 6: Report\n\nAssess each dimension in your response. Write ONLY grade, trajectory marker, and finding summary per dimension to HEALTH.md. No reasoning in the artifact; the conversation preserves analysis, the artifact preserves conclusions.\n\nOutput constraint per contract token budgets. Letter grade + ≤3 sentences justification per dimension.\n\nWhen updating existing HEALTH.md entries (e.g., updating patterns observed), edit the specific YAML entry rather than rewriting unrelated history. Append new audit entries.\n\nWrite the audit results to \u0060HEALTH.md\u0060 using its resolved YAML path (append new audit, keep prior audits for trajectory history) and present to the user.\n\nAfter writing a new audit entry to HEALTH.md, apply the schema COMPACTION rules before writing if thresholds are exceeded: keep 10 full audits, keep up to 40 one-line archive entries, and drop beyond 50 total.\n\nArtifact writing follows contract Artifact Writing Conventions: banned verbosity patterns, 25-word sentence cap, preferred vocabulary, and lead-with-conclusion structure.\n\n### Report structure\n\n\u0060\u0060\u0060markdown\n## Audit N · YYYY-MM-DD\n\n**Dimensions assessed**: [list]\n**Findings**: X critical, Y warnings, Z info (N filtered by confidence)\n**Overall trajectory**: ⮉ improving | stable | ⮋ degrading vs Audit N-1\n**Grades**: Architecture [B] | Patterns [A] | Coupling [C] | Complexity [B] | Tests [D] | Deps [A] | Security [A]\n\n### [Dimension Name]: [Grade]\n\n#### ⇶ [Finding title], critical (confidence: N/100)\n#### ⇉ [Finding title], warning (confidence: N/100)\n#### ⇢ [Finding title], info (confidence: N/100)\n- **Location**: \u0060file:line\u0060 (or module/package)\n- **Evidence**: [quoted code or structural observation]\n- **Impact**: [what breaks, degrades, or risks]\n- **Suggested action**: [specific fix, investigation, or refactor]\n\n[Repeat for each finding, ordered by severity then confidence]\n\n### Trends vs Audit N-1\n- **Improved**: [what got better and why]\n- **Degraded**: [what got worse and why]\n- **New findings**: [issues not present in prior audit]\n- **Resolved**: [prior findings no longer present]\n\n### Patterns Observed\n[De facto architecture patterns extracted, the \"what IS\" independent of what's stated.]\n- Module structure: [how code is organized]\n- Error handling: [predominant pattern]\n- Testing approach: [how tests are structured]\n- Dependency patterns: [how deps are managed]\n\u0060\u0060\u0060\n\n---\n\n## Step 7: Connect\n\nFeed actionable findings into the suite:\n\n1. **TODO.md**: for each critical finding not already tracked, offer to add under the appropriate severity section.\n   Severity mapping (protocol: SM1-SM3): critical (SF1) → \u0060## ⇶ Critical\u0060 (SI1), warning (SF2) → \u0060## ⇉ Degraded\u0060 (SI2), info (SF3) → \u0060## ⇢ Annoying\u0060 (SI4). Each entry is a checkbox line: \u0060- [ ] [finding description]\u0060. Get user confirmation before writing.\n   Output constraint per contract token budgets.\n2. **VISION.md**: if architecture has intentionally evolved past stated architecture, suggest updating via ❈ resonera.\n3. **Present findings** and ask if the user wants to: file to TODO.md, deliberate via ❈ resonera, deep-dive on a dimension, or investigate a specific finding.\n\n---\n\n## Safety rails\n\n<critical>\n\n- NEVER modify code. Inspektera audits; other capabilities fix.\n- NEVER file issues to TODO.md without explicit user confirmation.\n- NEVER present speculative findings (confidence < 50) as definitive problems.\n- NEVER ignore DECISIONS.md context. If a finding contradicts a deliberate decision,\n  it is not a finding but an implementation of that decision. Discard or downgrade.\n- NEVER report known issues already tracked in TODO.md as new findings.\n- NEVER flag subjective style preferences as findings unless they violate stated principles\n  in VISION.md, CLAUDE.md, or the decision profile.\n- NEVER run destructive commands or install packages. Read-only assessment.\n\n</critical>\n\n---\n\n## Exit signals\n\nReport one of these statuses at workflow completion (protocol refs: EX1-EX4).\n\nFormat: \u0060─── ⛶ inspektera · status ───\u0060 followed by a summary sentence.\nFor flagged, stuck, and waiting: add \u0060▸\u0060 bullet details below the summary.\n\n- **complete** (EX1): All selected audit dimensions were assessed, findings were synthesized, grades were assigned, HEALTH.md was updated, and the user was presented with actionable results.\n- **flagged** (EX2): The audit completed but with notable caveats: one or more dimensions had to be skipped due to missing tooling, confidence was too low to grade a dimension reliably, or critical findings were discovered that require urgent attention beyond the audit scope.\n- **stuck** (EX3): Cannot complete the audit because the project is inaccessible, required language tooling is unavailable and manual analysis is not feasible, or filing findings to TODO.md was declined by the user and the results cannot be safely surfaced any other way.\n- **waiting** (EX4): The audit target is ambiguous: no project was identified, the codebase is too incomplete to assess meaningfully, or the user's request specifies dimensions that cannot be evaluated without additional information.\n\n---\n\n## Cross-capability integration\n\nInspektera is part of a twelve-capability suite. It is the feedback loop, the capability that tells realisera whether its work is making things better.\n\n### Inspektera feeds ⧉ realisera\n\nCritical and warning findings filed to TODO.md become candidates for realisera's work selection. The severity mapping ensures structural problems compete fairly with feature work. The \"Patterns Observed\" section helps realisera understand the codebase's de facto architecture when planning changes.\n\n### Inspektera feeds ❈ resonera\n\nWhen the audit reveals an architecture mismatch, suggest ❈ resonera before fixes begin.\n\nUse it when code has moved past stated architecture or competing patterns need a decision.\n\n### Inspektera feeds ≡ planera\n\nWhen the audit reveals multiple related structural issues, suggest ≡ planera to create a remediation plan. The plan's acceptance criteria give inspektera concrete targets to verify in the next audit.\n\n### Inspektera feeds ⎘ optimera\n\nWhen a dimension grade is poor and the improvement is measurable (test coverage, dependency count, complexity score), the finding can become an optimization objective. Suggest ⎘ optimera when the metric and direction are clear.\n\n### Inspektera reads ⧉ realisera output\n\nPROGRESS.md tells inspektera what was built recently. Recent changes are higher-priority audit targets because they're the most likely source of regressions or pattern breaks. Cycle count since last audit signals when a health check is overdue.\n\n### Inspektera reads ❈ resonera output\n\nDECISIONS.md explains why things are the way they are. Findings that contradict deliberate decisions are not findings. This prevents inspektera from flagging intentional tradeoffs as problems.\n\n### Inspektera reads ◰ visualisera output\n\nDESIGN.md provides visual identity constraints that inspektera can audit for consistency, checking whether the codebase respects the declared design tokens and patterns.\n\n### Inspektera is informed by ♾ profilera\n\nThe decision profile calibrates what \"healthy\" means for this user. A user who values simplicity over flexibility will have different complexity thresholds than one who values extensibility. High-confidence quality preferences from the profile weight the grading.\n\n---\n\n## Getting started\n\n### First audit\n\n1. \u0060/agentera audit\u0060: runs a full audit across all applicable dimensions, bootstraps HEALTH.md\n2. Review findings, file critical ones to TODO.md\n3. \u0060/agentera build\u0060: next cycle picks up the filed issues and starts fixing\n\n### Periodic health checks\n\nRun ⛶ inspektera every 5-10 realisera cycles, or when:\n\n- A major feature was added\n- Significant refactoring occurred\n- The codebase \"feels\" harder to work in\n- Before a major architectural decision (to understand current state)\n\nHej mirrors this cadence through hybrid audit staleness: \u0060agentera hej\u0060 marks a health audit stale when days since the latest audit date reach \u0060AGENTERA_INSPEKTERA_MAX_AGE_DAYS\u0060 (default 30) or progress cycles after that audit date reach \u0060AGENTERA_INSPEKTERA_MAX_CYCLES\u0060 (default 10). Either axis exceeding its threshold is enough; when progress is absent, time-only evaluation still applies.\n\n### Targeted audits\n\n\u0060\u0060\u0060\n/agentera audit architecture coupling\n\u0060\u0060\u0060\n\nSpecify dimensions to narrow the audit scope. Useful after specific kinds of changes.\n\n### After an audit\n\n- **Good grades (A/B)**: Celebrate. Keep building.\n- **Mixed grades (C)**: File the critical findings, deliberate on the warnings.\n- **Poor grades (D/F)**: Consider pausing feature work. Use ❈ resonera to deliberate on priorities, then ⧉ realisera to fix the structural problems before building more.\n"`);
+export default instructions;
+//# sourceMappingURL=instructions.js.map

package/dist/capabilities/inspektera/instructions.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"instructions.js","sourceRoot":"","sources":["../../../src/capabilities/inspektera/instructions.ts"],"names":[],"mappings":"AAAA,kFAAkF;AAClF,qFAAqF;AACrF,yFAAyF;AACzF,MAAM,CAAC,MAAM,YAAY,GAAW,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,CAAA,03gCAA03gC,CAAC,CAAC;AACr7gC,eAAe,YAAY,CAAC"}

package/dist/capabilities/inspirera/instructions.js

@@ -0,0 +1,6 @@
+// Source: skills/agentera/capabilities/inspirera/instructions.md (relocated D65)
+// Markdown body lifted verbatim; the JSON literal below round-trips to byte-for-byte
+// equivalence with the deleted file (whitespace allowed to differ at line endings only).
+export const instructions = JSON.parse(String.raw `"# INSPIRERA\n\n**Insight Navigation: Source Pattern Identification and Resonance. Evaluate, Reframe, Assimilate**\n\nAnalyze an external resource and map its ideas to a target project. Output a structured markdown analysis the user can navigate and act on.\n\nSkill introduction: \u0060─── ⬚ inspirera · analysis ───\u0060\n\n---\n\n## Visual identity\n\nGlyph: **⬚** (protocol ref: SG10). Used in the mandatory exit marker.\n\n---\n\n## State artifacts\n\nNo dedicated state file. Writes to other capabilities' artifacts.\n\n| Artifact | Purpose | Path |\n|----------|---------|------|\n| TODO.md | File actionable findings for realisera (severity per protocol SF1-SF3) | \u0060TODO.md\u0060 (per DOCS.md mapping) |\n| VISION.md | Refine direction when inspiration shifts thinking | \u0060VISION.md\u0060 (per DOCS.md mapping) |\n| PROFILE.md | Decision profile for persona-grounded applicability judgments | \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060 (global, not project-scoped) |\n\n### Artifact path resolution\n\nBefore reading or writing any artifact, check if .agentera/docs.yaml exists. If it has an Artifact Mapping section, use the path specified for each canonical filename (TODO.md, VISION.md, etc.). If .agentera/docs.yaml doesn't exist or has no mapping for a given artifact, use the default layout: TODO.md, CHANGELOG.md, and DESIGN.md at the project root; canonical VISION.md at .agentera/vision.yaml; other agent-facing artifacts at .agentera/*.yaml. This applies to all artifact references in this capability, including cross-capability writes (TODO.md, VISION.md).\n\nPROFILE.md is global, not project-scoped. Its path is determined by profilera: \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060 (default: \u0060$XDG_DATA_HOME/agentera/PROFILE.md\u0060). Check the profilera-determined path directly rather than falling back to the project root.\n\n### Contract values\n\nContract values are inlined where referenced. Visual tokens from protocol: confidence tokens VT9-VT11 (━/─/┄), list item VT15 (▸), inline separator VT16 (·), section divider VT14. Skill glyph SG10 for exit markers. Exit signals EX1-EX4 for status reporting. Severity finding levels SF1-SF3 for TODO.md entries.\n\n\u0060references/contract.md\u0060 (at the v2 skill location \u0060skills/agentera/references/contract.md\u0060) remains available as a full-spec reference for ambiguous cases or cross-checking.\n\n---\n\nStep markers: display \u0060── step N/5: verb\u0060 before each step.\nSteps: identify, read, explore, map, deliver.\n\n---\n\n## Step 1: Identify source and target\n\nFrom the user's message, extract:\n\n- **Source**: the external URL (GitHub repo, article, docs, HN thread, etc.)\n- **Target**: the user's project, which could be any of:\n  - A **GitHub repo URL** → explore via the optional GitHub MCP integration\n  - A **local path** or project name → explore via filesystem tools\n  - The **current working directory** → if the user says \"my project\" / \"what I'm building\" without a URL, and they're clearly working in a project, treat cwd as the target\n  - **Absent** → if truly no target is implied, skip Steps 3–4 and do source-only analysis\n\n---\n\n## Step 2: Read the source\n\nThis should feel like a colleague diving into something interesting, genuinely curious, reading deeply, forming opinions as you go. Not a report generator collecting data points.\n\n### GitHub repos\n\nUse the optional GitHub MCP integration to explore deeply:\n\n1. List root directory structure\n2. Read README\n3. Read key source directories until you understand: core abstractions, design patterns,\n   notable primitives, dependencies, clever approaches worth borrowing\n\nGo deep and don't stop at the README. If the optional GitHub MCP integration\nreturns errors, fall back to public pages or note the limitation.\n\n### Articles, blog posts, docs pages\n\nFetch full content. Extract core thesis, named concepts/patterns, code samples, and referenced tools. If paywalled, try reader-mode variant; if that fails, note the limitation.\n\n### Hacker News threads\n\nRead both the linked article and top comments. HN comments often contain the most useful distillation. Treat as signal.\n\n### Known libraries\n\nFor well-known libraries, also check context7 for up-to-date docs beyond the README.\n\nBefore proceeding to target analysis: in your response, list the 3-5 most transferable concepts from the source. These survive if the source file reads are cleared.\n\n---\n\n## Step 3: Read the target project\n\nChoose the exploration strategy based on the target type identified in Step 1.\n\n### Local projects (current directory or local path)\n\nCommon case. Use filesystem tools (faster, includes uncommitted work):\n\n1. \u0060Glob\u0060 to map the directory structure (e.g. \u0060**/*.{ts,go,py,rs}\u0060)\n2. Read README.md if one exists\n3. Check dependency manifests (\u0060package.json\u0060, \u0060go.mod\u0060, \u0060Cargo.toml\u0060, \u0060pyproject.toml\u0060, etc.)\n4. \u0060Grep\u0060 for patterns, imports, or abstractions relevant to the source's concepts\n5. Read key source files to understand architecture and current patterns\n\n### Remote GitHub repos\n\nUse the optional GitHub MCP integration:\n\n1. List the root directory structure\n2. Read the README\n3. Read dependency manifests and key source files\n\n### Build understanding of\n\nLanguage, stack, dependencies, architecture, patterns, and problems being solved.\n\n### Check for existing usage\n\nDoes the target already use the source (or a fork/alternative)?\n\n- **Already using**: \"Getting the most out of it?\" Focus on underused features and better patterns.\n- **Using alternative**: \"Worth switching?\" Compare approaches and migration cost.\n- **Not using**: \"Should you adopt?\" This is the default framing.\n\n---\n\n## Step 4: Map concepts across\n\nWith both codebases understood, reason about applicability:\n\n- What is the source doing that the target should be?\n- Abstractions that simplify current complexity?\n- Patterns the target implements manually or poorly?\n- Primitives worth borrowing or adapting?\n- Source doing something the target does, but better?\n- Fundamentally incompatible? Say so clearly.\n- Adoption cost: one-file change or multi-sprint refactor?\n\n---\n\n## Step 5: Deliver the analysis\n\nThe sharp colleague, here to share what you dug up, not file a report. Open with your take before the structured sections: what excited you, what surprised you, what the user should care about most. \"Here's what I found and what matters for us.\" The structured analysis follows, but the human read comes first.\n\nWrite a **structured markdown analysis**:\n\n### Output format\n\n\u0060\u0060\u0060\u0060markdown\n# [Source Name] → [Target Name]: Cross-Pollination Analysis\n\n## TL;DR\nOne or two sentences. Is this worth pursuing? What's the strongest single takeaway?\n\n## Source Overview\nBrief summary of what the source does and its core design philosophy.\n\n## Key Concepts\n\n### [Concept Name]\nWhat it is, why it's interesting, and concretely where/how it applies to the target.\n\n### [Concept Name]\n...repeat for each significant concept (typically 2–5)\n\nReason through concept applicability in your response text. The Applicability Matrix below\nshould contain only conclusions, not reasoning chains.\nOutput constraint: ≤15 words per matrix cell.\n\n## Applicability Matrix\n\n| Concept | Relevance | Effort | Where in [Target] | Already Partially Done? |\n|---------|-----------|--------|-------------------|------------------------|\n| ...     | High/Med/Low | Low/Med/High | specific module or file | Yes/No |\n\n## What Doesn't Apply\nHonest assessment of concepts/patterns that look interesting but don't fit, and why.\nBeing clear about what *not* to adopt is as valuable as the recommendations.\n\n## Recommended Next Steps\n▸ [action] · [specific file or module]\n▸ [action] · [specific file or module]\nOrdered by value/effort ratio.\n\u0060\u0060\u0060\u0060\n\n**Tone**: direct, technically fluent. Skip empty sections. Lead with highest signal.\n\nOffer to go deeper: prototype a change, explore a concept with code, compare alternatives.\n\n### No target given\n\nSurface transferable concepts in general terms. Skip Applicability Matrix. Ask if the user wants to map to a specific project.\n\n---\n\n## Safety rails\n\n<critical>\n- NEVER modify code in the target project. Inspirera analyzes; other capabilities implement.\n- NEVER write to TODO.md or VISION.md without explicit user confirmation. Present findings and get approval before filing.\n- NEVER present shallow analysis as deep insight. If you haven't read the source thoroughly, say so.\n- NEVER recommend adoption without assessing fit. Every recommendation must consider the target project's constraints, stack, and principles.\n- NEVER fabricate source content. Quote actual code and text from the source.\n</critical>\n\n---\n\n## Exit signals\n\nReport one of these statuses at workflow completion (protocol refs: EX1-EX4).\n\nFormat: emit \u0060⬚ inspirera · <status>\u0060 on its own line, followed by a one-sentence summary. For \u0060flagged\u0060 (EX2), \u0060stuck\u0060 (EX3), and \u0060waiting\u0060 (EX4), add a ▸ (VT15) bullet below the summary identifying what needs attention. The exit marker uses inspirera's canonical glyph ⬚ (SG10, U+2B1A).\n\n- **complete** (EX1): Source was read deeply, target project was explored (if provided), concept mapping was completed, and a structured analysis with applicability matrix and recommended next steps was delivered.\n- **flagged** (EX2): Analysis completed but with limitations worth surfacing: the source was paywalled or truncated, the target project was inaccessible, or key concepts could not be fully assessed for fit (e.g., incompatible language or paradigm).\n- **stuck** (EX3): Cannot proceed because the source URL is inaccessible and no fallback content is available, or the target project specified does not exist and cannot be located.\n- **waiting** (EX4): The source link was not provided or is malformed, or the target project is genuinely ambiguous and neither the current directory nor context resolves it.\n\n---\n\n## Cross-capability integration\n\nInspirera is part of a twelve-capability suite. Its analysis feeds naturally into the other capabilities.\n\n### Feeding into realisera\n\nAdd actionable findings to the project's TODO.md, classifying each by severity per protocol SF1-SF3. Or refine VISION.md's direction if the inspiration shifts thinking. The next realisera cycle picks up the changes automatically.\n\n### Feeding into optimera\n\nWhen the source contains optimization techniques (performance patterns, algorithm improvements, caching strategies), optimera's Hypothesize step can draw on the analysis for its next experiment.\n\n### Informed by profilera\n\nIf a decision profile exists at \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060, read it directly and use effective confidence to weight applicability judgments. If PROFILE.md is missing, proceed without persona grounding.\n\n### Feeding into visionera\n\nWhen the analysis shifts thinking about the project's direction (a new paradigm, a competitor's approach, or a user need not yet captured), the findings can inform vision refinement. Suggest ⛥ visionera to revisit VISION.md with the new context.\n\n### Feeding into planera\n\nWhen the analysis recommends adopting patterns or libraries, planera can incorporate those recommendations into a plan's design section and task decomposition.\n\n### Feeding into resonera\n\nWhen the analysis surfaces recommendations that require deliberation (competing approaches, unclear adoption cost, or tradeoffs the user needs to resolve), suggest ❈ resonera to think it through before acting. Resonera can evaluate which recommendations are actually worth adopting and capture the reasoning in DECISIONS.md.\n\n---\n\n## Getting started\n\n### Analyze a GitHub repo\n\n\u0060\u0060\u0060\n/agentera research https://github.com/org/repo\n\u0060\u0060\u0060\n\nReads the repo, maps its patterns to your current project.\n\n### Analyze an article or docs page\n\n\u0060\u0060\u0060\n/agentera research https://example.com/blog/interesting-approach\n\u0060\u0060\u0060\n\nExtracts transferable concepts and assesses applicability.\n\n### Feed findings into the development loop\n\nAfter analysis, file actionable findings to TODO.md for ⧉ realisera to pick up, or refine VISION.md if the research shifts your project's direction.\n\n---\n\n## Notes on depth vs. speed\n\n- Read more files, not fewer. Shallow reads produce shallow analysis.\n- Large repos: focus on modules most relevant to the concept, not everything.\n- Explore source and target concurrently where possible.\n- Always use the optional GitHub MCP integration for GitHub URLs.\n"`);
+export default instructions;
+//# sourceMappingURL=instructions.js.map

