maestro-flow 0.5.46 → 0.5.47

package/.claude/commands/manage-status.md

@@ -24,12 +24,34 @@ $ARGUMENTS (no arguments required)
 - `.workflow/roadmap.md` -- milestone and phase structure
 - `.workflow/scratch/*/plan.json` -- plan metadata (via artifact registry paths)
 - `.workflow/scratch/*/.task/TASK-*.json` -- individual task statuses
+
+**Output boundary**: Read-only command. MUST NOT write any files. All output is displayed to the user via text.
 </context>
 
+<invariants>
+1. **Read-only** — MUST NOT write or modify any files; this is a pure display command
+2. **Graceful degradation** — missing roadmap.md, plan.json, or task files MUST NOT cause failure; display available data and note missing sections
+3. **State accuracy** — progress percentages MUST be calculated from actual task statuses, NEVER estimated or inferred
+4. **Wiki health optional** — wiki health score display MUST degrade gracefully if wiki is unavailable
+5. **Complete dashboard** — MUST include: milestone progress, phase status, task counts, active work, and next-step suggestions
+</invariants>
+
 <execution>
 Follow '~/.maestro/workflows/status.md' completely.
 
 Next-step decision table defined in workflow status.md Step 5.
+
+### Phase Gates (MANDATORY, BLOCKING)
+
+**GATE 1: Load → Render** (State loading → Dashboard display)
+- REQUIRED: `.workflow/` exists and `state.json` is readable (E001/E002 if not).
+- REQUIRED: Project state loaded with milestone and artifact registry.
+- BLOCKED if state.json missing or corrupt (E002).
+
+**GATE 2: Render → Route** (Dashboard → Next-step suggestions)
+- REQUIRED: Per-phase progress calculated from actual task statuses.
+- REQUIRED: Dashboard rendered with progress bars and status table.
+- BLOCKED if state parsing fails entirely.
 </execution>
 
 <error_codes>

package/.claude/commands/manage-wiki.md

@@ -43,13 +43,41 @@ $ARGUMENTS — subcommand and optional flags.
 - `--format brief|full` — (digest) Output format
 - `--recent N` — (digest) Scope to N most recent entries
 - `--create-issues` — (digest) Create issues for identified knowledge gaps
+
+**Output boundary**: File writes MUST target `.workflow/wiki/`, `.workflow/knowhow/`, or `.workflow/issues/issues.jsonl` (when `--create-issues`) only. NEVER modify source code or files outside these paths. `--dry-run` overrides `--fix` — no writes when both are set.
 </context>
 
+<invariants>
+1. **Dry-run precedence** — `--dry-run` MUST override `--fix` when both are passed; preview only, no writes
+2. **Read-only by default** — without `--fix` or `--create-issues`, all subcommands MUST be read-only
+3. **Confirmation on fixes** — `--fix` MUST show preview of changes before applying; auto-apply only when explicitly set
+4. **Graph integrity** — `connect` MUST NOT create circular link chains; validate graph acyclicity for parent-child relationships
+5. **Threshold enforcement** — `--min-similarity` MUST be respected; NEVER suggest connections below the threshold
+6. **Subcommand isolation** — each subcommand routes to its own workflow file; NEVER cross-execute subcommand logic
+</invariants>
+
 <execution>
 **Subcommand routing:**
 - `health|search|cleanup|stats` → Follow `~/.maestro/workflows/wiki-manage.md` completely.
 - `connect` → Follow `~/.maestro/workflows/wiki-connect.md` completely (Stages 1-6).
 - `digest` → Follow `~/.maestro/workflows/wiki-digest.md` completely (Stages 1-8).
+
+### Phase Gates (MANDATORY, BLOCKING)
+
+**GATE 1: Parse → Load** (Subcommand routing → Wiki data loading)
+- REQUIRED: Subcommand parsed and validated (health/search/cleanup/stats/connect/digest).
+- REQUIRED: `.workflow/` initialized (E001 if missing).
+- BLOCKED if E003 (invalid subcommand) or E001.
+
+**GATE 2: Load → Execute** (Wiki data → Subcommand execution)
+- REQUIRED: Wiki data loaded via `maestro wiki` CLI.
+- REQUIRED: At least one wiki entry exists (E002 if none).
+- BLOCKED if wiki data loading fails entirely.
+
+**GATE 3: Execute → Write** (For mutating operations: cleanup --fix, connect --fix, digest --create-issues)
+- REQUIRED: Preview of changes shown to user.
+- REQUIRED: `--dry-run` NOT set (overrides `--fix`).
+- BLOCKED if preview generation fails or user declines.
 </execution>
 