package/dist/capabilities/inspirera/instructions.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"instructions.js","sourceRoot":"","sources":["../../../src/capabilities/inspirera/instructions.ts"],"names":[],"mappings":"AAAA,iFAAiF;AACjF,qFAAqF;AACrF,yFAAyF;AACzF,MAAM,CAAC,MAAM,YAAY,GAAW,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,CAAA,8kZAA8kZ,CAAC,CAAC;AACzoZ,eAAe,YAAY,CAAC"}

package/dist/capabilities/optimera/instructions.js

@@ -0,0 +1,6 @@
+// Source: skills/agentera/capabilities/optimera/instructions.md (relocated D65)
+// Markdown body lifted verbatim; the JSON literal below round-trips to byte-for-byte
+// equivalence with the deleted file (whitespace allowed to differ at line endings only).
+export const instructions = JSON.parse(String.raw `"# OPTIMERA\n\n**Objective Pursuit: Targeted Iterative Measurement. Experiment, Record, Advance.**\n\nMetric-driven optimization: improve any measurable property one experiment at a time. User defines the objective, agent writes an eval harness, harness becomes the immutable judge. Improve + pass regression = keep; everything else is discarded.\n\nEach invocation = one experiment. \u0060/loop\u0060 handles recurrence.\n\n---\n\n## Visual identity\n\nGlyph: **⎘** (protocol ref: SG7). Used in the mandatory exit marker.\n\n---\n\n## State artifacts\n\nThree artifacts per objective, under \u0060.agentera/optimera/<objective-name>/\u0060, bootstrapped if absent.\n\n| Artifact | Purpose | Bootstrap |\n|----------|---------|-----------|\n| \u0060.agentera/optimera/<objective-name>/objective.yaml\u0060 | What we're optimizing, why, how we measure it, and what \"done\" looks like. | Via inline brainstorm session with the user (see below). |\n| \u0060.agentera/optimera/<objective-name>/harness\u0060 | Eval script that measures the metric. Locked after user approval. | Written by the agent during brainstorm, approved by the user. |\n| \u0060.agentera/optimera/<objective-name>/experiments.yaml\u0060 | Log of every experiment: what was tried, what the metric said, kept or discarded. | First experiment entry in YAML form. |\n\n### Artifact path resolution\n\nBefore reading or writing any artifact, check if \u0060.agentera/docs.yaml\u0060 exists. If it has an Artifact Mapping section, use the path specified for each canonical filename. If \u0060.agentera/docs.yaml\u0060 doesn't exist or has no mapping for a given artifact, use the default layout: TODO.md, CHANGELOG.md, and DESIGN.md at the project root; canonical VISION.md at \u0060.agentera/vision.yaml\u0060; other agent-facing artifacts at \u0060.agentera/*.yaml\u0060. This applies to all artifact references in this capability, including cross-capability reads (\u0060.agentera/decisions.yaml\u0060). objective.yaml and experiments.yaml are NOT resolved via the docs.yaml mapping; they always live under \u0060.agentera/optimera/<objective-name>/\u0060 for whichever objective is active.\n\n### Contract\n\nBefore starting, read \u0060references/contract.md\u0060 (at v2 skill location \u0060skills/agentera/references/contract.md\u0060) for authoritative values: token budgets, severity levels, format contracts, and other shared conventions referenced in the steps below. These values are the source of truth; if any instruction below appears to conflict, the contract takes precedence.\n\n### Benchmark context source contract\n\nFor benchmark-oriented optimization work, start from:\n\n\u0060\u0060\u0060bash\nagentera prime --context optimera --format json\n\u0060\u0060\u0060\n\nUse \u0060benchmark_context\u0060 before direct retained startup benchmark file access. If \u0060benchmark_context.source_contract.complete_for_benchmark_context\u0060 is true, do not read \u0060latest-report.json\u0060, \u0060latest-report.md\u0060, or \u0060runs.jsonl\u0060 during normal Optimera startup. Use the bounded fields in \u0060benchmark_context.latest_report\u0060, \u0060benchmark_context.history_summary\u0060, \u0060benchmark_context.runtime_coverage\u0060, \u0060benchmark_context.state_access_metrics\u0060, \u0060benchmark_context.token_impact\u0060, \u0060benchmark_context.comparison\u0060, \u0060benchmark_context.recommendation\u0060, and \u0060benchmark_context.manual_refresh\u0060 instead.\n\nIf benchmark_context is incomplete, follow \u0060benchmark_context.fallback_commands\u0060 and \u0060benchmark_context.manual_refresh\u0060 first. Direct reads of retained benchmark files are last-resort diagnostics only, and must preserve the context caveats rather than reconstructing hidden state. Never run \u0060mage bench:startupState\u0060 automatically; it is manual-only.\n\nWhen reporting benchmark evidence, preserve caveats about manual-only execution, missing or malformed retained evidence, empty local history, runtime coverage degradation, missing token estimates, non-comparable previous rows, and privacy boundaries. Do not expose raw transcripts, raw corpus files, raw intermediates, raw runtime store paths, raw session IDs, private salts, generated salted hashes, raw benchmark report bodies, or full local benchmark paths.\n\n### objective.yaml\n\nEvergreen. Created via brainstorm on first run, refined only when the user explicitly asks. Outside those two cases, the agent reads it but never writes it. Typical structure:\n\n\u0060\u0060\u0060yaml\ntarget: Optimization target name\nstatus: active\nobjective: >-\n  Precise metric, current value, and target value, for example reduce p95\n  latency of /api/search from 320ms to under 100ms.\nwhy: >-\n  What changes when the target is hit, who benefits, and what tradeoffs matter.\nmeasurement:\n  command: .agentera/optimera/<objective-name>/harness\n  metric: p95_latency_ms\n  direction: lower\n  baseline: 320\n  target: 100\n  budget:\n    runs: 5\n    time_limit: 10m\nconstraints:\n  - Existing tests must pass.\n  - Public API must not change.\nscope:\n  included: [api/search]\n  excluded: [public_api]\n\u0060\u0060\u0060\n\nThe objective must be precise enough to measure, constraints clear enough to enforce, and scope defined enough to prevent wandering.\n\nFixed budgets are part of the measurement contract, not experiment strategy. Keep them in objective.yaml and the locked harness. Do not store budget state in root artifacts, registries, symlinks, or DOCS.md mappings. experiments.yaml records the budget actually used only when that evidence matters to interpret the result.\n\n### \u0060.agentera/optimera/<objective-name>/harness\u0060\n\nScript that measures the metric and outputs structured JSON. Written during brainstorm, approved by the user, then **locked**. Never modified during optimization cycles.\n\nWraps the project's own tooling (test runners, benchmarks, linters) and translates output into a consistent format. The project's tooling is the source of truth.\n\n**Before writing a harness**, inspect the project's existing test, benchmark, lint, or measurement commands. The Agentera app currently ships only the shared contract reference, so harness specifics come from project tooling and the objective's measurement fields.\n\n**Output contract** (minimal):\n\n\u0060\u0060\u0060json\n{\"metric\": <number>, \"direction\": \"higher\"|\"lower\"}\n\u0060\u0060\u0060\n\n**Output contract** (with optional fields for richer signal):\n\n\u0060\u0060\u0060json\n{\"metric\": 85.5, \"direction\": \"higher\", \"unit\": \"%\", \"detail\": \"42/50 tests passing\", \"breakdown\": [{\"name\": \"unit\", \"value\": 95.0}, {\"name\": \"integration\", \"value\": 60.0}]}\n\u0060\u0060\u0060\n\nThe harness is the **immutable ground truth**, separating measurement from optimization. If wrong, the user must explicitly ask to rebuild it.\n\n### experiments.yaml\n\nWhen presenting experiment results, open with your interpretation of what happened before the structured data. \"Here's what I tried and what it told us\"; then the metrics table backs it up. Call out surprises, dead ends, and what the result changes about the approach.\n\n\u0060\u0060\u0060yaml\nexperiments:\n  - number: N\n    timestamp: YYYY-MM-DD HH:MM\n    hypothesis: What we expected to improve and why.\n    method: The approach taken to test the hypothesis.\n    change: One-line summary of the code change.\n    metric:\n      before: 320\n      after: 250\n      direction: lower\n      verdict: better\n    regression: pass\n    status: kept\n    commit: <hash>\n    inspiration: External source, if any.\n    conclusion: What the experiment taught.\n    next: What the result suggests trying next.\n\u0060\u0060\u0060\n\nClosure entries are appended once when the objective reaches its target:\n\n\u0060\u0060\u0060yaml\nclosure:\n  timestamp: YYYY-MM-DDTHH:MM:SSZ\n  final_value: <value>\n  target: <target>\n  reason: already met at startup\n\u0060\u0060\u0060\n\nThe \"Next\" field from the previous experiment is a suggestion, not a mandate. Re-evaluate fresh each cycle based on the full experiment history.\n\n### Experiment history analyzer contract\n\n\u0060npx -y agentera experiments\u0060 is the read-only summary layer for rich experiments.yaml records. It must inspect the active objective directory only. The command never creates root objective artifacts, registries, symlinks, DOCS.md fixed mappings, or sidecar ledgers.\n\n---\n\n## Brainstorm: bootstrapping or refining the objective\n\nThis runs in two situations:\n\n1. **objective.yaml doesn't exist**: the first time optimera runs on a project\n2. **User explicitly asks** to refine the objective (e.g., \"change the target\", \"update objective.yaml\")\n\nIn all other cases, skip straight to the cycle.\n\n### How the brainstorm works\n\nThe sharp colleague figuring out what to optimize. One question at a time, push for precision, push back on vague targets. Call out when an objective is too fuzzy to measure or when constraints are missing.\n\n1. **Objective**: \"What metric, current value, target?\" If code exists, run existing test/bench/lint commands first.\n2. **Motivation**: \"Why does this matter? What breaks at current value? What's possible at target?\"\n3. **Constraints**: \"What must NOT break? Off-limits files? Resource limits?\" If a decision profile exists, propose constraints from it.\n4. **Scope**: \"Which parts to focus on? Where are the biggest gains?\" Read codebase to propose informed boundaries.\n5. **Pre-write self-audit**: run \u0060agentera lint --artifact <ARTIFACT> --text \"<DRAFT>\"\u0060 (or \u0060--file <PATH>\u0060; schema names such as \u0060decisions\u0060 auto-resolve the artifact file when no input is given) on the draft entry to check verbosity overruns, abstraction creep, and filler accumulation. Max 3 revision attempts. Flag with [post-audit-flagged] if still failing.\n6. **Write objective.yaml**: synthesize into a precise charter. Write to \u0060.agentera/optimera/<objective-name>/objective.yaml\u0060. Present for approval.\n7. **Write the eval harness**: use the project's own tooling and the objective's measurement fields. Write \u0060.agentera/optimera/<objective-name>/harness\u0060 so it outputs JSON with at least \u0060metric\u0060 and \u0060direction\u0060. Present, explain, get approval, run once to establish baseline.\n\nArtifact writing follows contract Artifact Writing Conventions: banned verbosity patterns, 25-word sentence cap, preferred vocabulary, and lead-with-conclusion structure.\n\nWhen **refining**, read current objective.yaml, show proposed changes with rationale, get confirmation. If the harness changes, the user must approve the new version. After brainstorm, proceed to experiment 1.\n\n---\n\n## The cycle\n\nSkill introduction: \u0060─── ⎘ optimera · experiment N ───\u0060\n\nStep markers: display \u0060── step N/8: verb\u0060 before each step.\nSteps: orient, analyze, hypothesize, implement, measure, decide, audit, log.\n\n### Step 1: Orient\n\n**Benchmark context**: for benchmark-oriented work, use \u0060benchmark_context\u0060 from \u0060agentera prime --context optimera --format json\u0060 before direct retained benchmark files. Raw benchmark file reads are last-resort diagnostics.\n\n**Active-objective inference**: before reading any per-objective artifact, determine which objective is active by inspecting \u0060.agentera/optimera/\u0060:\n\n- If no objective subdirectories exist, keep the existing new-objective path: run the brainstorm.\n- For each objective subdirectory with an objective.yaml, classify it as closed before any active selection when \u0060status: closed\u0060. Do not reopen closed objectives.\n- If the user explicitly names a closed objective, load its objective.yaml and experiments.yaml read-only for context, summarize that it is closed, and ask before defining successor work.\n- If one or more objective subdirectories exist and all are closed, ask the user for a successor objective.\n- If only one non-closed subdirectory exists, use it.\n- If multiple non-closed subdirectories exist, run \u0060git log -1 --format=%aI -- .agentera/optimera/<name>/experiments.yaml\u0060 for each and pick the one with the most recent modification timestamp.\n- If the result is ambiguous, ask the user to specify the active objective by name.\n\nAll subsequent references to objective.yaml, experiments.yaml, and harness refer to the files under \u0060.agentera/optimera/<active-objective-name>/\u0060.\n\n1. **experiments.yaml**: last 5 experiments only (check for plateau patterns)\n2. **objective.yaml**: the metric, target, constraints, and scope\n3. **Decision profile**: read \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060 directly when it exists. Apply confidence thresholds per contract profile consumption conventions. If missing, proceed without persona grounding but flag it.\n4. **Project discovery** (experiment 1 or when unfamiliar): map directory structure within scope, read dependency manifests, and read README.md, CLAUDE.md, AGENTS.md.\n5. \u0060git log --oneline -20\u0060 for recent changes\n\nBefore experimenting: in your response, list the current baseline, target, status, and constraints from objective.yaml.\n\n**Objective closure procedure**: when closing an objective, update objective.yaml with canonical closed state: \u0060status: closed\u0060, \u0060closed_at: <ISO-8601 UTC timestamp>\u0060, \u0060final_value: <value>\u0060, \u0060target: <target>\u0060, and \u0060reason: <reason>\u0060. Append one experiments.yaml closure entry. Do not append duplicates.\n\n**Exit-early stop condition**: If objective.yaml or experiments.yaml evidence shows the target is already met and the objective is not already closed, run the objective closure procedure with reason \u0060already met at startup\u0060, report exit signal \u0060complete: objective achieved\u0060, and stop before Analyze.\n\n### Step 2: Analyze\n\nRun two things:\n\n**2a. Experiment history analysis**: if experiments.yaml has prior entries, run:\n\n\u0060\u0060\u0060bash\nnpx -y agentera experiments\n\u0060\u0060\u0060\n\nOutputs recent experiment status counts, metric deltas, conclusions, and next-step notes.\n\n**2b. Current metric**: run the eval harness to get the baseline for this experiment:\n\n\u0060\u0060\u0060bash\nchmod +x .agentera/optimera/<objective-name>/harness && .agentera/optimera/<objective-name>/harness\n\u0060\u0060\u0060\n\nParse the JSON output. Record the current metric as the baseline.\n\n**Plateau detection**: if \u0060plateau_detected: true\u0060 (no improvement in 3+ experiments), flag explicitly. Consider a radically different approach, ⬚ inspirera, or escalate to the user.\n\n### Step 3: Hypothesize\n\nFormulate a single, focused hypothesis.\n\nEffort-bias check: if one hypothesis took more effort to construct, reset before selection. Choose by experiment history, expected metric impact, risk, constraints, and smallest falsifiable test; construction effort is not evidence.\n\n1. **Review history**: what's been tried, what worked, what failed?\n2. **Seek inspiration**: for non-trivial domains, 2-3 targeted web queries for techniques, libraries, or patterns.\n3. **Formulate**: \"I expect [change] to improve the metric because [reasoning].\" Must be falsifiable.\n\nBe conservative early; escalate if conservative approaches plateau.\n\n### Step 4: Implement\n\n**Pre-spawn Git commit**: before creating the worktree, commit any pending artifact changes so the subagent branches from current state.\n\n1. Run \u0060git status --porcelain\u0060. If empty, skip to spawn.\n2. Stage only the artifact files this session wrote.\n3. Commit with \u0060chore(optimera): checkpoint before worktree dispatch\u0060. Do not pass \u0060--no-verify\u0060.\n4. If pre-commit hooks reject the commit: fix and retry. If retry also fails, abort the spawn.\n\n**Stale-base awareness**: some harnesses create the worktree branch from \u0060origin/main\u0060 rather than local \u0060HEAD\u0060. Before spawning, run \u0060git rev-list --count origin/main..HEAD\u0060. If the count is greater than zero, the worktree will be based on a stale commit. Proceed with spawn, but in Step 5 do NOT merge the worktree branch: fetch the diff and apply it to the main checkout. Re-run the eval harness in the main checkout.\n\nRuntime subagent mechanisms:\n\n| Runtime | Substrate | Limitation |\n|---------|-----------|------------|\n| Claude Code | Task tool with worktree-aware prompt | Native in-session spawn. |\n| OpenCode | \u0060@<capability>\u0060 descriptors from \u0060~/.config/opencode/agents/*.md\u0060 or a host Task subagent | Same working tree unless this step explicitly creates and targets a manual git worktree. |\n| Codex CLI | \u0060~/.codex/agents/*.toml\u0060 descriptors plus \u0060[agents]\u0060 limits | Agentera setup installs descriptor files; do not write legacy \u0060[agents.<name>]\u0060 config blocks. |\n| Copilot CLI | User-driven \u0060/fleet\u0060 or equivalent host action | No guaranteed programmatic in-session spawn. |\n\nNever spawn workers by running unsupported capability-name CLI commands such as \u0060agentera optimera\u0060; use the runtime-native subagent surface with the experiment prompt below.\n\nSpawn an implementation sub-agent in a worktree (\u0060isolation: \"worktree\"\u0060) with:\n\n- The hypothesis from step 3\n- Relevant context files (objective.yaml, recent experiments, source files being modified)\n- Clear constraint: implement the hypothesis and nothing else\n\n\u0060\u0060\u0060\nYou are implementing one optimization experiment for [project].\n\n## Hypothesis\n[The hypothesis]\n\n## Context\n- Current metric: [value] ([unit])\n- Target: [target value]\n- Scope: [files/modules in scope from objective.yaml]\n\n## Constraints\n- Implement ONLY what the hypothesis describes. No scope creep.\n- Do NOT modify the eval harness at .agentera/optimera/<objective-name>/harness.\n- Do NOT modify objective.yaml or experiments.yaml.\n- Follow existing code patterns and conventions.\n- Read the files you are modifying before changing them.\n- Keep the change as small as possible while testing the hypothesis.\n- If you encounter a bug unrelated to your task, note it but do not fix it.\n\u0060\u0060\u0060\n\nWait for the implementation agent to complete before proceeding.\n\n### Step 5: Measure\n\nAfter implementation completes, run two checks in sequence:\n\n**5a. Regression check**: run the project's existing test/build/lint suite. If the regression check fails, **stop here**. The experiment is discarded. Do not run the eval harness. Log the regression failure and move to Step 7.\n\n**5b. Metric measurement**: run the eval harness. Parse the JSON output. Compare the new metric against the baseline from Step 2.\n\n### Step 6: Decide\n\nPresent the decision conversationally: what the numbers say and what you'd recommend, then the structured gate below makes it official.\n\nApply the decision gate. **Both conditions must be true** to keep an experiment:\n\n1. **Regression check passed** (from Step 5a)\n2. **Metric improved**: the new value is strictly better than the baseline, in the direction declared by the harness (lower for \"lower\", higher for \"higher\")\n\nIf both pass: **keep**. Merge the worktree branch into the current branch. Commit with a conventional commit message:\n\n\u0060\u0060\u0060\nperf(scope): summary of what improved the metric\n\nMetric: <before> → <after> ⮉ (<unit>)\n\u0060\u0060\u0060\n\nIf either fails: **discard**. The worktree is abandoned. No merge. No commit.\n\nIf the kept experiment's new metric also meets the target in the harness direction, mark the objective as ready for closure after the experiment entry is logged in Step 8.\n\n### Step 7: Pre-write self-audit\n\nPre-write self-audit: run \u0060agentera lint --artifact <ARTIFACT> --text \"<DRAFT>\"\u0060 (or \u0060--file <PATH>\u0060; schema names such as \u0060decisions\u0060 auto-resolve the artifact file when no input is given) on the draft entry to check verbosity overruns (per-artifact budget), abstraction creep (>=1 concrete anchor), and filler accumulation (banned patterns table). Max 3 revision attempts. Flag with [post-audit-flagged] if still failing.\n\nNarration voice (riff, don't script):\n\"Tightening this up...\" · \"Cutting the filler first...\" · \"One more pass...\"\n\n### Step 8: Log\n\nSummarize the experiment for the user before writing the log: what moved, what didn't, and what it suggests trying next. Then write the structured record.\n\nUpdate **experiments.yaml**: append the experiment entry. Output constraint per contract token budgets.\n\nIf Step 6 marked the objective as ready for closure, immediately run the objective closure procedure with reason \u0060experiment met target\u0060. This closure is part of the same log step, after the experiment result is recorded.\n\nAfter writing a new experiment entry to experiments.yaml, apply the schema COMPACTION rules before writing if thresholds are exceeded: keep 10 full experiments, keep up to 40 one-line archive entries, and drop beyond 50 total.\n\nArtifact writing follows contract Artifact Writing Conventions: banned verbosity patterns, 25-word sentence cap, preferred vocabulary, and lead-with-conclusion structure.\n\nThen stop. One experiment complete.\n\n---\n\n## Safety rails\n\n<critical>\n\n- NEVER push to any remote. Local commits only.\n- NEVER modify the eval harness (\u0060.agentera/optimera/<objective-name>/harness\u0060) during an optimization cycle. Only touch it during a brainstorm (bootstrap or user-requested refinement).\n- NEVER modify objective.yaml during a cycle except to record canonical closure when the target is met. Other objective.yaml edits only happen during brainstorm or refine.\n- NEVER bypass the project's test/lint/build suite. Regression check before every metric measurement. Regression failure = automatic discard.\n- NEVER modify git config or skip git hooks.\n- NEVER force push, amend published commits, or run destructive git operations.\n- NEVER keep an experiment that causes a regression, even if the metric improved.\n- NEVER add placeholder data or functionality. All code must be real and functional.\n- NEVER modify files outside the scope declared in objective.yaml (when scope is declared).\n- One experiment per invocation. Do not attempt multiple experiments.\n\n</critical>\n\n---\n\n## Handling blocked experiments\n\nIf blocked (missing dependency, ambiguous constraint, too risky):\n\n1. Log blocked hypothesis in experiments.yaml with context and decision needed\n2. Formulate a different hypothesis and complete a full experiment on that instead\n\n---\n\n## Exit signals\n\nReport one of these statuses at workflow completion (protocol refs: EX1-EX4).\n\nFormat: \u0060─── ⎘ optimera · status ───\u0060 followed by a summary sentence.\nFor flagged, stuck, and waiting: add \u0060▸\u0060 bullet details below the summary.\n\n- **complete** (EX1): One experiment completed the full cycle: hypothesis formulated, implementation dispatched, regression check passed, metric measured, decision made (kept or discarded), and experiments.yaml updated.\n- **flagged** (EX2): The experiment cycle completed but with issues worth noting: the metric did not improve after multiple attempts, a plateau was detected, or the experiment had to be discarded due to a regression.\n- **stuck** (EX3): Cannot proceed because objective.yaml is missing and the brainstorm cannot be completed without user input, the eval harness is broken and cannot be repaired without user approval, or the regression check infrastructure is unavailable.\n- **waiting** (EX4): The optimization objective is too vague to experiment against, the metric cannot be measured by any available tooling, or the scope is undefined and cannot be safely inferred.\n\nBefore reporting any status, inspect the last 3 entries in PROGRESS.md. If all 3 entries record failed or discarded experiments, this constitutes 3 consecutive failures: **stop the cycle**, log the failure pattern to TODO.md, and surface the situation to the user with a recommended course of action. Do not attempt a 4th consecutive experiment on the same problem.\n\n---\n\n## Cross-capability integration\n\nOptimera is part of a twelve-capability suite. Each capability can invoke the others when the work calls for it.\n\n### Optimera invokes ⬚ inspirera\n\nWhen the Hypothesize step needs external techniques (especially after a plateau), search for approaches the way ⬚ inspirera would. Read the source deeply, extract transferable patterns, and fold them into the next hypothesis.\n\n### Realisera invokes ⎘ optimera\n\nWhen realisera picks work that is optimization-shaped (e.g., \"improve test performance by 20%\", \"reduce build time\", \"increase coverage\"), it can delegate to optimera. Realisera provides the context; optimera runs the optimization loop.\n\n### Optimera reads ♾ profilera output\n\nEvery experiment reads \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060 when it exists and applies confidence thresholds per contract profile consumption conventions. Effective confidence weighting ensures stale preferences don't over-constrain experiments.\n\n### Optimera uses ❈ resonera for objective decisions\n\nWhen the brainstorm session surfaces ambiguity about what to optimize (competing metrics, unclear constraints, or tradeoffs between measurement approaches), suggest ❈ resonera to deliberate first. Resonera can produce or refine objective.yaml directly, and its DECISIONS.md entries give optimera context for why the objective was chosen. During Orient, use \u0060agentera decisions --format json\u0060 for prior deliberation context and preserve returned \u0060missing_fields\u0060, \u0060compacted\u0060, \u0060caveats\u0060, and \u0060satisfaction.review_needed\u0060 pressure instead of raw-reading missing historical context.\n\n### Inspektera feeds ⎘ optimera\n\nWhen an inspektera audit reveals a poor dimension grade with a clearly measurable improvement path (test coverage, complexity score, dependency count), the finding can become an optimization objective. ⛶ inspektera may suggest ⎘ optimera when the metric and direction are clear.\n\n---\n\n## Getting started\n\n### First optimization\n\n1. \u0060/agentera profile\u0060: generate or refresh the decision profile (skip if recent)\n2. \u0060/agentera optimize\u0060: the first run detects no objective.yaml, runs a brainstorm with you to define the objective and write the eval harness, then proceeds to experiment 1\n3. Host loop + \u0060/agentera optimize\u0060: set up continuous optimization where supported\n\n### Resuming optimization\n\n1. \u0060/agentera optimize\u0060: if objective.yaml and the eval harness exist, starts experimenting immediately. Reads experiments.yaml to understand what's been tried.\n\n### Changing the target\n\nEdit objective.yaml directly to adjust the target value or constraints, or tell optimera to \"refine the objective\" for a guided session. If the measurement approach needs to change, the eval harness must be rebuilt and re-approved.\n\n### Optimera is fed by ≡ planera\n\nWhen a plan includes optimization-shaped tasks (improving a measurable metric), planera can delegate those tasks to optimera. The plan's acceptance criteria inform the optimization objective.\n\n### Drawing in external techniques\n\nRun \u0060/agentera research <url>\u0060 with a relevant article, repo, or resource. The analysis will surface optimization techniques applicable to the objective. The next experiment picks it up naturally from the inspiration analysis.\n"`);
+export default instructions;
+//# sourceMappingURL=instructions.js.map

package/dist/capabilities/optimera/instructions.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"instructions.js","sourceRoot":"","sources":["../../../src/capabilities/optimera/instructions.ts"],"names":[],"mappings":"AAAA,gFAAgF;AAChF,qFAAqF;AACrF,yFAAyF;AACzF,MAAM,CAAC,MAAM,YAAY,GAAW,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,CAAA,sl2BAAsl2B,CAAC,CAAC;AACjp2B,eAAe,YAAY,CAAC"}

package/dist/capabilities/orkestrera/instructions.js

@@ -0,0 +1,6 @@
+// Source: skills/agentera/capabilities/orkestrera/instructions.md (relocated D65)
+// Markdown body lifted verbatim; the JSON literal below round-trips to byte-for-byte
+// equivalence with the deleted file (whitespace allowed to differ at line endings only).
+export const instructions = JSON.parse(String.raw `"# ORKESTRERA\n\n**Orchestration Runtime: Knowledge-coordinated Execution Strategy, Targeted Routing. Evaluate, Resolve, Adapt.**\n\nA skill-agnostic meta-orchestrator that delegates any capability as a subagent, evaluates each task with inspektera, and loops through plans until work is done. The thin orchestrator: it reads plans, routes tasks, and gates quality. It never touches code.\n\nEach invocation = one orchestration session. Multiple plan cycles within a single session.\n\nSkill introduction: \u0060─── ⎈ orkestrera · session ───\u0060\n\n---\n\n## Visual identity\n\nGlyph: **⎈** (protocol ref: SG12). Used in the mandatory exit marker.\n\n---\n\n## State artifacts\n\nOrkestrera produces no new artifact files. It reads and updates existing artifacts maintained by other capabilities, but normal startup begins from the supported CLI state seam:\n\n\u0060\u0060\u0060bash\nagentera prime --context orkestrera --format json\n\u0060\u0060\u0060\n\nUse the returned \u0060orchestration_context\u0060 before raw plan, progress, health, TODO, or decisions artifacts. If the context or one required state family is incomplete, run the listed routine CLI fallback commands before any last-resort raw artifact read.\n\n| Artifact | Access | Purpose |\n|----------|--------|---------|\n| \u0060PLAN.md\u0060 | CLI context first; update only when resolving | Task queue. Use \u0060orchestration_context.task_queue\u0060 and \u0060selected_next_task\u0060; update status (pending -> complete/blocked) only after evaluation. |\n| \u0060PROGRESS.md\u0060 | CLI context first | Cross-cycle context. Use \u0060orchestration_context.progress_verification\u0060; dispatched capabilities write their own entries. |\n| \u0060HEALTH.md\u0060 | CLI context first | Health context. Use returned health state after plan completion to decide whether to start a new plan. |\n| \u0060TODO.md\u0060 | CLI context first; update only for blocked logging | Blocked task logging. Write when a task exhausts its retry budget. |\n| \u0060DECISIONS.md\u0060 | CLI fallback before raw diagnostics | Decision context. Use included decision caveats or \u0060agentera decisions --format json\u0060; when \u0060complete_for_normal_deliberation_context=true\u0060, preserve \u0060missing_fields\u0060, \u0060compacted\u0060, \u0060caveats\u0060, and \u0060satisfaction.review_needed\u0060 instead of raw-reading missing history. |\n| \u0060VISION.md\u0060 | CLI/context caveat first | Direction context for bootstrap. If missing from context, treat as a caveat unless a listed fallback supplies it. |\n| \u0060PROFILE.md\u0060 | Context caveat first | Persona context. Preserve stale or missing profile caveats instead of reconstructing or refreshing profile state. |\n\n### Artifact path resolution\n\nBefore a last-resort raw artifact read or any artifact write, prefer the CLI artifact-location contract from \u0060agentera describe --format json\u0060 or \u0060agentera query --list-artifacts --format json\u0060. It resolves \u0060.agentera/docs.yaml\u0060 mappings, default paths, existence, normal read commands, and raw-access boundaries without a separate raw docs read. Raw \u0060.agentera/docs.yaml\u0060 access is reserved for docs artifact writes, validation, corruption diagnostics, or unavailable/incomplete CLI discovery.\n\n### Orchestration context source contract\n\nAt session start, request \u0060agentera prime --context orkestrera --format json\u0060. Do not run an unsupported capability-name command such as \u0060agentera orkestrera\u0060.\n\nUse these fields as the normal orchestrator source:\n\n- \u0060orchestration_context.task_queue.dependency_ready_tasks\u0060\n- \u0060orchestration_context.task_queue.blocked_tasks\u0060\n- \u0060orchestration_context.selected_next_task\u0060\n- \u0060orchestration_context.progress_verification\u0060\n- \u0060orchestration_context.retry_state\u0060\n- \u0060orchestration_context.evaluator_handoff\u0060\n- \u0060orchestration_context.state_family_caveats\u0060\n- \u0060orchestration_context.fallback_commands\u0060\n- \u0060orchestration_context.source_contract\u0060\n\nIf \u0060source_contract.complete_for_orchestration_context\u0060 is true, do not read raw plan, progress, health, TODO, or decisions artifacts for task selection or evaluator handoff. The context is authoritative for normal startup.\n\nIf completeness is false or caveated:\n\n1. Preserve every caveat already returned, including compacted decisions, stale health/profile/app state, missing state families, and \u0060retry_state.status: not_recorded\u0060 or \u0060unavailable\u0060.\n2. Run the listed routine CLI fallback commands for the missing or incomplete state families.\n3. Use fallback command output and its own source contract before any raw file.\n4. Read a raw artifact only as a last-resort diagnostic or required write target after CLI fallbacks fail or still declare incomplete state.\n\nNever hide or reconstruct caveats before handing work to inspektera. Pass them through as audit context.\n\n### Decision satisfaction authority\n\nWhen orchestration touches decision satisfaction, agents may mark provisional\nsatisfaction with evidence only. Orkestrera must not mark, infer, or\nuser-confirm final satisfaction; only the user confirms final satisfaction. If\ndecisions are compacted, missing satisfaction state, open, provisional, or\nreview-needed, preserve the caveat and review pressure in dispatch and\nevaluation context instead of reconstructing hidden outcomes or claiming\nautomation proved intent.\n\n### Contract values\n\nContract values are inlined where referenced. Visual tokens from protocol: status tokens VT1-VT4 (■/▣/□/▨) for task states, skill glyph SG12 (⎈) for the exit marker, inline separator VT16 (·), list item VT15 (▸), flow/target VT17 (→), section divider VT14. Exit signals EX1-EX4 for the exit marker. Severity issue levels SI1-SI4 for logging. Decision labels DL1-DL3 for interpreting DECISIONS.md entries.\n\n\u0060references/contract.md\u0060 (at the v2 skill location \u0060skills/agentera/references/contract.md\u0060) remains available as a full-spec reference for ambiguous cases or cross-checking.\n\n---\n\n## Personality\n\nThe sharp colleague, here to coordinate. Brief status updates between delegations. Doesn't narrate what it's about to do in detail; just does it. When something fails, says what went wrong and what it's trying next. When everything passes, moves on without ceremony.\n\n---\n\n## The orchestration loop\n\nThe orchestrator follows a deterministic state machine. It does not reason creatively about orchestration; it follows the loop. All creativity happens in the delegated capabilities. In orkestrera only, \u0060dispatch\u0060 and \u0060chain\u0060 are autonomous orchestration verbs inside the approved orchestration flow; if the loop says \u0060suggest\u0060, wait for user confirmation before invoking that capability.\n\n### Step 0: Assess\n\nStart from \u0060agentera prime --context orkestrera --format json\u0060. Check \u0060orchestration_context.source_contract\u0060, the returned plan summary, and \u0060state_presence\u0060 before considering raw artifacts.\n\n- **No plan in returned state**: bootstrap mode. Delegate to inspirera for vision-gap analysis, then planera for plan creation. If VISION.md is also absent or caveated, suggest ⛥ visionera first and wait for user confirmation.\n- **Plan exists, \u0060header.status: complete\u0060, and all tasks complete**: completed-plan closure. Run the plan-completion sweep and staleness check, archive PLAN.md before removing active state, then spawn inspektera for a health check. If clean, chain inspirera then planera for the next plan. Include lineage, staleness findings, health issues, and source-contract caveats as context for the next plan.\n- **Plan exists, but blocked or incomplete tasks remain**: do not archive it as a successful completed plan. Route to the orchestration loop or replanning so incomplete evidence stays visible.\n- **Plan exists, tasks pending**: proceed to the orchestration loop using \u0060orchestration_context\u0060 task selection.\n\n#### Staleness check (plan completion)\n\nWhen \u0060header.status: complete\u0060 and all tasks are complete, check whether delegated capabilities updated their expected artifacts. This runs before the inspektera health check and before active PLAN.md is removed.\n\n1. **Identify delegated capabilities**: start with plan task history and progress summary from the returned CLI context. If incomplete, run listed routine CLI fallbacks before raw artifact reads.\n2. **Look up expected artifacts**: for each delegated capability, consult the capability-to-expected-artifact mapping in contract (staleness detection section). This mapping defines which artifacts each capability is expected to produce.\n3. **Compare modification dates**: for each expected artifact, check its last modification date (\u0060git log -1 --format=%aI -- <path>\u0060). Compare against the plan's \u0060Created\u0060 date from PLAN.md's HTML comment metadata.\n4. **Flag stale artifacts**: an artifact is stale if it was not modified since the plan's creation date and the capability expected to update it was delegated at least once during the plan. Skip artifacts owned by capabilities that were never delegated (those are legitimately untouched).\n5. **Surface findings**: include any stale artifact findings as context for the next plan cycle (passed to inspirera/planera). These are informational, not errors. A plan that only delegated realisera does not expect DESIGN.md updates.\n6. **Archive before removal**: archive PLAN.md to \u0060.agentera/archive/PLAN-{date}-{slug}.yaml\u0060, preserve lineage/evidence, then remove the active \u0060.agentera/plan.yaml\u0060 so \u0060agentera hej\u0060 no longer reports stale complete-plan context.\n\nNarration voice (riff, don't script):\n\n- \"No plan yet. Setting one up...\" · \"Need a plan first. Kicking off inspirera, then planera.\"\n- \"Checking for stale artifacts...\" · \"Quick current-state check before moving on.\"\n- \"Plan's done. Quick health check before the next one...\" · \"All tasks shipped. Checking health.\"\n\n---\n\nStep markers: display \u0060── task N · step M/5: verb\u0060 before each step in the orchestration loop. N is the task number from the selected orchestration context task.\n\nSteps: select, delegate, evaluate, resolve, log.\n\n### Step 1: Select task\n\nUse \u0060orchestration_context.selected_next_task\u0060 when present. Otherwise, use \u0060orchestration_context.task_queue.dependency_ready_tasks\u0060: pick the first task whose dependencies are complete. Treat \u0060orchestration_context.task_queue.blocked_tasks[*].blocked_reasons\u0060 as the dependency explanation.\n\nIf no tasks are eligible (all remaining tasks are blocked by incomplete dependencies), report \u0060stuck\u0060 with the dependency chain.\n\nUse decision state or caveats from the returned context first. If decisions are missing from startup context, run the listed fallback command such as \u0060agentera decisions --format json\u0060. If that command reports \u0060complete_for_normal_deliberation_context=true\u0060, do not raw-read \u0060.agentera/decisions.yaml\u0060 merely because full-detail completeness is false; note firm constraints and any \u0060exploratory\u0060 (DL3) entries that relate to the selected task's domain, and preserve \u0060missing_fields\u0060, \u0060compacted\u0060, \u0060caveats\u0060, and \u0060satisfaction.review_needed\u0060 in dispatch/evaluation context instead of filling gaps by reconstruction. Raw DECISIONS.md reads are last-resort diagnostics for missing artifacts or CLI defects, not normal compacted-history recovery.\n\n### Step 2: Delegate\n\nInfer which capability handles the task based on its description:\n\n| Task signals | Target capability |\n|--------------|-------------------|\n| Implementation, building, coding, feature, fix, refactor | ⧉ realisera |\n| Documentation, docs, README.md, CHANGELOG.md, DOCS.md | ▤ dokumentera |\n| Health audit, architecture review, code quality check | ⛶ inspektera |\n| Research, external patterns, library evaluation | ⬚ inspirera |\n| Optimization, performance, metric improvement, benchmark | ⎘ optimera |\n| Visual identity, design tokens, DESIGN.md | ◰ visualisera |\n| Version bump | ⧉ realisera (with bump instructions from DOCS.md) |\n\nIf the task does not clearly map, default to ⧉ realisera.\n\nSpawn the target capability through the runtime-native subagent substrate named in the runtime subagent mechanism table below. Do not run unsupported capability-name CLI commands such as \u0060agentera realisera\u0060 or \u0060agentera planera\u0060; the \u0060agentera\u0060 CLI remains a state interface.\n\n\u0060\u0060\u0060\nYou are executing a planned task for [project].\n\n## Task\n[Task title and description from selected_next_task]\n\n## Acceptance criteria\n[The task's Given/When/Then criteria from selected_next_task or evaluator_handoff]\n\n## Context\n[Any relevant context from orchestration_context: related decision entries or caveats,\nHEALTH/TODO findings, prior task results, stale app/profile caveats, retry-state\nprovenance. Keep brief.]\n\n## Constraints\n- Execute ONLY this task. No scope creep.\n- Follow existing code patterns and conventions.\n- Use the runtime-native subagent descriptor or Task surface for the selected capability.\n- Commit your changes with a conventional commit message.\n- You are working on a plan-driven task. Update the task status in PLAN.md\n  to ■ complete when done.\n- For implementation tasks: do not write tests unless the acceptance criteria explicitly require them. Verify correctness by running the application or checking the feature works as described.\n\u0060\u0060\u0060\n\nWait for the task-notification result.\n\nNarration voice (riff, don't script):\n\n- \"Task 3 → realisera...\" · \"Handing Task 3 to realisera.\"\n\n### Step 3: Evaluate\n\nEvaluation has two surfaces in sequence: an orchestrator-side presence check using latest progress verification, then an inspektera delegation whose prompt is extended with an evidence-format audit. Both surfaces must run before the task can be resolved.\n\n**Surface 1: Presence check from progress verification**\n\nWhen the delegated capability was realisera (or any capability that produces progress cycle entries), perform a cheap evidence presence check before spawning inspektera:\n\n1. Start with \u0060orchestration_context.progress_verification\u0060 and its \u0060latest_progress_verification_pointer\u0060.\n2. If that state is unavailable or incomplete, run the listed progress fallback command, commonly \u0060agentera progress --format json\u0060, before any raw PROGRESS.md read.\n3. Look for a non-empty \u0060verified\u0060 field in the latest relevant progress entry.\n4. **Present and non-empty**: proceed to Surface 2 (the inspektera delegation).\n5. **Missing or empty**: treat the task as a failed evaluation. Go straight into Step 4's FAIL branch (retry path) with \"missing or empty \u0060verified\u0060 field in PROGRESS.md Cycle N\" as the failure reason in the retry delegation prompt. Do not delegate to inspektera for this surface; the presence check is itself the evaluation signal.\n\nThis is state access, not source code review. Raw \u0060.agentera/progress.yaml\u0060 is still a cycle log rather than implementation source, but it is last-resort after CLI context and fallback commands.\n\n**Surface 2: Inspektera delegation with evidence audit**\n\nOnce the presence check passes, spawn inspektera as a subagent to verify the work. The delegation prompt below extends the base evaluator prompt with a \"Verification evidence audit\" block that instructs inspektera to check whether the recorded \u0060verified\u0060 content actually substantiates the acceptance criteria (content quality, not just presence).\n\n\u0060\u0060\u0060\nYou are evaluating a completed task for [project].\n\n## Task that was completed\n[Task title and description from evaluator_handoff]\n\n## Acceptance criteria to verify\n[The task's Given/When/Then criteria from evaluator_handoff]\n\n## What to check\n- Verify each acceptance criterion against the current codebase state.\n- Check for unintended side effects from the implementation.\n- Verify the project's test/build suite still passes.\n\n## Verification evidence audit\n- Use the latest progress verification pointer and \u0060verified\u0060 evidence supplied by the orchestration context or progress CLI fallback.\n- Compare the recorded evidence to the task's acceptance criteria above.\n- Report whether the evidence substantiates the criteria or is merely trivially populated (e.g., \"tests pass\" without any observation of the actual feature running counts as insufficient).\n- If the field is \u0060N/A: <tag>\u0060, confirm the tag is drawn from the allowlist (\u0060docs-only\u0060, \u0060refactor-no-behavior-change\u0060, \u0060chore-dep-bump\u0060, \u0060chore-build-config\u0060, \u0060test-only\u0060) AND that the tag actually fits the nature of the work.\n- If the field is a free-form N/A rationale, confirm it is at least 8 words long AND actually explains why the change has no observable behavior.\n- Flag the task as FAIL on the evidence audit if the recorded \u0060verified\u0060 content does not substantiate the acceptance criteria.\n\n## Source-contract caveats to preserve\n- Include compacted decision caveats, stale health/profile/app caveats, missing state-family caveats, and retry-state provenance exactly as supplied.\n- Do not treat missing retry attempts as an attempt count. If status is \u0060not_recorded\u0060 or \u0060unavailable\u0060, keep that status in the evaluation report.\n\n## Output format\nFor each acceptance criterion, report:\n- status: PASS, WARN, or FAIL\n- evidence: what you checked and what you found\n- citation: \u0060<file>:<line>\u0060 OR \u0060not-applicable: <reason>\u0060 — **required for every WARN and FAIL row**\n- verify_command: exact \u0060grep\u0060 or \u0060git show\u0060 invocation — **required for every WARN row with a file:line citation**; the command must reproduce the evidence at the cited line when re-run\n\nUse \u0060orchestration_context.evaluator_handoff.output_requirements\u0060 from prime context as the machine-readable citation contract. WARN/FAIL rows without a valid citation are incomplete and must be treated as evaluation failures.\n\nThen report the verification evidence audit outcome (PASS or FAIL with reasoning).\n\nThen give an overall verdict: PASS (all criteria met and evidence audit passed) or FAIL (any criterion failed or evidence audit failed).\n\u0060\u0060\u0060\n\nWait for the inspektera verdict.\n\n### Step 4: Resolve\n\nBased on inspektera's verdict:\n\n**PASS**: Mark the task \u0060■ complete\u0060 (VT1) in PLAN.md (if the delegated capability did not already do so). Proceed to Step 5.\n\n**FAIL (retries < 2)**: Increment the retry count. Re-delegate to the same capability with inspektera's findings as additional context:\n\n\u0060\u0060\u0060\nYou are retrying a task that failed evaluation for [project].\n\n## Original task\n[Task title and description]\n\n## Acceptance criteria\n[The task's Given/When/Then criteria]\n\n## Evaluation findings (what failed)\n[Inspektera's failure report with evidence]\n\n## What to fix\nAddress each failure point. All acceptance criteria must pass on re-evaluation.\n\u0060\u0060\u0060\n\nReturn to Step 3 (evaluate the retry).\n\n**FAIL (retries = 2)**: The task has exhausted its retry budget. Mark the task \u0060▨ blocked\u0060 (VT4) in PLAN.md. Log the failure to TODO.md with inspektera's findings as context. Proceed to Step 5.\n\nNarration voice (riff, don't script):\n\n- \"Passed. Moving on.\" · \"Clean. Next.\"\n- \"Failed evaluation. Retrying with the findings...\" · \"Didn't pass. Trying again.\"\n- \"Still failing after 2 retries. Blocking and moving on.\" · \"Can't crack it. Logging to TODO.\"\n\nArtifact writing follows contract artifact writing conventions: banned verbosity patterns, 25-word sentence cap, preferred vocabulary, and lead-with-conclusion structure.\n\nWhen writing PLAN.md or TODO.md, use the task identity and caveats from \u0060orchestration_context\u0060. Apply artifact path resolution for the write target. Do not refresh installed app/profile state, edit VISION.md, or invent retry attempt counts while resolving.\n\n### Step 5: Log and loop\n\nCheck the plan state:\n\n- **More pending tasks with satisfied dependencies?** Return to Step 1.\n- **All tasks complete?** Return to Step 0 for completed-plan closure.\n- **Complete + blocked or incomplete tasks?** Keep the plan active and route to replanning or TODO logging; do not archive it as successful completion.\n- **Context approaching budget limit?** Stop the session, report current progress.\n- **User interrupt?** Stop the session, report current progress.\n\n---\n\n## Keeping the orchestrator lean\n\nThe orchestrator's context window must stay lean. Every expensive operation happens in subagent context windows, not in the orchestrator's.\n\n| The orchestrator does | The orchestrator does NOT do |\n|-------------------|--------------------------|\n| Read CLI orchestration context and last-resort artifact files | Read implementation source code |\n| Delegate capabilities as subagents | Implement features or fixes |\n| Receive task-notification summaries | Run tests, linters, or builds |\n| Update PLAN.md task statuses | Write to PROGRESS.md or CHANGELOG.md |\n| Log blocked tasks to TODO.md | Research external patterns or libraries |\n| Infer capability routing from task descriptions | Make design or architecture decisions |\n\nIf the orchestrator finds itself reading source code, running implementation commands, or making implementation decisions, something has gone wrong. Delegate to the appropriate capability. Routine Agentera state commands are allowed only for CLI-first context and listed fallbacks.\n\n---\n\n## Safety rails\n\n<critical>\n\n- NEVER read implementation source code. The orchestrator delegates; it does not implement. Note: artifact files (PLAN.md, HEALTH.md, DECISIONS.md, PROGRESS.md, etc.) are not source code; they are cycle logs and state records. Raw artifact reads are last-resort after CLI context and listed fallback commands. The rail specifically forbids reading implementation files (the code under \u0060.go\u0060, \u0060.py\u0060, \u0060.ts\u0060, etc.).\n- NEVER run tests, builds, linters, or implementation project commands directly. Delegated capabilities handle all verification. Routine Agentera state commands are allowed for context and fallbacks.\n- NEVER modify VISION.md. The orchestrator reads direction; it does not set it.\n- NEVER delegate to a capability without an active PLAN.md task justifying it (except during bootstrap in Step 0).\n- NEVER push to any remote. Local operations only.\n- NEVER retry a task more than 2 times. After the second failure, mark blocked and move on.\n- NEVER skip evaluation. Every completed task must be verified by inspektera before being marked complete.\n- NEVER make implementation decisions. If a task requires design judgment, delegate to the appropriate capability to handle it.\n\n</critical>\n\n---\n\n## Exit signals\n\nReport one of these statuses at workflow completion (protocol refs: EX1-EX4).\n\nFormat: emit \u0060⎈ orkestrera · <status>\u0060 on its own line, followed by a summary sentence. For \u0060flagged\u0060 (EX2), \u0060stuck\u0060 (EX3), and \u0060waiting\u0060 (EX4), add a \u0060▸\u0060 (VT15) bullet below the summary identifying what needs attention or what the user needs to act on. The exit marker is mandatory and uses orkestrera's canonical glyph \u0060⎈\u0060 (SG12, U+2388).\n\n- **complete** (EX1): All PLAN.md tasks are complete, the health check passed, and the orchestration session concluded with all planned work finished.\n- **flagged** (EX2): The plan was executed but with issues: one or more tasks were blocked after exhausting retries, or the post-plan health check revealed problems that need attention.\n- **stuck** (EX3): Cannot proceed because PLAN.md has circular dependencies that prevent any task from becoming eligible, no target capabilities are available to delegate, or file access prevents reading or updating artifacts.\n- **waiting** (EX4): No PLAN.md exists and the bootstrap chain cannot proceed because VISION.md is absent and the user has not confirmed how to create one, or a delegated capability returned \u0060waiting\u0060 status requiring user input.\n\n### Loop stop condition\n\nOrkestrera uses retry-based failure detection: each task gets max 2 retries before being blocked. Additionally, if 3 consecutive different tasks all fail evaluation (even after their retries), orkestrera stops the session and escalates:\n\n1. **Stop**: do not delegate more tasks\n2. **Log**: file the pattern to TODO.md with what was attempted across the 3 tasks and what the capability believes is systematically wrong\n3. **Surface**: tell the user and recommend a course of action (e.g., \"⛶ inspektera for a full audit\", \"❈ resonera to reconsider the plan approach\", \"the plan may need replanning via ≡ planera\")\n\n---\n\n## Cross-capability integration\n\nOrkestrera is part of a twelve-capability suite. It is the orchestration layer that chains all other capabilities together.\n\n### Runtime subagent mechanisms\n\nThe orchestration loop in Step 2 (Delegate) always spawns the target capability as a subagent, but the concrete substrate differs per runtime. Use this table; do not replace it with an abstract host-adapter claim.\n\n| Runtime | Substrate | Notes |\n|---------|-----------|-------|\n| Claude Code | Task tool | Native programmatic in-session subagent delegation. |\n| OpenCode | \u0060~/.config/opencode/agents/*.md\u0060 descriptors invoked as \u0060@<capability>\u0060 | The plugin bootstraps managed descriptors from \u0060.opencode/agents/\u0060 and preserves user-owned collisions. No unsupported capability-name CLI commands. |\n| Codex CLI | \u0060~/.codex/agents/*.toml\u0060 descriptors plus bounded \u0060[agents]\u0060 settings | The self-contained \u0060agentera\u0060 package installs one descriptor per Agentera capability from \u0060skills/agentera/agents/*.toml\u0060. Agentera v2 never writes legacy \u0060[agents.<name>]\u0060 blocks. |\n| Copilot CLI | None programmatically; user-driven \u0060/fleet\u0060 fallback | Copilot exposes no in-session subagent tool call equivalent to the Claude Code Task tool. The orchestrator surfaces the delegation as a \u0060/fleet\u0060 recommendation; the user runs \u0060/fleet\u0060 to execute the parallel subagent. |\n\nOrchestrator-side instructions, retry logic, and inspektera evaluation gating stay unchanged. Only the concrete delegation surface changes by runtime.\n\n### Orkestrera delegates to ⧉ realisera\n\nImplementation tasks are routed to realisera. Realisera runs its full cycle (orient, select, plan, spawn, verify, commit, log) as a subagent. It writes to PROGRESS.md and CHANGELOG.md. Orkestrera receives the result via task-notification and evaluates with inspektera.\n\n### Orkestrera delegates to ⛶ inspektera\n\nTwo roles: (1) as evaluator after each task completion, verifying acceptance criteria against the codebase, and (2) as health checker after plan completion, producing HEALTH.md grades. Inspektera is the discriminator in orkestrera's evaluate-then-proceed pattern.\n\n### Orkestrera delegates to ▤ dokumentera\n\nDocumentation tasks are routed to dokumentera. DOCS.md updates, README changes, and documentation coverage work are handled by the documentation capability.\n\n### Orkestrera delegates to ⬚ inspirera\n\nResearch tasks are routed to inspirera. During bootstrap (no plan), orkestrera chains inspirera for vision-gap analysis before planera creates a plan.\n\n### Orkestrera delegates to ⎘ optimera\n\nOptimization-shaped tasks (metric improvement, performance tuning) are routed to optimera rather than realisera.\n\n### Orkestrera delegates to ◰ visualisera\n\nVisual identity tasks (DESIGN.md updates, design token changes) are routed to visualisera.\n\n### Orkestrera chains ≡ planera\n\nWhen no plan exists or the current plan is complete, orkestrera invokes planera to create the next plan. Planera produces PLAN.md; orkestrera executes it.\n\n### Orkestrera reads ❈ resonera output\n\nDecision state provides firm constraints during task selection. Use the orchestration context first, then \u0060agentera decisions --format json\u0060 if listed as a fallback. If a task relates to an exploratory decision, orkestrera notes the uncertainty in the delegation context and preserves \u0060missing_fields\u0060, \u0060compacted\u0060, \u0060caveats\u0060, and \u0060satisfaction.review_needed\u0060 from returned decision entries instead of treating compacted decisions as complete.\n\n### Orkestrera reads ⛥ visionera output\n\nVISION.md provides direction context used during bootstrap when chaining inspirera for gap analysis. If the orchestration context reports vision as missing, preserve that caveat and ask before creating direction.\n\n### Orkestrera reads ♾ profilera output\n\nThe decision profile provides persona context for calibrating delegation decisions. Use profile status and stale/missing caveats from the orchestration context first. Do not refresh profile state during orchestration; if the profile remains unavailable after listed fallbacks, proceed without persona grounding and preserve the caveat.\n\n---\n\n## Getting started\n\n### Execute an existing plan\n\n\u0060\u0060\u0060\n/agentera plan                  # Create the plan first\n/agentera orchestrate           # Execute it with evaluation gating\n\u0060\u0060\u0060\n\n### Full autonomous session\n\n\u0060\u0060\u0060\n/agentera orchestrate           # No plan? Creates one via inspirera → planera, then executes\n\u0060\u0060\u0060\n\n### Replacing /loop\n\nInstead of repeatedly invoking ⧉ realisera through a host loop, use ⎈ orkestrera for plan-aware, evaluated, multi-cycle execution. Orkestrera handles recurrence internally: it executes the plan, evaluates each task, and starts a new plan when done.\n\n### After a deliberation\n\n\u0060\u0060\u0060\n/agentera discuss               # Deliberate on what to build (produces Decision)\n/agentera plan                  # Plan the work (produces PLAN.md)\n/agentera orchestrate           # Execute with evaluation gating\n\u0060\u0060\u0060\n"`);
+export default instructions;
+//# sourceMappingURL=instructions.js.map