 <error_codes>

package/.claude/commands/odyssey-improve.md

@@ -50,6 +50,8 @@ $ARGUMENTS
 **Session**: `.workflow/scratch/{YYYYMMDD}-improve-odyssey-{slug}/`
 **Output**: `session.json` | `evidence.ndjson` | `understanding.md`
 
+**Output boundary**: ALL file writes MUST target the session directory (`.workflow/scratch/{YYYYMMDD}-improve-odyssey-{slug}/`) or `.workflow/state.json` only. Source code modifications during S_FIX are in-scope but MUST be committed per action. NEVER write artifacts outside these paths.
+
 **session.json — improve-specific fields:**
 ```json
 { "target": "", "dimensions": [], "baseline_metrics": {},
@@ -103,6 +105,54 @@ All invariants (evidence append-only, session-as-state, phase goal tracking, aut
 Applies to: **S_SURVEY, S_AUDIT, S_DIAGNOSE, S_GENERALIZE**. Logic in base.
 </self_iteration>
 
+<execution>
+Follow base execution discipline completely. Actions defined in state_machine below.
+
+### Phase Gates (MANDATORY, BLOCKING)
+
+**GATE 1: INTAKE → SURVEY**
+- REQUIRED: Target resolved, SESSION_DIR created, session.json initialized with baseline_metrics.
+- REQUIRED: phase_goals[] derived from flags.
+- BLOCKED if: no target specified (E001) or target path not found (E002).
+
+**GATE 2: SURVEY → AUDIT**
+- REQUIRED: Current state survey completed — dependency audit, complexity scan, test coverage map, error handling scan.
+- REQUIRED: Evidence phase=survey logged, understanding.md §2 updated, G1 marked done.
+- BLOCKED if: survey incomplete — all 4 scan types must be attempted.
+
+**GATE 3: AUDIT → DIAGNOSE**
+- REQUIRED: All dimension agents completed (or --dimensions subset), findings merged with severity classification.
+- REQUIRED: audit_result written to session.json, understanding.md §3 with severity matrix, G2 marked done.
+- BLOCKED if: zero dimensions reviewed (W002 partial is allowed, zero is not).
+
+**GATE 4: DIAGNOSE → FIX**
+- REQUIRED: Root causes identified for all critical/high findings with evidence.
+- REQUIRED: diagnoses[] written, understanding.md §4 updated, G3 marked done.
+- BLOCKED if: hypotheses failed 3 times without escalation decision (A_ESCALATE_DIAGNOSIS).
+
+**GATE 5: FIX → VERIFY**
+- REQUIRED: ALL findings within fix_threshold fixed by severity tier (critical → high → medium → low).
+- REQUIRED: Per-fix evidence phase=fix logged.
+- BLOCKED if: tier incomplete — each tier must be fully addressed before advancing.
+
+**GATE 6: VERIFY → GENERALIZE**
+- REQUIRED: Tests pass, metrics re-captured, before/after comparison logged.
+- REQUIRED: confirmation written, understanding.md §5 updated, G4 marked done.
+- BLOCKED if: needs_rework → route back to S_FIX.
+
+**GATE 7: GENERALIZE → DISCOVER**
+- REQUIRED: ALL 3 layers (syntax/semantic/structural) attempted with evidence logged.
+- REQUIRED: generalization_stats written with by_layer entries for all 3 layers, G5 marked done.
+- BLOCKED if: any layer not attempted (thoroughness floor violation).
+
+**GATE 8: DISCOVER → RECORD**
+- REQUIRED: All hits triaged with per-item classification and reason.
+- REQUIRED: remaining_actionable == 0 OR loops >= max_loops with per-item reasons logged.
+- REQUIRED: G6 marked done.
+- BLOCKED if: unclassified hits remain.
+
+</execution>
+
 <state_machine>
 
 <states>

package/.claude/commands/odyssey-planex.md

@@ -55,6 +55,8 @@ $ARGUMENTS
 **Session**: `.workflow/scratch/{YYYYMMDD}-planex-odyssey-{slug}/`
 **Output**: `session.json` | `evidence.ndjson` | `understanding.md`
 
+**Output boundary**: ALL session artifacts MUST target the session directory (`.workflow/scratch/{YYYYMMDD}-planex-odyssey-{slug}/`) or `.workflow/state.json` only. Source code modifications during S_EXECUTE and S_FIX are in-scope but MUST be committed per action. NEVER write session artifacts outside these paths.
+
 **session.json — planex-specific fields:**
 ```json
 { "requirement": "",
@@ -106,6 +108,50 @@ Base execution_discipline #1-5.
 Applies to: **S_PLAN, S_VERIFY, S_GENERALIZE**. Logic in base.
 </self_iteration>
 