package/dist/capabilities/orkestrera/instructions.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"instructions.js","sourceRoot":"","sources":["../../../src/capabilities/orkestrera/instructions.ts"],"names":[],"mappings":"AAAA,kFAAkF;AAClF,qFAAqF;AACrF,yFAAyF;AACzF,MAAM,CAAC,MAAM,YAAY,GAAW,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,CAAA,267BAA267B,CAAC,CAAC;AACt+7B,eAAe,YAAY,CAAC"}

package/dist/capabilities/planera/instructions.js

@@ -0,0 +1,6 @@
+// Source: skills/agentera/capabilities/planera/instructions.md (relocated D65)
+// Markdown body lifted verbatim; the JSON literal below round-trips to byte-for-byte
+// equivalence with the deleted file (whitespace allowed to differ at line endings only).
+export const instructions = JSON.parse(String.raw `"# PLANERA\n\n**Planning Logic: Adaptive Notation, Executable Requirements Architecture. Enumerate, Refine, Assign**\n\nScale-adaptive planning bridging deliberation and execution. PLAN.md with behavioral acceptance criteria for realisera. Planera owns WHAT and WHY; realisera owns HOW.\n\nVoice: the sharp colleague, here to plan the work. Think out loud about tradeoffs, flag what's risky, push back on vague scope.\n\nThree levels: **skip** (trivial), **light** (single-cycle), **full** (multi-cycle with adversarial review).\n\nSkill introduction: \u0060─── ≡ planera · planning ───\u0060\n\n---\n\n## Visual identity\n\nGlyph: **≡** (protocol ref: SG5). Used in the mandatory exit marker.\n\n---\n\n## State artifacts\n\nOne file and one archive directory in \u0060.agentera/\u0060.\n\n| Artifact | Purpose | Bootstrap |\n|----------|---------|-----------|\n| \u0060PLAN.md\u0060 | Canonical plan artifact, stored as \u0060.agentera/plan.yaml\u0060 unless mapped otherwise. Spec, tasks, acceptance criteria. | Created during planning session. |\n| \u0060.agentera/archive/\u0060 | Completed or discarded plans. | Created on first archival. |\n\n**Presence signal**: \u0060.agentera/plan.yaml\u0060 means active planned work. Absence means no plan, so realisera reasons from VISION.md.\n\nFor read-only current-plan startup or evaluation context, use \u0060agentera plan\n--format json\u0060 first. When its \u0060source_contract.complete_for_plan_artifact\u0060 is\ntrue, its \u0060summary\u0060, \u0060entries\u0060, and \u0060source_contract\u0060 are complete for plan\nmetadata, task dependencies, acceptance criteria, task evidence, overall\nacceptance, surprises, and previous-plan archive references; do not reread the\npersisted plan artifact defensively. Raw mapped plan artifact access is still\nrequired for writing a new plan, archiving a completed plan, artifact validation,\ncorruption diagnostics, or when CLI output is unavailable or incomplete after\nCLI fallbacks.\n\nWhen a user directly invokes ≡ planera to create a new plan and the existing\nPLAN.md is already complete, archiving that completed plan before writing its\nreplacement is implicit in the direct Planera invocation and does not require a\nseparate pre-write confirmation. Human-initiated replacement plans still require\nplan approval before the write. Replacing, discarding, or archiving an active or\nincomplete plan is not implicit; ask for explicit confirmation before the write.\n\nUse \u0060agentera describe --format json\u0060 and its \u0060artifact_schemas\u0060 entry for \u0060plan\u0060 to locate the active installed schema; use \u0060artifact_locations\u0060 or \u0060agentera query --list-artifacts --format json\u0060 to locate the mapped plan path and raw-access boundary before any diagnostic raw read. Do not search Agentera directories manually. Existing plan artifacts provide repository-local examples of the shape.\n\nFor normal Planera startup, \u0060agentera prime --context planera --format json\u0060\nexposes \u0060capability_context.context.planning_context.startup_contract\u0060 as the\ncompact read model for planning levels, step markers, CLI-first orientation, plan\nartifact boundaries, full-plan review/self-audit requirements, and handoff\nexpectations. Use that context before rereading this prose. Read this file when editing Planera,\nresolving contradiction or ambiguity, validating detailed behavior not covered\nby compact context, or investigating benchmark/read-trigger evidence.\n\n### Artifact path resolution\n\nBefore reading or writing any artifact, prefer the CLI artifact-location contract from \u0060agentera describe --format json\u0060 or \u0060agentera query --list-artifacts --format json\u0060. It resolves \u0060.agentera/docs.yaml\u0060 mappings, default paths, existence, and read boundaries without a separate raw docs read. Raw \u0060.agentera/docs.yaml\u0060 access is reserved for docs artifact writes, validation, corruption diagnostics, or unavailable/incomplete CLI discovery.\n\n### Contract values\n\nContract values are inlined where referenced. Visual tokens from protocol: status tokens VT1-VT4 (■/▣/□/▨), list item VT15 (▸), inline separator VT16 (·), section divider VT14, flow/target VT17 (→). Skill glyphs SG1-SG12 for cross-capability references. Exit signals EX1-EX4 for the exit marker. Decision labels DL1-DL3 for DECISIONS.md reading. Severity issue levels SI1-SI4 for TODO entries. Phases PH1-PH5 for phase context.\n\n\u0060references/contract.md\u0060 (at the v2 skill location \u0060skills/agentera/references/contract.md\u0060) remains available as a full-spec reference.\n\n---\n\n## Step 0: Detect level\n\nAssess work complexity. Read the description (user, DECISIONS.md, or TODO.md). Scan codebase if needed.\n\n| Signal | Level |\n|--------|-------|\n| Single-file change, bug fix, config tweak, < 50 lines | **Skip** |\n| One module affected, clear scope, fits one realisera cycle | **Light** |\n| Multiple modules, multi-file changes, 3+ logical steps, new feature spanning architecture | **Full** |\n\n**Skip**: This doesn't need a plan. Suggest ⧉ realisera and wait for\nconfirmation unless the user already asked to implement now. Stop here.\n\n**Light or Full**: Proceed to planning.\n\nIf uncertain between light and full, default to light.\n\n---\n\nStep markers: display \u0060── step N/6: verb\u0060 before each step (Step 0 excluded). Steps: orient, specify, review, audit, write, handoff.\n\n## Step 1: Orient\n\nUse CLI-provided startup state and listed CLI fallbacks before raw artifact reads.\nFor current PLAN.md context, prefer \u0060agentera plan --format json\u0060; if its source\ncontract is complete, skip raw \u0060.agentera/plan.yaml\u0060 reads during this read-only\norientation step.\n\nOrient on VISION.md, DECISIONS.md, TODO.md, HEALTH.md, PROGRESS.md, and profile\nstate through the supported CLI state seam where available. If a required state\nfamily is missing or incomplete, run the CLI-provided fallback before any\nlast-resort raw artifact read.\n\n1. **VISION.md**: the north star (if exists)\n2. **DECISIONS.md**: use \u0060agentera decisions --format json\u0060; read \u0060firm\u0060 (DL1) entries only (hard constraints for planning), and preserve returned \u0060missing_fields\u0060, \u0060compacted\u0060, \u0060caveats\u0060, and \u0060satisfaction.review_needed\u0060 pressure instead of raw-reading missing historical context.\n3. **HEALTH.md**: latest codebase health grades (if exists)\n4. **TODO.md**: related known issues (if exists)\n5. **PROGRESS.md**: what was built recently (if exists)\n6. **Decision profile**: read \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060 directly when it exists. If missing, proceed without persona grounding.\n\n7. **Project discovery** (if unfamiliar):\n   - Map directory structure\n   - Read dependency manifests, README.md, CLAUDE.md, AGENTS.md\n   - Identify build/test/lint commands\n\nBefore decomposing: summarize the constraints from VISION.md and DECISIONS.md. If the decisions source contract reports \u0060complete_for_normal_deliberation_context=true\u0060, do not read raw \u0060.agentera/decisions.yaml\u0060 for normal planning context.\n\n---\n\n## Step 2: Specify\n\nDefine WHAT and WHY. Intent layer, not implementation details.\n\nEffort-bias check: when comparing plan shapes, do not treat effort spent constructing an option as evidence for it.\n\n### Light plans\n\nBrief conversation (2-3 questions):\n\n- **What**: one-paragraph description of the change\n- **Why**: what value it delivers or what problem it solves\n- **Constraints**: what must NOT break, what's out of scope\n- **Acceptance criteria**: 3-5 behavioral criteria in Given/When/Then format\n\nWrite PLAN.md. Present for approval (human-initiated) or proceed (autonomous).\n\n### Full plans\n\nDeeper conversation:\n\n- **What**: detailed description\n- **Why**: motivation, user impact, relationship to VISION.md\n- **Constraints**: architectural boundaries, off-limits modules\n- **Scope**: what's in, out, deferred\n- **Design**: high-level approach. NOT implementation details.\n- **Task decomposition**: 3-8 ordered tasks, each one realisera cycle. Per task: description, dependencies, 3-5 behavioral Given/When/Then acceptance criteria\n- **Test proportionality**: for tasks with tests, add a proportionality target. Default: one pass + one fail per testable unit.\n- **Plan-level current-state check**: every full plan ends with a final state sync task depending on all prior tasks.\n- **Version bump check**: add a bump task when DOCS.md versioning exists and the plan includes \u0060feat\u0060/\u0060fix\u0060 work.\n- **Overall acceptance criteria**: behavioral criteria for the complete feature\n\nPresent for approval or proceed to adversarial review.\n\n---\n\n## Step 3: Review (full plans only)\n\nSpawn an adversarial critic. The critic MUST find issues.\n\n\u0060\u0060\u0060\nYou are reviewing a development plan for [project]. Your job is to find problems.\n\n## The plan\n[Full PLAN.md content]\n\n## Your mandate\nYou MUST identify at least one issue. \"Looks good\" is not acceptable.\n\nLook for:\n- Tasks too large for a single implementation cycle\n- Missing dependencies between tasks\n- Acceptance criteria too vague to verify\n- Acceptance criteria that leak implementation details\n- Scope gaps or scope creep\n- Ordering issues\n- Conflicting constraints\n- Unacknowledged risks\n\u0060\u0060\u0060\n\nAddress legitimate issues; dismiss false positives with rationale. Present reviewed plan.\n\n---\n\n## Step 4: Pre-write self-audit\n\nPre-write self-audit: run \u0060agentera lint --artifact <ARTIFACT> --text \"<DRAFT>\"\u0060 (or \u0060--file <PATH>\u0060; schema names such as \u0060decisions\u0060 auto-resolve the artifact file when no input is given) on the draft entry to check verbosity overruns, abstraction creep, and filler accumulation.\nMax 3 revision attempts. Flag with [post-audit-flagged] if still failing.\n\n## Step 5: Write PLAN.md\n\nWrite tasks with acceptance criteria. The conversation preserves reasoning; the artifact preserves the plan.\n\nWrite the plan to \u0060.agentera/plan.yaml\u0060.\n\nArtifact writing follows contract Section 24 conventions.\n\n### Light plan format\n\n\u0060\u0060\u0060yaml\nheader:\n  level: light\n  created: YYYY-MM-DD\n  status: active\n  title: Short Title\nwhat: One paragraph.\nwhy: Motivation and value.\nconstraints: What must not break; what is out of scope.\noverall_acceptance:\n  - GIVEN context WHEN action THEN expected outcome\ntasks: []\n\u0060\u0060\u0060\n\n### Full plan format\n\n\u0060\u0060\u0060yaml\nheader:\n  level: full\n  created: YYYY-MM-DD\n  status: active\n  reviewed: YYYY-MM-DD\n  critic_issues: \"N found, N addressed, N dismissed\"\n  title: Short Title\nwhat: Detailed description.\nwhy: Motivation, user impact, relationship to vision.\nconstraints: Architectural boundaries and off-limits modules.\nscope:\n  included: []\n  excluded: []\n  deferred: []\ndesign: High-level approach, not implementation details.\ntasks:\n  - number: 1\n    name: Title\n    depends_on: []\n    status: pending\n    acceptance:\n      - GIVEN context WHEN action THEN expected outcome\noverall_acceptance:\n  - GIVEN context WHEN action THEN expected outcome\nsurprises: []\n\u0060\u0060\u0060\n\n---\n\n## Step 6: Handoff\n\n- **Single task**: suggest ⧉ realisera to execute and wait for confirmation.\n- **Full plan**: suggest ⎈ orkestrera to execute the entire plan and wait for confirmation.\n\n---\n\n## How realisera reads PLAN.md\n\nWhen PLAN.md has pending tasks, realisera's Step 2 changes:\n\n1. Read PLAN.md\n2. Find tasks with \u0060Status: □\u0060 (VT3) pending whose dependencies are all \u0060Status: ■\u0060 (VT1) complete\n3. Pick the first eligible task\n4. Use the task's acceptance criteria as exit conditions\n5. After committing, update task status to \u0060■ complete\u0060\n6. If unexpected, add to \u0060## Surprises\u0060\n7. If a task doesn't make sense, mark it \u0060skipped\u0060\n\nWhen all tasks complete:\n\n1. Archive PLAN.md to \u0060.agentera/archive/plan-{date}.yaml\u0060\n2. Delete \u0060.agentera/plan.yaml\u0060\n3. Realisera resumes vision-driven work selection\n\n---\n\n## Safety rails\n\n<critical>\n\n- NEVER include implementation details in PLAN.md. Planera owns WHAT and WHY. Realisera owns HOW.\n- NEVER write acceptance criteria that reference implementation. Use behavioral, domain-language criteria only.\n- NEVER produce more than 8 tasks in a full plan. If work requires more, split into sequential plans.\n- NEVER modify PLAN.md during a realisera cycle except to update task status and add surprises.\n- NEVER skip adversarial review for full plans.\n- NEVER auto-approve plans when human-initiated. Present for approval.\n- NEVER plan trivial work. If skip level, say so and stop.\n\n</critical>\n\n---\n\n## Exit signals\n\nReport one of these statuses at workflow completion (protocol refs: EX1-EX4).\n\nFormat: \u0060─── ≡ planera · <status> ───\u0060 followed by a summary sentence.\nFor flagged, stuck, and waiting: add \u0060▸\u0060 (VT15) bullet details.\n\n- **complete** (EX1): PLAN.md written and approved, adversarial review ran for full plans, handoff suggested.\n- **flagged** (EX2): Plan produced with caveats: critic issues dismissed, scope larger than ideal, or acceptance criteria not fully behavioral.\n- **stuck** (EX3): Cannot plan: description too ambiguous, context files contradict, or user declined approval with no revision path.\n- **waiting** (EX4): Feature not specified enough for acceptance criteria, or key architectural constraints unknown.\n\n---\n\n## Cross-capability integration\n\nPlanera is the bridge between deliberation and execution.\n\n### Fed by ❈ resonera\n\nWhen resonera's deliberation concludes with a decision to build, the next step is ≡ planera. DECISIONS.md provides the \"why\" context.\n\n### Feeds ⧉ realisera\n\nPLAN.md tasks become realisera's work queue. Task acceptance criteria become cycle exit conditions. Realisera updates status and logs surprises.\n\n### Feeds ⎘ optimera\n\nWhen a plan includes optimization-shaped tasks, those tasks can be delegated to optimera.\n\n### Informed by ⛶ inspektera\n\nHEALTH.md findings can trigger remediation plans. Inspektera reveals structural issues; planera produces a plan to address them.\n\n### Informed by ♾ profilera\n\nDecision profile calibrates planning depth and pattern preferences.\n\n### Informed by ⬚ inspirera\n\nWhen inspirera recommends patterns or libraries, planera incorporates them into the plan's design section.\n\n### Reads ⛥ visionera output\n\nVISION.md provides the north star that planera reads during Orient.\n\n### Fed by ▤ dokumentera (docs-first workflow)\n\nIn the docs-first workflow, dokumentera writes intent docs first, then planera decomposes them into tasks.\n\n### Reads ▤ dokumentera versioning conventions\n\nPlanera reads the \u0060versioning\u0060 block from DOCS.md. When the plan includes \u0060feat\u0060/\u0060fix\u0060 work, planera appends a version bump task.\n\n---\n\n## Getting started\n\n### Planning a new feature\n\n1. ❈ resonera: deliberate on what to build and why\n2. ≡ planera: plan how to build it\n3. ⧉ realisera or ⎈ orkestrera: execute\n\n### Planning a remediation\n\n1. ⛶ inspektera: audit codebase health\n2. ≡ planera: plan fixes\n3. ⧉ realisera: execute\n\n### Mid-feature replanning\n\nIf realisera logs multiple surprises in PLAN.md:\n\n1. Read the surprises section\n2. ≡ planera: reassess tasks\n3. Resume ⧉ realisera\n\n### Skipping the plan\n\nFor trivial work, planera detects skip level and routes to ⧉ realisera directly.\n"`);
+export default instructions;
+//# sourceMappingURL=instructions.js.map

package/dist/capabilities/planera/instructions.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"instructions.js","sourceRoot":"","sources":["../../../src/capabilities/planera/instructions.ts"],"names":[],"mappings":"AAAA,+EAA+E;AAC/E,qFAAqF;AACrF,yFAAyF;AACzF,MAAM,CAAC,MAAM,YAAY,GAAW,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,CAAA,+2eAA+2e,CAAC,CAAC;AAC16e,eAAe,YAAY,CAAC"}

package/dist/capabilities/profilera/instructions.js

@@ -0,0 +1,6 @@
+// Source: skills/agentera/capabilities/profilera/instructions.md (relocated D65)
+// Markdown body lifted verbatim; the JSON literal below round-trips to byte-for-byte
+// equivalence with the deleted file (whitespace allowed to differ at line endings only).
+export const instructions = JSON.parse(String.raw `"# PROFILERA\n\n**Persona Reconstruction: Observable Footprint Indexing Logic. Extract, Reconcile, Formalize**\n\nMine the user's session history and produce a structured decision profile for predicting \"What would this person decide?\" Each entry carries numeric confidence, permanence classification, and temporal metadata enabling dormancy decay.\n\nSkill introduction: \u0060─── ♾ profilera · profile ───\u0060\n\n---\n\n## Visual identity\n\nGlyph: **♾** (protocol ref: SG9). Used in the mandatory exit marker.\n\n---\n\n## State artifacts\n\nOne global artifact (written) and project-level artifacts (read).\n\n| Artifact | Purpose | Path |\n|----------|---------|------|\n| PROFILE.md | Decision profile consumed by all capabilities | \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060 (default: \u0060$XDG_DATA_HOME/agentera/PROFILE.md\u0060) |\n| DECISIONS.md | High-signal source for pattern extraction | \u0060.agentera/decisions.yaml\u0060 (per docs.yaml mapping) |\n\n### Artifact path resolution\n\nPROFILE.md is global. Its base directory defaults to the platform-appropriate data directory (\u0060$XDG_DATA_HOME/agentera/\u0060 on Linux, \u0060~/Library/Application Support/agentera/\u0060 on macOS, \u0060%APPDATA%/agentera/\u0060 on Windows). Override via \u0060PROFILERA_PROFILE_DIR\u0060 environment variable. Existing profiles at \u0060~/.claude/profile/\u0060 are auto-migrated on first run. \u0060.agentera/docs.yaml\u0060 mapping does not apply to PROFILE.md. For project-level artifacts, check if .agentera/docs.yaml exists and use its path mapping; if absent, use the default layout.\n\n### Contract values\n\nContract values are inlined where referenced. Confidence scale tiers CS1-CS5 for numeric boundaries (90-100, 70-89, 50-69, 30-49, 0-29) with thresholds at 65 (strong constraint) and 45 (suggestion). Visual tokens: confidence tokens VT9-VT11 (━/─/┄), list item VT15 (▸), inline separator VT16 (·), section divider VT14, progress bar VT18. Skill glyph SG9 for exit markers. Exit signals EX1-EX4 for status reporting. Decision labels DL1-DL3 for entry firmness.\n\n\u0060references/contract.md\u0060 (at the v2 skill location \u0060skills/agentera/references/contract.md\u0060) remains available as a full-spec reference for ambiguous cases or cross-checking.\n\n---\n\nTwo modes:\n\n- **Full**: Detect available local runtime history, ask which extractable runtimes to include, synthesize from scratch, write a fresh PROFILE.md.\n- **Validate**: Quick incremental check. Surface the ~6 entries most worth validating, let the user confirm or challenge each one, update metadata in place.\n\n---\n\n## Step 0: Detect mode\n\nBefore doing anything else, check if \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060 exists (default: \u0060$XDG_DATA_HOME/agentera/PROFILE.md\u0060).\n\n**If it does NOT exist**: Proceed directly to Full mode (Step 1).\n\n**If it DOES exist**: Present the mode choice.\n\nNarration voice (riff, don't script):\n\n- \"Profile's here. Full rebuild or quick tune-up?\" · \"You've got a profile already. Regenerate from scratch, or just validate what's there?\"\n\nOffer:\n\n> **Full**: Regenerate from scratch using all session data. Replaces the existing profile including any accumulated tensions. Best when the profile feels significantly outdated or you want a clean baseline.\n>\n> **Validate**: Quick check of your existing profile (~2 minutes). Reviews the entries most worth validating: confirm, challenge, or skip each one. Best for regular maintenance between full regenerations.\n\nIf the user chooses **Full**, proceed to Step 1.\nIf the user chooses **Validate**, skip to Validate Mode.\n\n---\n\n## Full Mode\n\nThe sharp colleague, here to pay attention to how you decide, not run a classification pipeline. This is someone who's been watching your work, noticing patterns, and reflecting back what they've seen. \"Here's what I've noticed about how you work,\" not \"Signal extraction complete.\"\n\nStep markers: display \u0060── step N/6: verb\u0060 before each step.\nSteps: detect, extract, read, categorize, generate, validate.\n\n### Step 1: Detect runtime sources\n\nBefore asking what to include, run a deterministic local preview that uses the extractor defaults and writes a temporary preview corpus:\n\n\u0060\u0060\u0060bash\nnpx -y agentera report refresh --consent local-history --output <temporary-preview-corpus>\n\u0060\u0060\u0060\n\nRead only the preview corpus top-level \u0060metadata.runtime_statuses\u0060 plus per-runtime record counts. Do not display raw transcript content in the source-selection prompt. Remove the temporary preview after source selection unless it is reused as the final corpus for \u0060All (Recommended)\u0060.\n\nTreat a runtime as selectable only when its status is \u0060ok\u0060 and its \u0060record_count\u0060 is greater than zero. Treat \u0060missing\u0060, \u0060skipped\u0060, \u0060sparse\u0060, and \u0060degraded\u0060 runtimes as unavailable for this run; report them briefly with bounded status/reason labels and remediation labels when present.\n\nSupported runtime sources:\n\n- **Claude Code**: default \u0060~/.claude/projects\u0060, override with \u0060--claude-projects-dir <path>\u0060, disable with \u0060--no-claude\u0060\n- **Codex**: default \u0060~/.codex/sessions\u0060, override with \u0060--codex-sessions-dir <path>\u0060, disable with \u0060--no-codex\u0060\n- **OpenCode**: default \u0060opencode db path\u0060 when available, override with \u0060--opencode-conversations-dir <path>\u0060, disable with \u0060--no-opencode\u0060\n- **GitHub Copilot**: default \u0060$COPILOT_HOME\u0060 or \u0060~/.copilot\u0060, override with \u0060--copilot-conversations-dir <path>\u0060, disable with \u0060--no-copilot\u0060\n- **Cursor IDE**: default \u0060$CURSOR_HOME/projects\u0060 or \u0060~/.cursor/projects\u0060, override with \u0060--cursor-projects-dir <path>\u0060, disable with \u0060--no-cursor\u0060\n- **Cursor Agent CLI**: default \u0060~/.config/cursor/chats\u0060, override with \u0060--cursor-chats-dir <path>\u0060 or \u0060$CURSOR_CONFIG_HOME/chats\u0060; disabled with \u0060--no-cursor\u0060\n\nAsk which runtime histories to include with a multi-select question. Put \u0060All (Recommended)\u0060 first; it means every selectable runtime from the preview and wins over any individual runtime selections. Also offer one option per selectable runtime and a docs/config-only option for cases where the user wants no runtime conversation history. The question controls runtime conversation sources only; instruction documents and project config signals remain included.\n\nIf no runtime has extractable records, skip the selection question, say no local runtime history is currently extractable, and continue with instruction documents and project config signals.\n\n### Step 2: Run extraction\n\nRead \u0060$PROFILERA_PROFILE_DIR/intermediate/corpus.json\u0060 if it already exists and still matches the selected runtime set. If the corpus is absent, stale, or was produced for a different source selection, run the extractor from the Agentera app:\n\n\u0060\u0060\u0060bash\nnpx -y agentera report refresh --consent local-history\n\u0060\u0060\u0060\n\nApply runtime opt-out flags from Step 1. For example, if the user selects Claude Code and OpenCode only, run with \u0060--no-codex --no-copilot --no-cursor\u0060. If the user selects docs/config-only, run with \u0060--no-claude --no-codex --no-opencode --no-copilot --no-cursor\u0060. If the user selects \u0060All (Recommended)\u0060, use no runtime opt-out flags.\n\nThe extractor writes the default \u0060$PROFILERA_PROFILE_DIR/intermediate/corpus.json\u0060 envelope and emits the four portable Section 22 families: \u0060instruction_document\u0060, \u0060history_prompt\u0060, \u0060conversation_turn\u0060, and \u0060project_config_signal\u0060. Use \u0060--output <path>\u0060, repeated \u0060--project-root <path>\u0060, \u0060--codex-sessions-dir <path>\u0060, \u0060--claude-projects-dir <path>\u0060, \u0060--opencode-conversations-dir <path>\u0060, \u0060--copilot-conversations-dir <path>\u0060, \u0060--cursor-projects-dir <path>\u0060, or \u0060--cursor-chats-dir <path>\u0060 when the host stores data outside the defaults.\n\nRead the corpus file's top-level \u0060metadata\u0060 object to confirm counts per source family. Report totals to the user.\n\n**If extraction fails**: common causes include \u0060npx\u0060/agentera not found, permission errors, and empty output (no session history). If only some runtimes fail, the corpus will contain partial data with bounded runtime notes in \u0060metadata.runtime_statuses\u0060; proceed and note missing sources.\n\n---\n\n### Step 3: Read corpus data\n\nRead the corpus.json produced in Step 2. Each record carries a \u0060source_kind\u0060 field. Group records by source family for synthesis:\n\n1. **instruction_document**: Memory files, CLAUDE.md, AGENTS.md (highest signal: explicit user instructions)\n2. **history_prompt**: Decision-rich prompts from session history\n3. **conversation_turn**: Decision exchanges from conversations (most nuanced: real-time reasoning)\n4. **project_config_signal**: Recurring config patterns across projects (most objective: what shipped)\n\nRead the full corpus before synthesis. If total records exceed 500, prioritize high-signal records:\n\n- history correction or decision kinds\n- longer user responses\n- configs shared across projects\n\n---\n\n### Step 4: Categorize and synthesize\n\nGroup signals into 12 categories:\n\n1. **Architecture & Design Patterns**: package layout, abstraction boundaries, API design\n2. **Technology & Tooling Selection**: languages, frameworks, libraries, build tools\n3. **Agent & Automation Philosophy**: agent behavior, autonomy, interaction patterns\n4. **Code Quality & Standards**: error handling, testing, validation, naming\n5. **DX & Project Structure**: directory layout, build targets, configuration\n6. **Scoping & Prioritization**: what to build, milestones, complexity budgets\n7. **Communication Style**: writing preferences, documentation voice\n8. **Process & Workflow**: git workflow, commit conventions, release process\n9. **UI/UX Preferences**: visual patterns, interaction design, CLI vs TUI vs web\n10. **Trade-off Heuristics**: simplicity vs flexibility, speed vs correctness\n11. **Anti-patterns & Rejections**: things actively avoided, with reasoning\n12. **Meta-decision Style**: frameworks used, information gathering, decide vs defer\n\nPer category: identify distinct decisions (not just preferences; decisions have conditions and reasoning), look for the *why*, note exceptions where the rule was overridden.\n\n#### Assign confidence (numeric, 0-100, protocol ref: CS1-CS5)\n\nDecision patterns are empirically verifiable via git history and configs:\n\n| Range | Label | Token | Criteria |\n|-------|-------|-------|----------|\n| 90-100 (CS1) | Shipped consistently | ━ (VT9) | Appears in configs/code across 3+ projects, verifiable from artifacts |\n| 70-89 (CS2) | Established | ━ (VT9) | Consistent across sessions, corroborated by behavior |\n| 50-69 (CS3) | Emerging | ─ (VT10) | Observed multiple times but limited context or minor variations |\n| 30-49 (CS4) | Single signal | ┄ (VT11) | One data point or inferred from adjacent patterns |\n| 0-29 (CS5) | Speculative | ┄ (VT11) | No direct evidence, extrapolated from related decisions |\n\n**Bias check**: Confidence is earned through evidence, not assigned by how insightful the decision sounds. A pithy design principle observed once is 30, not 75.\n\n#### Assign permanence class\n\nPermanence captures domain *stability*, independent of confidence. You can be highly confident about something that will change (85, situational) or uncertain about something deep (35, stable).\n\n| Class | Domain | Timescale |\n|-------|--------|-----------|\n| **stable** | Architecture principles, design patterns, meta-decision heuristics | Decade |\n| **durable** | Tooling choices, code standards, process conventions, DX preferences | Year |\n| **situational** | Current project priorities, active initiative choices, recent tech stack picks | Month |\n\nDefault permanence mapping by category:\n\n- Architecture & Design Patterns, Meta-decision Style → stable\n- Technology & Tooling, Code Quality & Standards, Process & Workflow, DX & Project Structure,\n  Communication Style, Trade-off Heuristics, Anti-patterns → durable\n- Scoping & Prioritization, UI/UX Preferences → situational (unless clearly long-standing)\n- Agent & Automation Philosophy → durable (unless project-specific)\n\nOverride the default when the evidence suggests otherwise.\n\n#### Set dates\n\n- **first**: Earliest timestamp from the source data that evidences this decision\n- **refresh date**: Set to today's date (the generation date)\n- **challenged**: Set to \u0060—\u0060 (none yet on a fresh profile)\n\n#### Identify tensions\n\nLook for cross-category patterns and contradictions: stated principle vs shipped code, conflicts between categories, \"Exceptions\" suggesting a weaker rule. Record contradictions in the Tensions section rather than smoothing them into a coherent narrative.\n\n---\n\n### Step 5: Generate the profile\n\nOutput constraint: ≤30 words per signal, ≤15 words per evidence line.\n\nWrite the decision profile to \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060.\n\nIf a previous version exists: copy to \u0060$PROFILERA_PROFILE_DIR/history/PROFILE-{timestamp}.md\u0060, generate new version, show change summary (added, updated, removed).\n\nWhen presenting the profile, frame it as a colleague reflecting on what they've observed, not a system delivering results. Open with what stood out, what surprised you, where the user is most consistent and where they contradict themselves. The structured profile follows, but the human read comes first.\n\n#### Profile format\n\n\u0060\u0060\u0060markdown\n# Decision Profile: [User Name]\n\n<!-- Generated: {date} | Data: {date range from earliest to latest timestamp} -->\n<!-- Sources: {N} memory files, {N} history prompts, {N} conversation exchanges, {N} configs -->\n<!-- Decay parameters: stable λ=0.001, durable λ=0.005, situational λ=0.015 -->\n<!-- Formula: effective_conf = conf × e^(-λ × days_since_confirmed), floor 20 -->\n<!-- Regenerate with /agentera profile -->\n\n## How to Use This Profile\n\nThis profile captures decision-making patterns extracted from {N} months of sessions across {N} projects. Each entry carries inline metadata:\n\n\u0060━ conf:75 | perm:durable | first:2026-01-15 | confirmed:2026-03-28 | challenged:—\u0060\n\n- **conf** (0-100): Evidence-based confidence. 90+ shipped consistently (CS1), 70-89\n  established (CS2), 50-69 emerging (CS3), 30-49 single signal (CS4), 0-29 speculative (CS5).\n  Line weight tokens: ━ (VT9) high (90-100), ─ (VT10) medium (50-89), ┄ (VT11) low (0-49).\n- **perm**: How stable the decision domain is. stable (decade), durable (year),\n  situational (month).\n- **dates**: When the decision was first observed, refreshed,\n  and last challenged.\n\nWhen consuming this profile, compute effective confidence using the decay formula.\nStale situational entries carry less weight than fresh stable ones.\n\n**When the profile is silent**: If a situation isn't covered, look for the closest trade-off\nheuristic or meta-decision pattern. When truly uncertain, ask.\n\n## Decision-Making Philosophy\n\n[2-3 paragraphs describing the meta-patterns: how this person approaches decisions, what\nframeworks they use, their risk posture, when they decide quickly vs deliberate, what\ninformation they seek before deciding]\n\n## [Category Name]\n\n### [Decision Name]\n\u0060━ conf:75 | perm:durable | first:2026-01-15 | confirmed:2026-03-28 | challenged:—\u0060\n\n- ▸ **Rule**: [Imperative statement an agent can follow directly]\n- ▸ **When**: [Specific conditions or triggers for this rule]\n- ▸ **Why**: [The reasoning, the value or concern that drives this]\n- ▸ **Exceptions**: [Known cases where this was overridden, or \"None observed\"]\n\n[Repeat for each decision in the category. Order by confidence (highest first).]\n\n[Repeat for all 12 categories. Skip categories with no signal.]\n\n## Tensions\n\nEach entry records a contradiction or divergence found during profile generation or challenged during validation. Default status is **unresolved**. Resist the urge to wrap tensions in resolution narratives. Some tensions are real and persistent.\n\n### YYYY-MM-DD: [Short description]\n\n**Decision affected**: [which decision was contradicted]\n**What happened**: [what was observed or said that didn't fit]\n**Status**: unresolved\n\u0060\u0060\u0060\n\n#### Writing guidelines\n\n- Write rules as imperatives (\"Use X\" not \"[Name] prefers X\")\n- Be specific (\"when building Go CLIs\" not \"when building things\")\n- Always include the *why* because agents need reasoning for edge cases\n- Don't duplicate CLAUDE.md. This covers decision *patterns*, not project instructions\n- Omit categories with <2 decisions (insufficient signal)\n- Every entry MUST have inline metadata after the ### heading\n\n---\n\n### Step 6: Validate predictions\n\nPick 5 decision-rich prompts NOT used to create profile entries. For each: predict what the profile would recommend, check against what happened. Report accuracy (e.g., \"4/5\"). Below 3/5: identify categories needing more signal, note in profile header.\n\n---\n\n## Validate Mode\n\nQuick incremental check (~2 minutes). Same colleague voice: you're checking in on what you noticed before, not running a diagnostic. \"Still true? Let me know.\"\n\nStep markers: display \u0060── step N/4: verb\u0060 before each step.\nSteps: select, present, apply, write.\n\n### Step V1: Run smart selection\n\nIdentify which entries are most worth checking by reading \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060 directly and prioritizing high-confidence, stale, or tension-heavy entries. If PROFILE.md is missing, fall back to Full mode.\n\n### Step V2: Present entries for validation\n\nPresent entries one at a time: decision name, rule text, reason surfaced, stored vs effective confidence. Ask: **Confirm**, **Challenge**, or **Skip**.\n\n### Step V3: Apply updates\n\nFor each response:\n\n- **Confirm**: Bump \u0060conf\u0060 by 5 (cap at 95). Update \u0060confirmed\u0060 to today's date.\n- **Challenge**: Soften \u0060conf\u0060 by 10 (floor at 10). Update \u0060challenged\u0060 to today's date.\n  Append a tension entry to the \u0060## Tensions\u0060 section:\n\n  \u0060\u0060\u0060\n  ### {today}: {decision name} challenged during validation\n  **Decision affected**: {decision name}\n  **What happened**: Challenged by user during validation\n  **Status**: unresolved\n  \u0060\u0060\u0060\n\n- **Skip**: No changes to this entry.\n\n### Step V4: Write and report\n\nWrite updated PROFILE.md. Report: \"Reviewed {N} entries: {N} accepted, {N} challenged, {N} skipped.\" Mention challenged entries by name.\n\n---\n\n## Safety rails\n\n<critical>\n- NEVER fabricate decision patterns. Every profile entry must be grounded in observed evidence from session history, memory files, configs, or conversation data.\n- NEVER assign confidence higher than the evidence warrants. A single data point is 30-49 (CS4), not 70+, regardless of how insightful the decision sounds.\n- NEVER smooth over contradictions. When evidence conflicts, record tensions rather than forcing a coherent narrative.\n- NEVER modify the user's session history, memory files, or config files. Profilera reads these sources; it never writes to them.\n- NEVER share profile contents with external services or include them in commits.\n</critical>\n\n---\n\n## Exit signals\n\nReport one of these statuses at workflow completion (protocol refs: EX1-EX4).\n\nFormat: emit \u0060♾ profilera · <status>\u0060 on its own line, followed by a one-sentence summary. For \u0060flagged\u0060 (EX2), \u0060stuck\u0060 (EX3), and \u0060waiting\u0060 (EX4), add a ▸ (VT15) bullet below the summary identifying what needs attention. The exit marker uses profilera's canonical glyph ♾ (SG9, U+267E).\n\n- **complete** (EX1): PROFILE.md was written (Full mode) or updated (Validate mode). Metadata changes were applied, prediction accuracy was assessed, and changes were summarized.\n- **flagged** (EX2): Profile generation or validation completed but with data quality issues: extraction failed for one or more sources, prediction accuracy was below 3/5, or significant tensions were found that could not be resolved from available evidence.\n- **stuck** (EX3): Cannot generate or validate a profile because the extraction scripts failed entirely, Python is unavailable, or \u0060~/.claude/\u0060 is unreadable and no session data can be accessed.\n- **waiting** (EX4): The user chose Validate mode but PROFILE.md lacks valid metadata. A Full mode run needs user approval, or the requested mode is ambiguous.\n\n---\n\n## Cross-capability integration\n\nProfilera is part of a twelve-capability suite. The decision profile it produces is consumed by the other capabilities.\n\n### Consumed by realisera\n\nRealisera runs the effective profile script in its Orient step to get a confidence-weighted summary table. High effective confidence entries are treated as strong constraints; low effective confidence entries are treated as suggestions. Full rules are read from PROFILE.md when needed for detailed reasoning.\n\n### Consumed by optimera\n\nOptimera runs the effective profile script to calibrate experimentation style: how aggressive to be, how much complexity is acceptable, what trade-offs the user prefers. Effective confidence weighting ensures stale preferences don't over-constrain experiments.\n\n### Consumed by inspirera\n\nInspirera can run the effective profile script to inform applicability judgments: what patterns the user favors, what they resist, how to weigh recommendations. High-confidence entries strongly constrain recommendations; low-confidence entries are treated as tendencies.\n\n### Consumed by resonera\n\nResonera reads the decision profile at the start of every deliberation. High-confidence entries in the relevant domain are acknowledged upfront to prevent re-deliberating settled preferences. Low-confidence entries are surfaced as hypotheses worth testing during the conversation.\n\n### Fed by resonera\n\nDECISIONS.md (maintained by resonera) is a high-signal source for profilera's extraction scripts. Each decision entry captures reasoning, tradeoffs, and confidence, making deliberation sessions one of the richest inputs for decision profile generation. For normal read-only extraction, prefer \u0060agentera decisions --format json\u0060 and preserve returned \u0060missing_fields\u0060, \u0060compacted\u0060, \u0060caveats\u0060, and \u0060satisfaction.review_needed\u0060 pressure rather than raw-reading missing historical context.\n\n### Consumed by inspektera\n\nInspektera reads the decision profile to calibrate what \"healthy\" means for this user. Quality preferences, complexity tolerance, and pattern priorities from the profile weight the grading and determine which findings matter most.\n\n### Consumed by planera\n\nPlanera reads the decision profile during its Orient step to calibrate planning depth, pattern preferences, and constraint priorities.\n\n### Profile consumption\n\nAll consuming capabilities read \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060 directly when it exists. Confidence thresholds and dormancy notes are kept in the profile itself so the guidance remains editable and portable.\n\n---\n\n## Getting started\n\n### First profile generation\n\n\u0060\u0060\u0060\n/agentera profile\n\u0060\u0060\u0060\n\nFull extraction across all sources. Produces \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060.\n\n### Regular validation\n\n\u0060\u0060\u0060\n/agentera profile validate\n\u0060\u0060\u0060\n\nQuick confidence refresh without full regeneration. Run weekly or per-session.\n\n### Using the profile in other capabilities\n\nAll capabilities may read the profile directly when \u0060PROFILE.md\u0060 exists. No manual steps needed; just ensure PROFILE.md exists.\n\n---\n\n## Notes on depth vs speed\n\n- Extraction scripts handle I/O; Claude's job is synthesis, not parsing.\n- Large intermediate files: use subagents to read in parallel.\n- Signal hierarchy: crystallized.json (highest: memory + CLAUDE.md), conversation exchanges (most nuanced: real-time reasoning), config patterns (most objective: what shipped).\n- Validate mode: weekly/per-session. Full mode: monthly or when significantly stale.\n"`);
+export default instructions;
+//# sourceMappingURL=instructions.js.map