+<execution>
+Follow base execution discipline completely. Actions defined in state_machine below.
+
+### Phase Gates (MANDATORY, BLOCKING)
+
+**GATE 1: INTAKE → PLAN**
+- REQUIRED: Requirement parsed, >=1 acceptance criterion defined with verify_method assigned.
+- REQUIRED: session.json initialized, understanding.md §1 written, G1 marked done.
+- BLOCKED if: no requirement provided (E001) or zero criteria derived (W001).
+
+**GATE 2: PLAN → EXECUTE**
+- REQUIRED: Plan tasks decomposed with criteria_refs mapping each task to acceptance criteria.
+- REQUIRED: session.json.plan populated, understanding.md §2 updated, G2 marked done.
+- BLOCKED if: plan has zero tasks or unmapped criteria.
+
+**GATE 3: EXECUTE → VERIFY**
+- REQUIRED: All plan tasks executed (or marked blocked after 3 retries per deviation rule).
+- REQUIRED: execution_config confirmed, per-task evidence logged, understanding.md §3 updated, G3 marked done.
+- BLOCKED if: tasks still pending execution.
+
+**GATE 4: VERIFY → FIX / GENERALIZE**
+- REQUIRED: Every acceptance criterion verified by its assigned method (test/grep/cli-review/manual).
+- REQUIRED: Per-criterion evidence logged with pass/fail status and iteration count.
+- BLOCKED if: verification incomplete — all criteria must be checked before routing decision.
+- Route: all passed → GENERALIZE (or RECORD if skip_generalize). Some failed + iteration < max → FIX.
+
+**GATE 5: FIX → VERIFY**
+- REQUIRED: current_iteration incremented, targeted fixes applied for each failed criterion.
+- REQUIRED: Fix evidence logged, understanding.md §5 updated.
+- BLOCKED if: no fix attempted for failing criteria.
+
+**GATE 6: GENERALIZE → DISCOVER**
+- REQUIRED: ALL 3 layers (syntax/semantic/structural) attempted with evidence logged.
+- REQUIRED: generalization_stats written with by_layer entries for all 3 layers, G5 marked done.
+- BLOCKED if: any layer not attempted (thoroughness floor violation).
+
+**GATE 7: DISCOVER → RECORD**
+- REQUIRED: All hits triaged with per-item classification and reason.
+- REQUIRED: remaining_actionable == 0 OR loops >= max_loops with per-item reasons logged.
+- REQUIRED: G6 marked done.
+- BLOCKED if: unclassified hits remain.
+
+</execution>
+
 <state_machine>
 
 <states>

package/.claude/commands/odyssey-review-test-fix.md

@@ -43,6 +43,8 @@ $ARGUMENTS
 **Session**: `.workflow/scratch/{YYYYMMDD}-review-odyssey-{slug}/`
 **Output**: `session.json` | `evidence.ndjson` | `explore.json` | `understanding.md`
 