package/dist/capabilities/profilera/instructions.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"instructions.js","sourceRoot":"","sources":["../../../src/capabilities/profilera/instructions.ts"],"names":[],"mappings":"AAAA,iFAAiF;AACjF,qFAAqF;AACrF,yFAAyF;AACzF,MAAM,CAAC,MAAM,YAAY,GAAW,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,CAAA,8lwBAA8lwB,CAAC,CAAC;AACzpwB,eAAe,YAAY,CAAC"}

package/dist/capabilities/realisera/instructions.js

@@ -0,0 +1,6 @@
+// Source: skills/agentera/capabilities/realisera/instructions.md (relocated D65)
+// Markdown body lifted verbatim; the JSON literal below round-trips to byte-for-byte
+// equivalence with the deleted file (whitespace allowed to differ at line endings only).
+export const instructions = JSON.parse(String.raw `"# REALISERA\n\n**Relentless Execution: Autonomous Loops Iterating Software. Evolve, Refine, Adapt**\n\nAn autonomous development loop that evolves any software project one cycle at a time. Decisions grounded in the user's decision profile. Continuity lives in files, not memory.\n\nEach invocation = one cycle. \u0060/loop\u0060 handles recurrence.\n\n---\n\n## Visual identity\n\nGlyph: **⧉** (protocol ref: SG2). Used in the mandatory exit marker.\n\n---\n\n## State artifacts\n\nFour artifacts, bootstrapped if absent. TODO.md and CHANGELOG.md stay at project root; canonical VISION.md and PROGRESS.md are stored as \u0060.agentera/vision.yaml\u0060 and \u0060.agentera/progress.yaml\u0060 unless mapped otherwise.\n\n| File | Purpose | Bootstrap |\n|------|---------|-----------|\n| \u0060VISION.md\u0060 | Canonical vision artifact. North star, direction, principles, aspirations. | Via inline brainstorm session (see below), written to \u0060.agentera/vision.yaml\u0060 by default. |\n| \u0060TODO.md\u0060 | Tech debt, bugs, discrepancies. | \u0060# TODO\\n\\n## ⇶ Critical\\n\\n## ⇉ Degraded\\n\\n## → Normal\\n\\n## ⇢ Annoying\\n\\n## Resolved\\n\u0060 |\n| \u0060CHANGELOG.md\u0060 | Public change history. | \u0060# Changelog\\n\\n## [Unreleased]\\n\u0060 |\n| \u0060PROGRESS.md\u0060 | Canonical progress artifact. Operational cycle log. | First cycle entry in \u0060.agentera/progress.yaml\u0060 by default. |\n\nUse \u0060agentera schema --format json\u0060 and its \u0060artifact_schemas\u0060 entries for \u0060vision\u0060 and \u0060progress\u0060 to locate the active installed schemas; do not search Agentera directories manually. Top-level \u0060agentera describe\u0060 is a migration alias.\n\n### Artifact path resolution\n\nBefore reading or writing any artifact, check if \u0060.agentera/docs.yaml\u0060 exists. If it has an Artifact Mapping section, use the path specified for each canonical filename (VISION.md, TODO.md, .agentera/progress.yaml, etc.). If \u0060.agentera/docs.yaml\u0060 doesn't exist or has no mapping for a given artifact, use the default layout: TODO.md, CHANGELOG.md, and DESIGN.md at the project root; canonical VISION.md at \u0060.agentera/vision.yaml\u0060; other agent-facing artifacts at \u0060.agentera/*.yaml\u0060.\n\n### Contract values\n\nContract values are inlined where referenced. Visual tokens from protocol: severity arrows VT5-VT8 (⇶/⇉/→/⇢), status tokens VT1-VT4 (■/▣/□/▨), list item VT15 (▸), inline separator VT16 (·), section divider VT14, flow/target VT17 (→). Skill glyphs SG1-SG12 for cross-capability references. Exit signals EX1-EX4 for the exit marker. Severity issue levels SI1-SI4 for TODO classification. Decision labels DL1-DL3 for DECISIONS.md entries. Confidence scale CS1-CS5 with thresholds for profile consumption.\n\n\u0060references/contract.md\u0060 (at the v2 skill location \u0060skills/agentera/references/contract.md\u0060) remains available as a full-spec reference for ambiguous cases or cross-checking.\n\n### vision.yaml\n\nEvergreen. Created via brainstorm on first run, refined only when the user explicitly asks. Outside those two cases, the agent reads it but never writes it. A constitution, not a backlog.\n\n\u0060\u0060\u0060yaml\nproject_name: Project Name\nnorth_star: The dream. What this software makes possible.\npersonas:\n  - name: Specific persona\n    description: Their day, frustrations, and workflow.\nprinciples:\n  - name: Principle name\n    description: What it means and what it resists.\ndirection: Where this project is heading.\nidentity:\n  personality: Product personality.\n  voice: Communication style.\n  emotional_register: How it should feel to use.\n  naming: Naming conventions.\ntension: The hardest strategic tension.\n\u0060\u0060\u0060\n\n### progress.yaml\n\n\u0060\u0060\u0060yaml\ncycles:\n  - number: N\n    timestamp: YYYY-MM-DD HH:MM\n    type: feat\n    phase: build\n    what: One-line summary of what shipped.\n    inspiration: External source, if any.\n    discovered: Issues or ideas found.\n    verified: Observed output, N/A tag, or rationale.\n    next: Most valuable next work.\n    context:\n      intent: Why this cycle happened.\n      constraints: What had to stay true.\n      unknowns: What remains uncertain.\n      scope: What changed.\narchive: []\n\u0060\u0060\u0060\n\nThe \u0060verified\u0060 field is mandatory for every cycle entry.\n\n### CHANGELOG.md\n\nPublic-facing change history. Keep-a-changelog format. Realisera appends entries under \u0060## [Unreleased]\u0060 based on commit type: \u0060feat\u0060 → Added, \u0060refactor/chore\u0060 → Changed, \u0060fix\u0060 → Fixed. On version bumps, promote the Unreleased section to a versioned heading.\n\n---\n\n## Brainstorm: bootstrapping or refining the vision artifact\n\nThis runs in two situations:\n\n1. **The vision artifact doesn't exist**: the first time realisera runs on a project\n2. **User explicitly asks** to refine the vision\n\nIn all other cases, skip straight to the cycle.\n\nThe sharp colleague, here to build. Brief, focused conversation. One question at a time. Push for ambition.\n\n1. **Understand the dream**: \"Not what the software does, but what does it make possible?\"\n2. **Find the people**: \"Who reaches for this? Describe a person: their day, their frustrations.\"\n3. **Find the principles**: \"What principles guide every decision?\" If a decision profile exists, propose principles from it.\n4. **Set the direction**: \"Where is this heading? Not features, but capabilities.\"\n5. **Write the vision artifact**: synthesize into an aspirational north star. Present for approval.\n\nArtifact writing follows contract Section 24 conventions: banned verbosity patterns, 25-word sentence cap, preferred vocabulary, and lead-with-conclusion structure.\n\n---\n\n## The cycle\n\nSkill introduction: \u0060─── ⧉ realisera · cycle N ───\u0060\n\nStep markers: display \u0060── step N/9: verb\u0060 before each step.\nSteps: orient, select, research, plan, spawn, verify, commit, audit, log.\n\n### Step 1: Orient\n\nStart from the supported Realisera execution-context seam:\n\n\u0060\u0060\u0060bash\nagentera prime --context realisera --format json\n\u0060\u0060\u0060\n\nIf \u0060execution_context.source_contract.complete_for_execution_context\u0060 is true,\nuse \u0060execution_context\u0060 and included \u0060capability_context.state\u0060 as normal startup context. Do\nnot read raw PLAN, PROGRESS, TODO, DOCS, HEALTH, DECISIONS, CHANGELOG, VISION,\nPROFILE, or DESIGN artifacts just to re-check selected work, acceptance\ncriteria, constraints, verification expectations, artifact update requirements,\nprogress logging requirements, changelog boundary, or scope caveats.\n\nIf \u0060execution_context\u0060 is incomplete or caveated, preserve every caveat in the\ncycle report and run the listed \u0060execution_context.fallback_commands\u0060 before any\nlast-resort raw artifact diagnostic. Raw artifact reads are last-resort\ndiagnostics, not normal Realisera startup behavior.\n\nFor progress fallback specifically, use \u0060npx -y agentera state progress --format json\u0060\nor the installed app equivalent from the returned fallback command; the routine\nprogress command owns startup progress state.\n\n### Decision satisfaction authority\n\nWhen a cycle touches decision satisfaction, agents may mark provisional\nsatisfaction with evidence only. Realisera must not mark or imply\nuser-confirmed satisfaction; only the user confirms final satisfaction. If\ndecisions are compacted, missing satisfaction state, open, provisional, or\nreview-needed, preserve the caveat and review pressure in the cycle report\ninstead of reconstructing hidden outcomes or claiming automation proved intent.\n\n1. **execution_context.work_selection**: selected task or no-plan/completed-plan mode\n2. **execution_context.acceptance_criteria**: exact criteria for this cycle\n3. **execution_context.constraints**: plan constraints and protected-action boundaries\n4. **execution_context.verification_expectations**: expected validation and latest progress evidence\n5. **execution_context.artifact_update_requirements**: plan, TODO, changelog, and progress update obligations\n6. **execution_context.changelog_boundary**: current public-history boundary or fallback\n7. **execution_context.scope_boundary**: artifact-family scope and conservative source-file scope\n8. **source_contract.capability_context**: missing state families and CLI fallback commands\n9. **profile summary**: use \u0060hej.profile\u0060; stale or missing profile is a caveat, not approval to refresh profile state.\n\n10. **Project discovery** (cycle 1 or when unfamiliar):\n    - Map the directory structure\n    - Read dependency manifests\n    - Read README.md, CLAUDE.md, AGENTS.md if they exist\n    - Identify build/test/lint commands\n    - Read key source files to understand architecture\n\n11. \u0060git log --oneline -20\u0060 for recent changes\n\nBefore proceeding, list the 3-5 facts that determine this cycle.\n\n**Exit-early stop condition (plan-driven mode only)**: If PLAN.md has \u0060header.status: complete\u0060 and every task is complete, perform a **plan-completion sweep** before archiving. A plan with blocked, skipped, or otherwise incomplete tasks is not a successfully completed plan and must remain visible for replanning or follow-up. This stop condition does NOT apply in vision-driven mode.\n\nSweep checklist:\n\n1. **PROGRESS.md aggregate cycle entry**: insert a newest-first cycle entry summarizing the whole plan.\n2. **CHANGELOG.md plan-level entries**: verify \u0060## [Unreleased]\u0060 covers each completed task's user-facing impact.\n3. **TODO.md milestone advance**: mark each plan task as Resolved.\n4. **HEALTH.md cross-reference**: mention any resolved findings.\n\nAfter the sweep, archive PLAN.md to \u0060.agentera/archive/PLAN-{date}-{slug}.yaml\u0060, preserve lineage/evidence in the archive or next plan's \u0060previous_plan_archived\u0060, remove the active \u0060.agentera/plan.yaml\u0060, and report exit signal \u0060complete: plan finished\u0060.\n\n### Step 2: Pick work\n\nChoose **one** focused increment. No backlog; decide by reasoning about the gap between vision and codebase, weighted against known issues.\n\nEach cycle: **build toward the vision, or fix something broken?** Consult the decision profile. A critical bug trumps a new feature; a minor nit doesn't block progress.\n\n**Building toward vision:** Read codebase + VISION.md, identify the gap, pick the smallest increment closing the most valuable part.\n\n**Fixing issues:** Pick from TODO.md by severity (critical > degraded > annoying).\n\n**Optimization-shaped work:** suggest ⎘ optimera for measurable metrics and\nwait for confirmation instead of silently delegating.\n\nWrite a 1-2 sentence rationale. Scope down aggressively.\n\nCompose a Context block for this cycle: intent, constraints, unknowns, and scope. Keep it ≤80 words.\n\n**Decision gate**: After selecting work, use \u0060agentera decisions --format json\u0060 and check whether any \u0060exploratory\u0060 (DL3) entries in DECISIONS.md relate to the selected work area. Preserve returned \u0060missing_fields\u0060, \u0060compacted\u0060, \u0060caveats\u0060, and \u0060satisfaction.review_needed\u0060 pressure in the cycle context instead of raw-reading missing historical context. If an exploratory decision is found: flag the uncertain foundation, suggest ❈ resonera to firm up the decision, and wait for confirmation before invoking it. In autonomous mode, proceed with the work but log the risk instead of silently delegating to resonera.\n\n### Step 3: Seek inspiration\n\nSearch for relevant external approaches before planning.\n\n1. **Assess**: bug fixes rarely benefit from inspiration. New features, architecture decisions, and unfamiliar domains do.\n2. **Search**: 2-3 targeted web queries for libraries, articles, repos, or patterns.\n3. **Analyze**: read promising finds deeply.\n4. **Integrate**: fold applicable patterns into the plan.\n\n### Step 4: Plan\n\nWrite a concrete plan: what changes in which files, expected behavior, verification approach.\n\nRead files you plan to modify before committing to the plan. If the docs-first workflow should update intent docs before tests and code, include that.\n\nKeep small enough for one agent session. Too large? Split and save the rest.\n\n### Step 5: Dispatch\n\n**Pre-spawn Git commit**: before creating the worktree, commit any pending artifact changes so the subagent branches from current state.\n\n1. Run \u0060git status --porcelain\u0060. If empty, skip to spawn.\n2. Stage only the artifact files this session wrote.\n3. Commit with \u0060chore(realisera): checkpoint before worktree dispatch\u0060.\n4. If pre-commit hooks reject: fix, re-stage, retry. If retry fails, abort spawn.\n\n**Stale-base awareness**: Before spawning, run \u0060git rev-list --count origin/main..HEAD\u0060. If count > 0, do not merge the worktree branch. Fetch the sub-agent's diff and apply it to the main checkout.\n\nRuntime subagent mechanisms:\n\n| Runtime | Substrate | Limitation |\n|---------|-----------|------------|\n| Claude Code | Task tool with worktree-aware prompt | Native in-session spawn. |\n| OpenCode | \u0060@<capability>\u0060 descriptors from \u0060~/.config/opencode/agents/*.md\u0060 or a host Task subagent | Same working tree unless this step explicitly creates and targets a manual git worktree. |\n| Codex CLI | \u0060~/.codex/agents/*.toml\u0060 descriptors plus \u0060[agents]\u0060 limits | Agentera setup installs descriptor files; do not write legacy \u0060[agents.<name>]\u0060 config blocks. |\n| Copilot CLI | User-driven \u0060/fleet\u0060 or equivalent host action | No guaranteed programmatic in-session spawn. |\n\nNever spawn workers by running unsupported capability-name CLI commands such as \u0060agentera realisera\u0060; use the runtime-native subagent surface with the implementation prompt below.\n\nSpawn an implementation sub-agent in a worktree with:\n\n- The plan from step 4\n- Relevant context files\n- Clear constraint: implement the plan and nothing else\n\n\u0060\u0060\u0060\nYou are implementing a focused change for [project].\n\n## Task\n[The plan]\n\n## Constraints\n- Implement ONLY what the plan describes. No scope creep.\n- Follow existing code patterns and conventions.\n- Read the files you are modifying before changing them.\n- Verify the change works as described, then run the project's test/build suite.\n- If you encounter a bug unrelated to your task, note it but do not fix it.\n\u0060\u0060\u0060\n\n### Step 6: Verify\n\nVerification has two phases: structural and behavioral. Both must pass before commit.\n\n**Phase A, structural verification**: After implementation:\n\n1. **Check the diff**: does it match the plan?\n2. **Functional check**: does the changed behavior work end-to-end?\n3. **Run the project's verification suite** (test/build/lint).\n\n**Phase B, behavioral verification gate**: observe the new behavior by running the project's primary entrypoint against real project state:\n\n- CLI tool: invoke with realistic arguments\n- Library/SDK: run a smoke driver\n- Web service: send a request to a production-shaped endpoint\n- Skill repo: \u0060npx -y agentera verify eval skills --skill <name>\u0060\n\nIf verification fails: diagnose, spawn a fix agent, re-verify.\n\n**N/A path**: If the cycle has no runnable behavior change, use \u0060N/A: <tag>\u0060 from the allowlist: \u0060docs-only\u0060, \u0060refactor-no-behavior-change\u0060, \u0060chore-dep-bump\u0060, \u0060chore-build-config\u0060, \u0060test-only\u0060.\n\n### Step 7: Commit\n\nOnce verified, commit with a conventional commit message: \u0060type(scope): summary\u0060.\n\nTypes: \u0060feat\u0060, \u0060fix\u0060, \u0060docs\u0060, \u0060refactor\u0060, \u0060chore\u0060, \u0060test\u0060. Include all related files. Never commit partial or broken work. Never push to remote.\n\nIf the current task is a version bump: read DOCS.md for the \u0060versioning\u0060 section. Update every file in \u0060version_files\u0060.\n\n### Step 8: Pre-write self-audit\n\nPre-write self-audit: run \u0060agentera lint --artifact <ARTIFACT> --text \"<DRAFT>\"\u0060 (or \u0060--file <PATH>\u0060; schema names such as \u0060decisions\u0060 auto-resolve the artifact file when no input is given) on the draft entry to check verbosity overruns, abstraction creep, and filler accumulation.\nMax 3 revision attempts. Flag with [post-audit-flagged] if still failing.\n\n### Step 9: Log\n\n**Dual-write**: realisera maintains the resolved PROGRESS.md YAML artifact and root CHANGELOG.md.\n\n- **TODO.md**: add newly discovered issues, mark resolved ones. Classify by severity (SI1-SI4).\n- **PROGRESS.md**: insert the newest cycle entry before older active cycles. The \u0060verified\u0060 field is mandatory.\n- **CHANGELOG.md**: append a one-line entry under \u0060## [Unreleased]\u0060.\n\nAfter writing PROGRESS.md, apply the schema COMPACTION rules if thresholds are exceeded: keep 10 full entries, keep up to 40 one-line archive entries, and drop beyond 50 total.\n\nArtifact writing follows contract Section 24 conventions.\n\nThen stop. One cycle complete.\n\n---\n\n## Safety rails\n\n<critical>\n\n- NEVER push to any remote. Local commits only.\n- NEVER bypass the project's test/lint/build suite.\n- NEVER modify git config or skip git hooks.\n- NEVER force push, amend published commits, or run destructive git operations.\n- NEVER add placeholder data or functionality.\n- NEVER modify files outside the project directory.\n- NEVER modify the vision artifact during a cycle. Only touch it during a brainstorm.\n- One cycle per invocation. Do not attempt multiple cycles.\n\n</critical>\n\n---\n\n## Handling blocked work\n\nIf blocked:\n\n1. Log blocker in TODO.md with context and decision needed\n2. Log skipped attempt in PROGRESS.md\n3. Pick different work and complete a full cycle on that instead\n\n---\n\n## Exit signals\n\nReport one of these statuses at workflow completion (protocol refs: EX1-EX4).\n\nFormat: \u0060─── ⧉ realisera · <status> ───\u0060 followed by a summary sentence.\nFor flagged, stuck, and waiting: add \u0060▸\u0060 (VT15) bullet details below the summary.\n\n- **complete** (EX1): One full cycle completed. Work selected, implemented, verified, committed, artifacts updated.\n- **flagged** (EX2): Cycle completed but with notable issues: verification warnings, scope reduction, or discoveries suggesting next cycle may face blockers.\n- **stuck** (EX3): Cannot complete: the vision artifact is missing and brainstorm can't proceed, all work blocked, or verification suite broken.\n- **waiting** (EX4): No vision artifact and no codebase to infer direction, or user instruction too ambiguous.\n\nBefore reporting any status, inspect the last 3 entries in PROGRESS.md. If all 3 record failed cycles, stop, log the failure pattern to TODO.md, and surface to the user. Do not attempt a 4th consecutive cycle on the same failing problem.\n\n---\n\n## Cross-capability integration\n\nRealisera is part of a twelve-capability suite.\n\n### Delegates to ⛥ visionera\n\nWhen visionera is installed and the vision artifact doesn't exist, suggest ⛥ visionera for deep vision creation. If visionera is NOT installed, the built-in brainstorm works as a standalone fallback.\n\n### Delegates to ⎘ optimera\n\nWhen picked work is optimization-shaped (improving a measurable metric), delegate to optimera.\n\n### Uses ⬚ inspirera\n\nIn Step 3 (Seek inspiration), search for external approaches. For deeper analysis, use \u0060/agentera research <url>\u0060.\n\n### Reads ♾ profilera output\n\nEvery cycle runs the effective profile script. Confidence thresholds (CS1-CS5) determine which entries are strong constraints vs suggestions.\n\n### Uses ❈ resonera for complex decisions\n\nWhen the brainstorm or work selection surfaces a decision too complex for inline resolution, suggest ❈ resonera.\n\n### Consumes ≡ planera plans\n\nWhen PLAN.md exists with pending tasks, Step 2 reads the plan instead of reasoning from vision. Pick next pending task with satisfied dependencies. Update task status. When \u0060header.status: complete\u0060 and every task is complete, run the plan-completion sweep, archive PLAN.md before removing active state, and preserve lineage/evidence.\n\n### Reads ▤ dokumentera output\n\nDOCS.md provides artifact path resolution. In the docs-first workflow, dokumentera writes intent docs that feed planera, which feeds realisera.\n\n### Reads ◰ visualisera output\n\nDESIGN.md provides visual identity context respected when building user-facing features.\n\n### Audited by ⛶ inspektera\n\nHEALTH.md findings become candidates for work selection. Run ⛶ inspektera every 5-10 cycles.\n"`);
+export default instructions;
+//# sourceMappingURL=instructions.js.map