+**Output boundary**: ALL session artifacts MUST target the session directory (`.workflow/scratch/{YYYYMMDD}-review-odyssey-{slug}/`) or `.workflow/state.json` only. Source code modifications during S_FIX are in-scope but MUST be committed per action. NEVER write session artifacts outside these paths.
+
 **session.json — review-specific fields:**
 ```json
 { "target": "", "dimensions": [], "review_result": {"remaining_actionable": 0},
@@ -88,6 +90,54 @@ All invariants defined in base.
 Applies to: **S_ARCHAEOLOGY, S_EXPLORE, S_REVIEW, S_FIX, S_GENERALIZE**. Logic in base.
 </self_iteration>
 
+<execution>
+Follow base execution discipline completely. Actions defined in state_machine below.
+
+### Phase Gates (MANDATORY, BLOCKING)
+
+**GATE 1: INTAKE → ARCHAEOLOGY**
+- REQUIRED: Target resolved to file list, SESSION_DIR created, session.json initialized.
+- REQUIRED: phase_goals[] derived from flags, understanding.md §1 written.
+- BLOCKED if: no target specified (E001) or target path not found (E002).
+
+**GATE 2: ARCHAEOLOGY → EXPLORE**
+- REQUIRED: Git history analysis completed (timeline + blame agents), evidence phase=archaeology logged.
+- REQUIRED: understanding.md §2 updated.
+- BLOCKED if: both archaeology agents failed AND delegate failed (partial results via W003 are acceptable).
+
+**GATE 3: EXPLORE → REVIEW**
+- REQUIRED: explore.json written with call_chains/recent_changes/error_gaps/similar_patterns (or W006 skip logged).
+- REQUIRED: Evidence phase=explore logged, understanding.md §3 updated, G2 marked done.
+- BLOCKED if: exploration started but not completed (W006 skip is acceptable, incomplete is not).
+
+**GATE 4: REVIEW → FIX**
+- REQUIRED: All dimension agents completed, findings merged with severity classification.
+- REQUIRED: review_result written to session.json, understanding.md §4 with severity matrix, G1 marked done.
+- BLOCKED if: zero dimensions reviewed (W002 partial is allowed, zero is not).
+
+**GATE 5: FIX → CONFIRM**
+- REQUIRED: Current severity tier fully addressed — all findings in tier fixed or individually classified.
+- REQUIRED: Per-fix evidence phase=fix logged, auto-commit per tier.
+- BLOCKED if: tier incomplete — no partial tier advancement.
+
+**GATE 6: CONFIRM → GENERALIZE**
+- REQUIRED: Tests pass, remaining_actionable == 0, new findings == 0.
+- REQUIRED: confirmation written, understanding.md §5 updated, G3 marked done.
+- BLOCKED if: needs_rework → route back to S_FIX.
+
+**GATE 7: GENERALIZE → DISCOVER**
+- REQUIRED: ALL 3 layers (syntax/semantic/structural) attempted with evidence logged.
+- REQUIRED: generalization_stats written with by_layer entries for all 3 layers, G4 marked done.
+- BLOCKED if: any layer not attempted (thoroughness floor violation).
+
+**GATE 8: DISCOVER → RECORD**
+- REQUIRED: All hits triaged with per-item classification and reason.
+- REQUIRED: remaining_actionable == 0 OR loops >= max_loops with per-item reasons logged.
+- REQUIRED: G5 marked done.
+- BLOCKED if: unclassified hits remain.
+
+</execution>
+
 <state_machine>
 
 <states>

package/.claude/commands/odyssey-ui.md

@@ -39,6 +39,8 @@ $ARGUMENTS
 **Session**: `.workflow/scratch/{YYYYMMDD}-ui-odyssey-{slug}/`
 **Output**: `session.json` | `evidence.ndjson` | `understanding.md`
 
+**Output boundary**: ALL session artifacts MUST target the session directory (`.workflow/scratch/{YYYYMMDD}-ui-odyssey-{slug}/`) or `.workflow/state.json` only. Source code modifications during S_FIX are in-scope but MUST be committed per action. NEVER write session artifacts outside these paths.
+
 **session.json — ui-specific fields:**
 ```json
 { "target": "", "dimensions": [],
@@ -87,6 +89,54 @@ $ARGUMENTS
 Applies to: **S_SURVEY, S_AUDIT, S_DIVERGE, S_GENERALIZE**. Logic in base.
 </self_iteration>
 
+<execution>
+Follow base execution discipline completely. Actions defined in state_machine below.
+
+### Phase Gates (MANDATORY, BLOCKING)
+
+**GATE 1: INTAKE → SURVEY**
+- REQUIRED: Target resolved, SESSION_DIR created, session.json initialized.
+- REQUIRED: phase_goals[] derived from flags, understanding.md §1 written.
+- BLOCKED if: no target specified (E001) or target path not found (E002).
+
+**GATE 2: SURVEY → AUDIT**
+- REQUIRED: Design system inventory + current state analysis completed.
+- REQUIRED: Evidence phase=survey logged, understanding.md §2 updated, G1 marked done.
+- BLOCKED if: survey incomplete — token scan and styling analysis must both be attempted.
+
+**GATE 3: AUDIT → DIVERGE**
+- REQUIRED: All 6 dimension agents completed (or --dimensions subset), findings merged with severity classification.
+- REQUIRED: audit_result written to session.json, understanding.md §3 with severity matrix, G2 marked done.
+- BLOCKED if: zero dimensions reviewed (W002 partial is allowed, zero is not).
+
+**GATE 4: DIVERGE → FIX**
+- REQUIRED: Both parallel agents (Polish + Delight) completed, ideas consolidated with audit findings.
+- REQUIRED: diverge_result written, understanding.md §4 updated, G3 marked done.
+- BLOCKED if: divergent exploration not attempted.
+
+**GATE 5: FIX → VERIFY**
+- REQUIRED: ALL findings/ideas within fix_threshold fixed by priority tier.
+- REQUIRED: Per-fix evidence phase=fix logged.
+- BLOCKED if: tier incomplete — each tier must be fully addressed before advancing.
+
+**GATE 6: VERIFY → GENERALIZE**
+- REQUIRED: Tests pass (lint, unit, visual regression), delegate verification completed.
+- REQUIRED: confirmation written, understanding.md §5 updated, G4 marked done.
+- BLOCKED if: needs_rework → route back to S_FIX.
+
+**GATE 7: GENERALIZE → DISCOVER**
+- REQUIRED: ALL 3 layers (syntax/semantic/structural) attempted with evidence logged.
+- REQUIRED: generalization_stats written with by_layer entries for all 3 layers, G5 marked done.
+- BLOCKED if: any layer not attempted (thoroughness floor violation).
+
+**GATE 8: DISCOVER → RECORD**
+- REQUIRED: All hits triaged with per-item classification and reason.
+- REQUIRED: remaining_actionable == 0 OR loops >= max_loops with per-item reasons logged.
+- REQUIRED: G6 marked done.
+- BLOCKED if: unclassified hits remain.
+
+</execution>
+
 <state_machine>
 
 <states>

package/.claude/commands/quality-auto-test.md

@@ -52,8 +52,20 @@ Flags, artifact context resolution, and output formats defined in workflow auto-
    - Browse: `maestro search --category test`
    - Load task-relevant entries: `maestro load --type knowhow --id <id1> [id2...]`
 4. All are optional — proceed without if unavailable.
+
+**Output boundary**: ALL file writes MUST target `.workflow/scratch/{YYYYMMDD}-auto-test-P{N}-{slug}/` or `.workflow/state.json` only. Source code modifications are limited to test files generated by this command. NEVER modify existing production source code.
 </context>
 
+<invariants>
+1. **Test code isolation** — generated tests MUST be written to test directories following existing project conventions. NEVER modify production source code to make tests pass.
+2. **RED-GREEN integrity** — tests MUST be written to fail first (RED), then verified to pass against implementation (GREEN). NEVER write tests that pass trivially or assert nothing.
+3. **Layer ordering is strict** — L0→L3 execution is sequential and fail-fast. NEVER skip a layer or run L2 before L1 passes.
+4. **Existing tests are sacred** — NEVER modify, delete, or overwrite existing test files. New tests are additive only.
+5. **Convergence requires evidence** — pass rate and confidence score MUST be computed from actual execution results. NEVER infer or estimate pass rates without running tests.
+6. **Iteration has bounds** — outer iteration MUST NOT exceed `--max-iter` (default 5). Inner test_defect fix MUST NOT exceed 3 attempts per scenario before escalating.
+7. **Traceability is mandatory for spec source** — when route=spec, every test scenario MUST trace back to a REQ-*.md requirement. Untraceable tests are flagged.
+</invariants>
+
 <execution>
 Follow '~/.maestro/workflows/auto-test.md' completely.
 

package/.claude/commands/quality-debug.md

@@ -48,8 +48,19 @@ Each artifact's type determines its outputs at `.workflow/{a.path}/`:
 - Role knowledge: `maestro search --category debug` → select relevant → `maestro load --type knowhow --id`
 
 **Output**: `DEBUG_DIR = .workflow/scratch/{YYYYMMDD}-debug-P{N}-{slug}/` (P{N} = phase number when phase-scoped; omit for standalone). Output directory rules defined in workflow debug.md Step 4.
+
+**Output boundary**: ALL file writes MUST target `DEBUG_DIR` or `.workflow/state.json` only. NEVER modify source code, test files, or other artifacts outside these paths during investigation.
 </context>
 
+<invariants>
+1. **Investigation is read-only on source** — debug MUST NOT modify source code, test files, or execution artifacts. Diagnosis produces understanding.md, evidence.ndjson, and reports only.
+2. **Root cause requires reproduction** — NEVER declare a root cause confirmed without evidence (code trace, log entry, or reproduction steps). Hypothesis without evidence stays "suspected".
+3. **Evidence is append-only** — evidence.ndjson entries MUST only be appended, NEVER modified or deleted. Each entry is an immutable observation.
+4. **Confidence is multi-factor** — root cause confidence MUST use the multi-factor scoring model (Step 7.0). NEVER use bare high/medium/low without dimensional breakdown.
+5. **Prior investigations are consulted** — when related debug artifacts exist, check understanding.md for prior root causes. NEVER re-investigate an already-confirmed root cause without new symptoms.
+6. **Fix direction is not fix execution** — debug produces `fix_direction` and `affected_files` but NEVER applies fixes. Fix execution belongs to plan→execute cycle.
+</invariants>
+
 <execution>
 Follow '~/.maestro/workflows/debug.md' completely.
 

package/.claude/commands/quality-refactor.md

@@ -36,8 +36,19 @@ If not provided, prompt user for scope.
    - Browse: `maestro search --category coding`
    - Identify task-relevant entries, then load: `maestro load --type knowhow --id <id1> [id2...]`
 4. All are optional — proceed without if unavailable.
+
+**Output boundary**: Refactoring modifies source files within the declared scope only. Ancillary outputs (reflection-log.md) MUST target `.workflow/scratch/{YYYYMMDD}-refactor-{slug}/`. NEVER modify files outside the confirmed scope without re-confirmation.
 </context>
 