package/dist/capabilities/realisera/instructions.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"instructions.js","sourceRoot":"","sources":["../../../src/capabilities/realisera/instructions.ts"],"names":[],"mappings":"AAAA,iFAAiF;AACjF,qFAAqF;AACrF,yFAAyF;AACzF,MAAM,CAAC,MAAM,YAAY,GAAW,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,CAAA,y4oBAAy4oB,CAAC,CAAC;AACp8oB,eAAe,YAAY,CAAC"}

package/dist/capabilities/resonera/instructions.js

@@ -0,0 +1,6 @@
+// Source: skills/agentera/capabilities/resonera/instructions.md (relocated D65)
+// Markdown body lifted verbatim; the JSON literal below round-trips to byte-for-byte
+// equivalence with the deleted file (whitespace allowed to differ at line endings only).
+export const instructions = JSON.parse(String.raw `"# RESONERA\n\n**Reflective Engagement: Socratic Observation Nexus. Examine, Reason, Arbitrate**\n\nStructured deliberation via Socratic questioning. Decisions captured as artifacts the suite consumes. The user thinks; the capability asks the right questions, challenges assumptions, and ensures sound reasoning before action.\n\nEach invocation = one deliberation. The user controls when it ends.\n\nSkill introduction: \u0060─── ❈ resonera · deliberation ───\u0060\n\n---\n\n## Visual identity\n\nGlyph: **❈** (protocol ref: SG4). Used in the mandatory exit marker.\n\n---\n\n## State artifacts\n\nOne file in \u0060.agentera/\u0060, bootstrapped if absent.\n\n| File | Purpose | Bootstrap |\n|------|---------|-----------|\n| \u0060DECISIONS.md\u0060 | Canonical decision artifact, stored as \u0060.agentera/decisions.yaml\u0060 unless mapped otherwise. What was decided, alternatives considered, and why. | First decision entry in YAML form. |\n\nUse \u0060agentera describe --format json\u0060 and its \u0060artifact_schemas\u0060 entry for \u0060decisions\u0060 to locate the active installed schema; do not search Agentera directories manually. Existing decisions artifacts provide repository-local examples of the shape.\n\n### Artifact path resolution\n\nBefore reading or writing any artifact, check if \u0060.agentera/docs.yaml\u0060 exists. If it has an Artifact Mapping section, use the path specified for each canonical filename. If \u0060.agentera/docs.yaml\u0060 doesn't exist or has no mapping for a given artifact, use the default layout: TODO.md, CHANGELOG.md, and DESIGN.md at the project root; canonical VISION.md at \u0060.agentera/vision.yaml\u0060; other agent-facing artifacts at \u0060.agentera/*.yaml\u0060.\n\nWhen feeding a decision into OBJECTIVE.md, write to the active objective's file at \u0060.agentera/optimera/<objective-name>/objective.yaml\u0060 using optimera's active-objective inference.\n\n### Contract values\n\nContract values are inlined where referenced. Visual tokens from protocol: confidence markers VT9-VT11 (━/─/┄), list item VT15 (▸), inline separator VT16 (·), section divider VT14. Skill glyphs SG1-SG12 for cross-capability references. Exit signals EX1-EX4 for the exit marker. Decision labels DL1-DL3 for confidence field. Severity issue levels SI1-SI4 for TODO entries.\n\n\u0060references/contract.md\u0060 (at the v2 skill location \u0060skills/agentera/references/contract.md\u0060) remains available as a full-spec reference.\n\n### decisions.yaml\n\n\u0060\u0060\u0060yaml\ndecisions:\n  - number: N\n    date: YYYY-MM-DD\n    question: what was being decided\n    context: relevant constraints, triggers, or prior decisions\n    alternatives:\n      - name: Option A\n        tradeoffs: Tradeoffs.\n        win_condition: Concrete signal that proves this option right.\n        chosen: true\n      - name: Option B\n        tradeoffs: Tradeoffs.\n        win_condition: Concrete signal that proves this option right.\n        chosen: false\n    choice: what was chosen\n    reasoning: the key insight or tradeoff that resolved it\n    confidence: firm\n    feeds_into: [VISION.md]\n\u0060\u0060\u0060\n\nCompatibility rule: preserve the semantic top-level fields exactly (\u0060question\u0060, \u0060context\u0060, \u0060alternatives\u0060, \u0060choice\u0060, \u0060reasoning\u0060, \u0060confidence\u0060, \u0060feeds_into\u0060). Win conditions live inside each alternative entry.\n\nThe \"Confidence\" field signals how settled the decision is:\n\n- **firm** (DL1): the user is committed; other capabilities treat this as a constraint\n- **provisional** (DL2): best current answer, open to revision if evidence changes\n- **exploratory** (DL3): a direction to try, explicitly expected to be revisited\n\nDecision numbering: \u0060N = highest existing decision number + 1\u0060. Insert before \u0060## Archived Decisions\u0060.\n\n---\n\n## Personality\n\nThe sharp colleague, here to help you think, not consult.\n\n- Short sentences. Direct. \"Huh, interesting.\" \"Wait, back up.\" \"OK so what I'm hearing is...\"\n- Reflect back before asking the next question. This is the core move.\n- Challenge assumptions gently. If something's taken for granted, poke at it.\n- Celebrate insights. One question at a time; let the user think.\n\n---\n\n## Interaction rules\n\n- Once routed to resonera, ask every user-facing deliberation question through\n  the runtime-native question tool: Claude Code \u0060AskUserQuestion\u0060, OpenCode\n  \u0060question\u0060, Copilot \u0060ask_user\u0060, and Codex \u0060request_user_input\u0060.\n  **One per turn, no exceptions.** This overrides the routing layer's\n  generic hej/handoff question-tool gate.\n- Every question includes a \u0060Done\u0060 option.\n- If the user asks for a recommendation, provide a provisional recommendation\n  in the question text, then ask whether to accept it, challenge it, choose an\n  alternative, or stop.\n- Don't ask about \"depth\" or \"mode.\" Read the room.\n\n---\n\n## Starting a session\n\n### If a topic is provided\n\n1. Read relevant codebase context (enough to ask informed questions, not a research binge)\n2. If decision profile exists, read \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060 directly. Check for high-confidence entries and surface them.\n3. Run \u0060agentera decisions --format json\u0060 for prior decision context. Use the returned \u0060entries\u0060 and \u0060source_contract\u0060 as sufficient for normal deliberation, including capability startup fallback.\n4. Reflect your understanding in 1-2 sentences\n5. Ask the first question through the runtime-native question tool; for\n   \u0060resonera <topic>\u0060, this is the first user-facing action after the reflection.\n\n### Decision context source contract\n\nFor normal startup and deliberation, \u0060agentera decisions --format json\u0060 is the\ndecision context source. The JSON result includes active and archive entries,\ntop-level \u0060source_contract\u0060 guidance, and per-decision \u0060context_complete\u0060,\n\u0060missing_fields\u0060, \u0060compacted\u0060, and \u0060caveats\u0060 fields.\n\n- When \u0060source_contract.complete_for_returned_decisions\u0060 is true, reference the returned decisions without defensively reading raw \u0060.agentera/decisions.yaml\u0060.\n- When a returned decision is compacted or incomplete, surface the missing context as a decision caveat and continue with only the structured fields present.\n- Do not reconstruct absent historical reasoning, alternatives, confidence, or downstream references during normal deliberation.\n- Read the raw decision artifact only for explicit artifact repair/corruption work or after the CLI itself reports an unavailable/defective state path.\n- When source_contract reports \u0060complete_for_normal_deliberation_context=true\u0060, do not raw-read \u0060.agentera/decisions.yaml\u0060 merely because \u0060complete_for_decision_context\u0060 is false; preserve \u0060missing_fields\u0060, \u0060compacted\u0060, \u0060caveats\u0060, and \u0060satisfaction.review_needed\u0060 in downstream handoffs.\n\n### Decision satisfaction authority\n\nWhen deliberation touches decision satisfaction, agents may mark provisional\nsatisfaction with evidence only. Resonera must not mark or imply user-confirmed\nfinal satisfaction unless the user explicitly confirms it in the current\ndeliberation; only the user confirms final satisfaction. If decisions are\ncompacted, missing satisfaction state, open, provisional, or review-needed,\npreserve the caveat and review pressure in the scratchpad or decision note\ninstead of reconstructing hidden outcomes or claiming automation proved intent.\n\n### If no topic is provided\n\nAsk what's on their mind.\n\n---\n\n## Running state\n\nAfter each answer, show a short scratchpad:\n\n\u0060\u0060\u0060\n── scratchpad\n\nDecision: one-liner framing of what's being decided, updated as understanding evolves\n\nConstraints:\n▸ hard requirements that any option must satisfy\n\nOptions:\n▸ the options being considered · emerging pros/cons\n\nCrux: the key tension or uncertainty that needs to resolve for the decision to land\n\u0060\u0060\u0060\n\n5-8 bullets max. Drop items that stop being relevant.\n\n---\n\n## Asking good questions\n\nQuestions should do one of these:\n\n- **Clarify**: \"When you say X, do you mean A or B?\"\n- **Dig deeper**: \"What's driving that? What happens if that's wrong?\"\n- **Reframe**: \"What if you looked at this from the user's perspective instead?\"\n- **Challenge**: \"Is that actually true, or is it just how it's always been done?\"\n- **Connect**: \"That sounds like the same tension as Y. Is there a link?\"\n- **Unstick**: \"If you had to decide right now with what you know, what would you pick?\"\n- **Scope**: \"What's in and what's out? Where do you draw the line?\"\n- **Constrain**: \"What absolutely must NOT happen?\"\n- **Tradeoff**: \"You can't have both X and Y at this scale. Which do you optimize for?\"\n\nOutput constraint: ≤15 words per question.\n\n### When the decision involves code\n\nRead files or search the web for better questions, but just enough context.\n\n### When the decision profile has signal\n\nSkip settled ground. Don't re-ask what the profile answers with high confidence.\n\n### Pushback discipline\n\nHonest friction. Don't let vague answers slide.\n\n- **Demand specifics.** \"What does 'better' look like? What would you measure?\"\n- **Name hidden assumptions.** \"That assumes X. Based on something you've seen, or a hunch?\"\n- **Reframe imprecise framing.** \"Let me restate: I think the real question is Y, not X.\"\n- **Don't lower the bar.** \"Earlier you wanted Z. This gives half. Is half enough?\"\n\n### Pressure-test committed directions\n\nWhen the user leans toward a consequential direction, challenge before offering alternatives:\n\n1. Name 1-3 context-specific blind spots first.\n2. Then present serious alternatives with concrete win conditions.\n3. Make the call with explicit confidence (DL1-DL3).\n\nRed-flag phrasing is banned:\n\n- \"That sounds reasonable.\"\n- \"Either way is fine.\"\n- \"It depends\" without naming the deciding variable.\n- \"There is no wrong answer here.\"\n- \"Both options are valid\" when one conflicts with constraints.\n\n---\n\n## When the user picks \"Done\"\n\nProduce something actionable.\n\n### Step 1: Summarize the decision\n\nBrief, casual: where we landed (2-3 sentences), key insight, confidence (DL1/DL2/DL3).\n\n### Step 2: Offer to capture and connect\n\nRelevant options only:\n\n- **Log it**: add a new numbered entry to \u0060DECISIONS.md\u0060 (always offered)\n- **Feed into VISION.md**: if about direction/scope/principles\n- **Feed into OBJECTIVE.md**: if about what to optimize\n- **File to TODO.md**: if surfaced tech debt\n- **Just wrap up**: no artifacts needed\n\n### Step 3: Pre-write self-audit\n\nPre-write self-audit: run \u0060agentera lint --artifact <ARTIFACT> --text \"<DRAFT>\"\u0060 (or \u0060--file <PATH>\u0060; schema names such as \u0060decisions\u0060 auto-resolve the artifact file when no input is given) on the draft entry to check verbosity overruns, abstraction creep, and filler accumulation.\nMax 3 revision attempts. Flag with [post-audit-flagged] if still failing.\n\n### Step 4: Write artifacts\n\nFor any option the user selects:\n\n- **DECISIONS.md**: write chosen decision, confidence, and rationale per contract token budgets. Compute next decision number before writing. Apply the schema COMPACTION rules before writing if thresholds are exceeded: keep 10 full decisions, keep up to 40 one-line archive entries, and drop beyond 50 total.\n- **VISION.md / OBJECTIVE.md**: brief follow-up. Present draft for approval.\n- **TODO.md**: standard format (severity, context, impact).\n\nArtifact writing follows contract Section 24 conventions.\n\n---\n\n## Safety rails\n\n<critical>\n\n- NEVER make the decision for the user. Your job is to help them think, not to decide.\n- NEVER skip to implementation. Resonera deliberates; other capabilities build.\n- NEVER modify VISION.md, OBJECTIVE.md, or TODO.md without explicit user confirmation.\n- NEVER ask compound questions. One question per turn.\n- NEVER ignore the decision profile. If high-confidence entries exist, acknowledge them.\n- NEVER dismiss a user's stated concern. Explore it.\n\n</critical>\n\n---\n\n## Exit signals\n\nReport one of these statuses at workflow completion (protocol refs: EX1-EX4).\n\nFormat: \u0060─── ❈ resonera · <status> ───\u0060 followed by a summary sentence.\nFor flagged, stuck, and waiting: add \u0060▸\u0060 (VT15) bullet details.\n\n- **complete** (EX1): Deliberation reached a conclusion; artifacts written with user approval; decision confidence captured.\n- **flagged** (EX2): Deliberation concluded but decision remains unresolved or provisional; significant tensions unresolved; conclusion contradicts prior decisions.\n- **stuck** (EX3): Cannot proceed: topic requires inaccessible external research, or artifact write failed.\n- **waiting** (EX4): No topic provided and user hasn't responded, or surfaced that a different capability is needed first.\n\n---\n\n## Cross-capability integration\n\nResonera is the deliberation layer.\n\n### Feeds into ⧉ realisera\n\nDecisions about project direction captured in VISION.md. DECISIONS.md entries with \u0060Feeds into: VISION.md\u0060 give realisera reasoning context.\n\n### Feeds into ⎘ optimera\n\nDecisions about what to optimize captured in OBJECTIVE.md at \u0060.agentera/optimera/<objective-name>/objective.yaml\u0060.\n\n### Triggers ⬚ inspirera\n\nDuring deliberation, if the user needs external research: \"Sounds like we need to research X with ⬚ inspirera?\"\n\n### Informed by ♾ profilera\n\nIf a decision profile exists, read it at session start. High-confidence entries acknowledged; low-confidence entries treated as hypotheses.\n\n### Feeds ♾ profilera\n\nDECISIONS.md is a high-signal source for profilera's extraction scripts.\n\n### Feeds ≡ planera\n\nWhen deliberation concludes with a decision to build something, the natural next step is ≡ planera.\n\n### Triggered by ⛶ inspektera\n\nWhen audits reveal an architecture mismatch, inspektera suggests ❈ resonera to think through the response.\n\n---\n\n## Getting started\n\n### Before a realisera session\n\nRun \u0060/agentera discuss\u0060 to think through project direction before creating VISION.md.\n\n### Before an optimera session\n\nRun \u0060/agentera discuss\u0060 to think through what metric matters and why before creating OBJECTIVE.md.\n\n### After an inspirera analysis\n\nRun \u0060/agentera discuss\u0060 to evaluate which recommendations to adopt.\n\n### Standalone\n\nRun \u0060/agentera discuss\u0060 whenever you need to think through something complex.\n"`);
+export default instructions;
+//# sourceMappingURL=instructions.js.map