+<invariants>
+1. **Plan before change** — NEVER apply refactoring changes without a confirmed plan. Every modification traces to a plan item.
+2. **Behavioral equivalence** — refactoring MUST preserve existing behavior. All tests MUST pass after each individual change, not just at the end.
+3. **Scope is locked after confirmation** — once the user confirms the refactoring plan, do NOT expand scope to include additional files or changes without re-confirmation.
+4. **Incremental verification** — each discrete refactoring step MUST be verified (tests run) before proceeding to the next. NEVER batch multiple unrelated changes into a single verification.
+5. **No feature creep** — refactoring MUST NOT add new functionality, change APIs, or alter public interfaces. If a beneficial API change is discovered, log it as a recommendation, do NOT apply it.
+6. **Rollback safety** — if any test fails after a refactoring step, revert that specific change before attempting alternatives. NEVER proceed with failing tests.
+</invariants>
+
 <execution>
 Follow '~/.maestro/workflows/refactor.md' completely.
 

package/.claude/commands/quality-retrospective.md

@@ -38,8 +38,19 @@ Arguments: $ARGUMENTS
 - `--lens <name>` — Restrict to specific lens (technical|process|quality|decision); default: all four
 
 Modes (scan/single/range/all) and storage paths defined in workflow retrospective.md Argument Shape and Stages 1-7.
+
+**Output boundary**: ALL file writes MUST target the phase's retrospective directory (`.workflow/scratch/{YYYYMMDD}-retrospective-P{N}/`), `.workflow/state.json`, `.workflow/issues.jsonl`, or `.workflow/specs/` (append-only). NEVER modify source code, verification.json, review.json, plan.json, or other existing artifacts.
 </context>
 
+<invariants>
+1. **Source artifacts are read-only** — NEVER modify verification.json, review.json, plan.json, or any execution artifact. Retrospective reads these for analysis only.
+2. **Stable insight IDs** — `INS-{8hex}` MUST be deterministic from `hash(phase_num + lens + title)`. Re-runs MUST NOT create duplicate insights.
+3. **Routing requires confirmation** — unless `-y` flag is set, every external write (issues.jsonl, spec entry, knowhow capture) MUST be confirmed by user before execution.
+4. **Lens independence** — each lens agent (technical/process/quality/decision) operates independently. One lens's findings MUST NOT suppress or override another's.
+5. **Append-only for specs** — learnings.md entries are appended as `<spec-entry>` blocks. NEVER overwrite or restructure existing entries.
+6. **Archive before overwrite** — if retrospective.json already exists for a phase, the existing file MUST be archived before writing a new version.
+</invariants>
+
 <execution>
 Follow `~/.maestro/workflows/retrospective.md` Stages 1–8 in order.
 

package/.claude/commands/quality-review.md

@@ -54,8 +54,19 @@ Each artifact's type determines its outputs at `.workflow/{a.path}/`:
 - Role knowledge: `maestro search --category review` → select relevant → `maestro load --type knowhow --id`
 
 **Output**: `REVIEW_DIR = .workflow/scratch/{YYYYMMDD}-review-P{N}-{slug}/` (P{N} = phase number, enables directory-level identification as state.json fallback)
+
+**Output boundary**: ALL file writes MUST target `REVIEW_DIR` or `.workflow/state.json` only. NEVER modify source code, execution artifacts, or files outside these paths.
 </context>
 
+<invariants>
+1. **Review is read-only on source** — NEVER modify source code, test files, or execution artifacts. Review produces reports only.
+2. **Findings require evidence** — every finding MUST reference file:line and include a code snippet or concrete description. No vague or unanchored findings.
+3. **Verdict is data-driven** — NEVER change verdict severity to accommodate user preference without new evidence. Verdicts flow from findings, not negotiation.
+4. **Dimension independence** — each review dimension produces findings independently. One dimension's results MUST NOT suppress or override another's.
+5. **Prior review delta** — when a prior review.json exists for the same phase, findings MUST be compared. Do NOT re-report already-resolved findings as new.
+6. **Spec conflict integrity** — if code contradicts a spec entry, flag via `maestro spec conflict mark`. NEVER silently accept the contradiction or edit the spec inline.
+</invariants>
+
 <execution>
 Follow '~/.maestro/workflows/review.md' completely.
 

package/.claude/commands/quality-sync.md

@@ -25,8 +25,18 @@ $ARGUMENTS -- optional flags:
 - `--full` -- Complete resync of all tracked files (ignores git diff, rebuilds all docs)
 - `--since <commit|HEAD~N>` -- Diff since specific commit (default: last sync timestamp)
 - `--dry-run` -- Show what would be updated without writing changes
+
+**Output boundary**: ALL file writes MUST target `.workflow/codebase/`, `.workflow/state.json`, or `doc-index.json` only. NEVER modify source code or files outside `.workflow/`. `--dry-run` MUST suppress all writes.
 </context>
 
+<invariants>
+1. **Source code is read-only** — sync reads source files to generate documentation. NEVER modify source code, test files, or any non-documentation files.
+2. **Dry-run is side-effect-free** — when `--dry-run` is set, NO file writes occur. Report only what would change.
+3. **Impact trace before refresh** — NEVER regenerate a doc file without first tracing which source changes affect it via doc-index.json. Untargeted full-refresh requires explicit `--full` flag.
+4. **Idempotent sync** — running sync twice with the same diff MUST produce identical results. State.json timestamp prevents redundant re-runs.
+5. **Incremental by default** — without `--full`, only changed components are refreshed. NEVER silently expand to a full rebuild.
+</invariants>
+
 <execution>
 Follow '~/.maestro/workflows/sync.md' completely.
 

package/.claude/commands/quality-test.md

@@ -24,8 +24,20 @@ UAT-style conversational testing for a completed phase. Interactive scenario wal
 Phase or task: $ARGUMENTS (optional)
 
 Flags, artifact context resolution, and output directory format defined in workflow test.md.
+
+**Output boundary**: ALL file writes MUST target `.workflow/scratch/{YYYYMMDD}-test-P{N}-{slug}/`, `.workflow/state.json`, or `.workflow/issues.jsonl` only. NEVER modify source code or execution artifacts outside these paths. `--frontend-verify` additionally writes `e2e-results.json` to the same scratch directory.
 </context>
 
+<invariants>
+1. **UAT is observational** — test execution observes behavior and records results. NEVER modify source code during testing. Source fixes belong to debug→plan→execute cycle.
+2. **Severity is inferred, not asked** — severity MUST be inferred from user's natural language description of issues. NEVER explicitly ask the user to assign severity levels.
+3. **One scenario at a time** — tests MUST be presented individually for user verification. NEVER batch-present multiple scenarios or assume outcomes.
+4. **Evidence before verdict** — UAT confidence MUST be scored with the 4-dimension factor model from actual test results. NEVER emit a verdict without running the readiness gate.
+5. **Existing UAT is resumable** — when uat.md exists for the target phase, offer resume. NEVER silently overwrite prior test progress.
+6. **Frontend-verify is deterministic** — `--frontend-verify` mode uses browser assertions with concrete pass/fail per criterion. NEVER treat "no response" or timeout as pass.
+7. **Auto-fix has bounds** — `--auto-fix` gap-fix loop MUST NOT exceed 2 iterations. Persistent failures escalate to debug, not infinite retry.
+</invariants>
+
 <execution>
 **Mode select:** `--frontend-verify` → 走下方 **Frontend Verify Mode**（确定性浏览器 smoke，**不是**对话式 UAT）；否则 Follow '~/.maestro/workflows/test.md' completely.
 

package/.claude/commands/security-audit.md

@@ -32,8 +32,19 @@ $ARGUMENTS — Parse tier and scope:
 | quick | ✓ | ✓ | — | — | — | — |
 | standard | ✓ | ✓ | ✓ | ✓ | — | — |
 | deep | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
+
+**Output boundary**: ALL file writes MUST target `.workflow/scratch/{YYYYMMDD}-security-audit-{tier}-{slug}/` or `.workflow/state.json` only. NEVER modify source code, configuration files, or dependencies. Audit is read-only analysis.
 </context>
 
+<invariants>
+1. **Audit is read-only** — NEVER modify source code, configuration, dependencies, or CI/CD files during audit. Security audit produces reports only.
+2. **Findings require file:line evidence** — every finding MUST reference a specific file:line location and include the vulnerable code pattern. No vague or category-only findings.
+3. **Severity NEVER downgraded without justification** — if a finding matches a known OWASP category, its severity follows OWASP guidance. Downgrading requires documented rationale (e.g., compensating control exists).
+4. **Tier coverage is mandatory** — all scan phases required by the selected tier MUST complete. NEVER skip a tier-required phase silently; failures are logged as W00x warnings.
+5. **False positive marking requires evidence** — marking a finding as false positive MUST include the compensating control or code path that prevents exploitation. NEVER dismiss findings without counter-evidence.
+6. **Secrets are never logged** — if secrets are discovered, report their location (file:line) and type but NEVER include the actual secret value in the report output.
+</invariants>
+
 <execution>
 