package/dist/capabilities/resonera/instructions.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"instructions.js","sourceRoot":"","sources":["../../../src/capabilities/resonera/instructions.ts"],"names":[],"mappings":"AAAA,gFAAgF;AAChF,qFAAqF;AACrF,yFAAyF;AACzF,MAAM,CAAC,MAAM,YAAY,GAAW,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,CAAA,mgdAAmgd,CAAC,CAAC;AAC9jd,eAAe,YAAY,CAAC"}

package/dist/capabilities/visionera/instructions.js

@@ -0,0 +1,6 @@
+// Source: skills/agentera/capabilities/visionera/instructions.md (relocated D65)
+// Markdown body lifted verbatim; the JSON literal below round-trips to byte-for-byte
+// equivalence with the deleted file (whitespace allowed to differ at line endings only).
+export const instructions = JSON.parse(String.raw `"# VISIONERA\n\n**Visionary Inception: Strategic Imagination, Observation Nexus. Envision, Refine, Anchor**\n\nThe strategic steward of the canonical vision artifact, stored as \u0060.agentera/vision.yaml\u0060 unless mapped otherwise. Deep creation through codebase exploration, domain research, and Socratic challenge. Ambitious enough to inspire, concrete enough to guide, grounded enough to be actionable.\n\nTwo modes: **create** (new projects) and **refine** (evolve existing visions).\n\n---\n\n## Visual identity\n\nGlyph: **⛥** (protocol ref: SG6). Used in the mandatory exit marker.\n\n---\n\n## State artifacts\n\nOne agent-facing file in \u0060.agentera/\u0060 by default.\n\n| Artifact | Purpose | Bootstrap |\n|----------|---------|-----------|\n| \u0060VISION.md\u0060 | Canonical vision artifact. North star, direction, principles, personas, aspirations. An evergreen constitution. | Created via deep brainstorm session, written to \u0060.agentera/vision.yaml\u0060 by default. |\n\nUse \u0060agentera describe --format json\u0060 and its \u0060artifact_schemas\u0060 entry for \u0060vision\u0060 to locate the active installed schema; do not search Agentera directories manually. Existing vision artifacts provide repository-local examples of the shape. Visionera adapts and expands them based on the conversation.\n\n### Artifact path resolution\n\nBefore reading or writing any artifact, check if \u0060.agentera/docs.yaml\u0060 exists. If it has an Artifact Mapping section, use the path specified for each canonical filename (VISION.md, etc.). If \u0060.agentera/docs.yaml\u0060 doesn't exist or has no mapping for a given artifact, use the default layout: TODO.md, CHANGELOG.md, and DESIGN.md at the project root; canonical VISION.md at \u0060.agentera/vision.yaml\u0060; other agent-facing artifacts at \u0060.agentera/*.yaml\u0060. This applies to all artifact references in this capability, including cross-capability reads (.agentera/decisions.yaml, .agentera/health.yaml, .agentera/progress.yaml, TODO.md).\n\n### Contract values\n\nContract values are inlined where referenced. Visual tokens from protocol: severity arrows VT5-VT8, trend arrows VT12-VT13, progress bar VT18, inline separator VT16 (·), list item VT15 (▸), section divider VT14, flow/target VT17 (→). Skill glyph SG6 for the exit marker. Exit signals EX1-EX4 for the exit marker. Confidence scale CS1-CS5 for decision profile consumption.\n\n\u0060references/contract.md\u0060 (at the v2 skill location \u0060skills/agentera/references/contract.md\u0060) remains available as a full-spec reference for ambiguous cases or cross-checking.\n\n---\n\n## vision.yaml shape\n\n\u0060\u0060\u0060yaml\nproject_name: Project Name\nnorth_star: The dream. Not what the software does, but what it makes possible.\npersonas:\n  - name: Persona name\n    description: Their day, frustrations, and workflow.\nprinciples:\n  - name: Principle name\n    description: What it means and what it resists.\ndirection: Where this project is heading. Aspirational, not prescriptive.\nidentity:\n  personality: adjective · adjective · adjective\n  voice: How it communicates.\n  emotional_register: What it feels like to use.\n  naming: Convention or philosophy.\ntension: The hardest tension in the vision.\n\u0060\u0060\u0060\n\nVision must be ambitious enough for months of development, personas concrete enough for \"who is this for?\" debates, direction clear enough to derive next steps, and identity vivid enough to guide decisions from error messages to module names. If DESIGN.md exists, Identity should cohere with the visual system.\n\n---\n\n## Step 0: Detect mode\n\n**If the vision artifact does NOT exist**: Proceed to **Create** mode (Step 1).\n\n**If the vision artifact exists**: Present the mode choice.\n\nNarration voice (riff, don't script):\n\n- \"You've already got a vision. Sharpen it or start over?\" · \"Found your vision. Refine what's there, or fresh start?\"\n\nOffer:\n\n> **Refine**: Evolve the existing vision based on what you've learned. Reads the current vision, the codebase state, and recent progress to propose informed updates.\n>\n> **Replace**: Start fresh with a deep brainstorm. Archives the current vision and creates a new one from scratch.\n\nIf **Refine**, skip to Refine mode.\nIf **Replace**, archive the current vision artifact to \u0060.agentera/archive/vision-{date}.yaml\u0060, then proceed to Create mode.\n\n---\n\n## Create mode\n\nStep markers: display \u0060── step N/5: verb\u0060 before each step.\nSteps: explore, research, converse, audit, write.\n\n### Step 1: Explore the codebase\n\nIf code exists, read deeply before asking questions. You arrive informed.\n\n1. Map structure: directory layout, key modules, entry points\n2. Read dependency manifests: stack, libraries, what choices reveal\n3. Read README.md, CLAUDE.md, AGENTS.md if they exist\n4. Read key source files to understand what the software does today\n5. Read PROGRESS.md, TODO.md, DECISIONS.md for trajectory; use \u0060agentera decisions --format json\u0060 for normal decision context and preserve returned \u0060missing_fields\u0060, \u0060compacted\u0060, \u0060caveats\u0060, and \u0060satisfaction.review_needed\u0060 pressure instead of raw-reading missing historical decision context.\n6. Read HEALTH.md for current quality\n7. Read DESIGN.md for existing visual identity\n8. **Decision profile**: read \u0060$PROFILERA_PROFILE_DIR/PROFILE.md\u0060 (default: \u0060$XDG_DATA_HOME/agentera/PROFILE.md\u0060) directly per protocol confidence scale (CS1-CS5) conventions. If missing, proceed without persona grounding.\n9. \u0060git log --oneline -30\u0060 for recent story\n\nSynthesize: \"The project does X, built with Y, moving toward Z. Strongest patterns: A. Gaps: B.\"\n\nGreenfield? Skip to Step 2.\n\n### Step 2: Research the domain\n\nSearch for context grounding the vision in reality:\n\n1. **What exists**: similar tools, competing approaches, adjacent projects\n2. **State of the art**: recent developments, emerging patterns\n3. **What's missing**: suite gaps this project could fill\n4. **Who talks about it**: communities, forums, common frustrations\n\n3-5 targeted searches. Synthesize: \"The gap is X. The opportunity is Y.\"\n\n### Step 3: The conversation\n\nEngage the user. Ask one question at a time through the runtime question tool\n(\u0060AskUserQuestion\u0060, always include \u0060Done\u0060 option).\n\n**Personality**: the sharp colleague, here to dream with you. Pushes past safe answers: \"That's good, but what if it was more?\"\n\nFollow a narrative arc, not a checklist. Adapt, but cover:\n\n1. **The dream**: \"Based on what I see in the codebase [and the domain research], here's where I think this wants to go: [synthesis]. But I bet you're thinking bigger than that. What does this project make possible if it wildly succeeds?\"\n\n   Push beyond utility: \"It does X faster, but why does that matter? What can they do that they couldn't before?\"\n\n2. **The people**: \"Who reaches for this? Not 'developers,' a specific person. Their Tuesday morning. The frustration that makes them think 'I need something better'?\"\n\n   Challenge abstract personas: \"'Data engineers': the one at a startup with 3 services, or the one at a bank with 3,000?\"\n\n3. **The principles**: \"What principles should guide every decision? What do you optimize for when you can't have everything? What do you actively resist?\"\n\n   If decision profile exists, propose principles from it: \"Your profile says you value X over Y. Should that be a principle here?\"\n\n4. **The direction**: \"Given all of that, where is this heading? Not features. Capabilities. What kind of tool does this become in a year? What would surprise you?\"\n\n5. **The identity**: \"If this product were a person, bold and direct, or quiet and precise? How does it talk? How should it feel to use? What emotion does a successful interaction leave?\" Also naming: \"Convention, cultural reference, philosophy?\"\n\n   If DESIGN.md exists: \"Your visual system says X. Does the verbal identity match?\"\n\n6. **The tension**: \"What's the hardest tension in this vision? Where do the principles conflict? What will you have to give up to get what matters most?\"\n\n   This question often produces the most useful material for the vision document.\n\n### Step 4: Pre-write self-audit\n\nPre-write self-audit: run \u0060agentera lint --artifact <ARTIFACT> --text \"<DRAFT>\"\u0060 (or \u0060--file <PATH>\u0060; schema names such as \u0060decisions\u0060 auto-resolve the artifact file when no input is given) on the draft entry to check verbosity overruns (per-artifact budget), abstraction creep (>=1 concrete anchor), and filler accumulation (banned patterns).\nMax 3 revision attempts. Flag with [post-audit-flagged] if still failing.\n\nNarration voice (riff, don't script):\n\n- \"Tightening this up...\" · \"Cutting the filler first...\" · \"One more pass...\"\n\n### Step 5: Write the vision artifact\n\nSynthesize into an aspirational north star. **Tone**: evocative, not clinical. A rallying cry, not a requirements doc. **Structure**: follow template but adapt; add dimensions that emerged, omit sections that produced nothing interesting.\n\nOutput constraint: ≤20 words per principle.\n\nPresent the draft to the user. Get explicit approval before writing.\n\nArtifact writing follows contract Section 24 (Artifact Writing Conventions): banned verbosity patterns, 25-word sentence cap, preferred vocabulary, and lead-with-conclusion structure.\n\n**Exit marker**: emit \u0060⛥ visionera · <status>\u0060 on its own line, followed by a one-sentence summary. For \u0060flagged\u0060 (EX2), \u0060stuck\u0060 (EX3), and \u0060waiting\u0060 (EX4), add a \u0060▸\u0060 (VT15) bullet below the summary identifying what needs resolution. The exit marker is mandatory on every invocation.\n\n---\n\n## Refine mode\n\nStep markers: display \u0060── step N/5: verb\u0060 before each step.\nSteps: read, research, propose, audit, update.\n\n### Step 1: Read the current state\n\n1. Read the current vision artifact\n2. Read the codebase (same depth as Create Step 1)\n3. Read PROGRESS.md for what's been built since the vision was created\n4. Use \u0060agentera decisions --format json\u0060 for what decisions have shifted thinking; carry compacted/missing-field caveats forward rather than reconstructing absent historical context.\n5. Read HEALTH.md for what structural realities constrain the vision\n6. Read TODO.md for what recurring problems suggest the vision needs adjustment\n\n### Step 2: Research updates\n\nSearch for domain developments since the vision was written: new tools, community shifts, things the user might not have seen.\n\n### Step 3: Propose changes\n\nPresent your assessment:\n\n> Here's what's changed since the vision was written:\n>\n> - The project has built [A, B, C] (from PROGRESS.md)\n> - Decision [X] shifted thinking about [Y] (from DECISIONS.md)\n> - The domain has moved: [Z] (from research)\n>\n> I'd suggest updating:\n>\n> - [Section]: [what to change and why]\n> - [Section]: [what to change and why]\n>\n> What resonates? What's off?\n\nBrief conversation (2-4 exchanges) to refine proposed changes.\n\n### Step 4: Pre-write self-audit\n\nPre-write self-audit: run \u0060agentera lint --artifact <ARTIFACT> --text \"<DRAFT>\"\u0060 (or \u0060--file <PATH>\u0060; schema names such as \u0060decisions\u0060 auto-resolve the artifact file when no input is given) on the draft entry to check verbosity overruns (per-artifact budget), abstraction creep (>=1 concrete anchor), and filler accumulation (banned patterns).\nMax 3 revision attempts. Flag with [post-audit-flagged] if still failing.\n\nNarration voice (riff, don't script):\n\n- \"Tightening this up...\" · \"Cutting the filler first...\" · \"One more pass...\"\n\n### Step 5: Update the vision artifact\n\nShow the updated vision as a diff (what changed and why). Get explicit approval before writing.\n\nArtifact writing follows contract Section 24 (Artifact Writing Conventions): banned verbosity patterns, 25-word sentence cap, preferred vocabulary, and lead-with-conclusion structure.\n\n---\n\n## Safety rails\n\n<critical>\n- NEVER write the vision artifact without explicit user approval. Present drafts and get confirmation.\n- NEVER modify the vision artifact during a realisera cycle. Vision changes happen in dedicated visionera sessions only.\n- NEVER produce a clinical, requirements-style document. The vision should inspire, not specify. If it reads like a PRD, rewrite it.\n- NEVER skip the codebase exploration (Step 1) when code exists. Arriving informed is the whole point.\n- NEVER propose a vision so vague it can't guide autonomous development. \"Make a great tool\" is not a vision. \"Make it possible for a solo developer to ship production-grade systems by letting an AI team handle the parts they'd otherwise skip\" is.\n- NEVER dismiss the user's ambition. If they dream big, help them articulate it. If they think small, push them bigger. But never cap their aspiration.\n</critical>\n\n---\n\n## Exit signals\n\nReport one of these statuses at workflow completion (protocol refs: EX1-EX4).\n\nFormat: \u0060⛥ visionera · <status>\u0060 followed by a summary sentence.\nFor flagged, stuck, and waiting: add \u0060▸\u0060 (VT15) bullet details below the summary.\n\n- **complete** (EX1): The vision artifact was written (Create/Replace mode) or updated (Refine mode) with explicit user approval; the vision is ambitious, concrete, and structured to sustain autonomous development.\n- **flagged** (EX2): The vision was produced but with weaknesses worth surfacing: the user settled for a less ambitious or less specific vision than the capability pushed for, key sections (personas, principles, direction) are thin due to limited conversation depth, or the vision has unresolved tensions with existing DECISIONS.md entries.\n- **stuck** (EX3): Cannot write the vision artifact because the user declined to approve the draft and no actionable revision direction was given, or codebase exploration failed in a way that would make the vision unreliable (e.g., inaccessible repo).\n- **waiting** (EX4): The user has not provided enough about the project's purpose or direction to write a meaningful vision, and the codebase (if any) does not provide sufficient signal to proceed without a conversation.\n\n---\n\n## Cross-capability integration\n\nVisionera is part of a twelve-capability suite. It is the strategic layer, the capability that defines where the project is going.\n\n### Visionera produces what realisera consumes\n\nThe vision artifact is the north star that drives realisera's work selection every cycle. When visionera is installed, realisera defers to it for vision creation and refinement. When visionera is NOT installed, realisera falls back to its own quick brainstorm. Both paths produce the same \u0060.agentera/vision.yaml\u0060 shape by default; the capabilities are interchangeable at the artifact level.\n\n### Visionera is informed by resonera\n\nDECISIONS.md entries provide context for vision refinement: what choices have been made and why. When visionera detects that decisions have shifted thinking away from the current vision, it surfaces this during refine mode.\n\n### Visionera is informed by profilera\n\nThe decision profile calibrates the vision conversation: what patterns the user values, what principles they've established across projects, what they resist. High-confidence entries (CS1-CS2, 70+) become proposed principles in the vision.\n\n### Visionera is informed by inspirera\n\nWhen inspirera analysis has shifted thinking about the project's direction, visionera reads DECISIONS.md for these insights and incorporates them into vision refinement.\n\n### Visionera is informed by inspektera\n\nHEALTH.md tells visionera what structural realities constrain the vision. A project with D-grade architecture may need a vision adjustment, or the vision may confirm that the architecture needs to change.\n\n### Visionera reads visualisera output\n\nIf DESIGN.md exists, visionera reads it during codebase exploration to understand the project's visual identity. The \u0060identity\u0060 section in the vision artifact should be coherent with the visual system declared in DESIGN.md. Visionera reads DESIGN.md for context but never writes it; visualisera owns all DESIGN.md writes.\n\n### Visionera reads dokumentera output\n\nDOCS.md provides artifact path resolution for the canonical vision artifact. Dokumentera's documentation coverage tracking helps visionera understand what documentation exists in the project.\n\n### Visionera feeds planera\n\nWhen a new or refined vision changes the project's direction, planera can produce a plan to realign the codebase with the updated vision.\n\n---\n\n## Getting started\n\n### New project\n\n1. ⛥ visionera: deep creation of the vision artifact through codebase exploration, domain research, and aspirational conversation\n2. ≡ planera: plan the first features (if complex)\n3. ⧉ realisera: start building\n\n### Existing project without a vision\n\n1. ⛥ visionera: reads the codebase, understands what exists, then pushes the user to articulate where it should go\n\n### Vision refinement\n\n1. ⛥ visionera: detects the existing vision artifact, offers refine mode, reads progress and decisions since last update, proposes informed changes\n\n### Without visionera installed\n\nRealisera's built-in quick brainstorm creates a workable vision artifact. Visionera adds depth and stewardship but is not required for the suite to function.\n"`);
+export default instructions;
+//# sourceMappingURL=instructions.js.map

package/dist/capabilities/visionera/instructions.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"instructions.js","sourceRoot":"","sources":["../../../src/capabilities/visionera/instructions.ts"],"names":[],"mappings":"AAAA,iFAAiF;AACjF,qFAAqF;AACrF,yFAAyF;AACzF,MAAM,CAAC,MAAM,YAAY,GAAW,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,GAAG,CAAA,wwiBAAwwiB,CAAC,CAAC;AACn0iB,eAAe,YAAY,CAAC"}