 ### Phase Gates (MANDATORY, BLOCKING)

package/.claude/commands/spec-add.md

@@ -44,9 +44,36 @@ Scope-to-directory mapping, category-to-file mapping, and entry format defined i
 ```
 </context>
 
+<invariants>
+1. **Idempotent append** — duplicate entry ID MUST be rejected (E003-level check on title + category match before write)
+2. **Category validation** — category MUST be one of: coding, arch, quality, debug, test, review, learning, ui. Invalid category → E003
+3. **Scope isolation** — writes target ONLY the scope-resolved directory; project scope NEVER writes to global (~/.maestro/specs/), global scope NEVER writes to project (.workflow/specs/)
+4. **Confirmation gate** — MUST AskUserQuestion before appending entry (unless -y flag); NEVER write without user confirmation in interactive mode
+5. **Entry format invariance** — all entries MUST use `<spec-entry>` closed-tag format with id, keywords, and category attributes
+6. **Output boundary** — ALL file writes MUST target the scope-resolved specs directory (.workflow/specs/, ~/.maestro/specs/, .workflow/collab/specs/, or .workflow/collab/{uid}/specs/) and optionally .workflow/knowhow/ for --ref mode. NEVER modify source code or files outside these paths
+</invariants>
+
 <execution>
 Follow '~/.maestro/workflows/specs-add.md' completely.
 
+### Phase Gates (MANDATORY, BLOCKING)
+
+**GATE 1: Parse → Validate**
+- REQUIRED: Category and content both parsed from arguments.
+- REQUIRED: Category is a valid value (coding, arch, quality, debug, test, review, learning, ui).
+- REQUIRED: Scope resolved to a valid directory path.
+- BLOCKED if: E001 (missing args), E003 (invalid category), E004 (invalid scope), E005 (personal scope without uid).
+
+**GATE 2: Validate → Format**
+- REQUIRED: Specs directory exists for the resolved scope.
+- REQUIRED: No duplicate entry with identical title + category already present in target file.
+- BLOCKED if: E002 (specs not initialized).
+
+**GATE 3: Format → Write**
+- REQUIRED: `<spec-entry>` block formatted with id, keywords, category attributes.
+- REQUIRED: User confirmation via AskUserQuestion (unless -y flag).
+- BLOCKED if: user declines confirmation — abort without writing.
+
 **Confirmation gate**: Unless -y flag is passed, after formatting the `<spec-entry>` block but before appending to the target file, AskUserQuestion showing the formatted entry, target file path, and scope. Proceed only on user confirm.
 </execution>
 

package/.claude/commands/spec-load.md

@@ -57,8 +57,33 @@ When loading entries with `ref` attribute, only the summary is shown with a load
 Use the load command to read the full referenced document.
 </context>
 
+<invariants>
+1. **Read-only** — NEVER modify, create, or delete any spec files during load. This command is purely a read operation
+2. **Output to context only** — loaded specs are injected into the conversation context; NEVER write loaded content to new files or modify existing files
+3. **Scope layering** — global scope MUST merge both ~/.maestro/specs/ and .workflow/specs/; project scope loads .workflow/specs/ only; team adds .workflow/collab/specs/; personal adds .workflow/collab/{uid}/specs/
+4. **Category primary doc** — when --category is specified, the primary category doc MUST be loaded in full before cross-file matching
+5. **Entry-level filtering** — --keyword filtering operates at `<spec-entry>` level via keywords attribute, NOT at file level; unmatched entries in a matching file are excluded
+6. **Output boundary** — this command produces NO file writes. All output is conversation-context injection only
+</invariants>
+
 <execution>
 Follow '~/.maestro/workflows/specs-load.md' completely.
+
+### Phase Gates (MANDATORY, BLOCKING)
+
+**GATE 1: Parse → Discover**
+- REQUIRED: Arguments parsed — at least one of --category or --keyword is provided, or empty args triggers full load.
+- REQUIRED: Scope resolved (default: global+project merged).
+- BLOCKED if: invalid scope value or invalid category value.
+
+**GATE 2: Discover → Load**
+- REQUIRED: At least one spec directory exists in the resolved scope chain.
+- BLOCKED if: E001 — .workflow/specs/ not initialized AND no global specs available. Warn and abort.
+
+**GATE 3: Load → Display**
+- REQUIRED: Spec files read and entries parsed.
+- REQUIRED: Keyword filtering applied if --keyword was provided.
+- BLOCKED if: no readable spec files found in any scope layer.
 </execution>
 
 <error_codes>

package/.claude/commands/spec-remove.md

@@ -31,8 +31,34 @@ $ARGUMENTS -- expects `<entry-id>` (e.g., `spec-learnings-003`, `spec-coding-con
 - `--cascade` — When the target spec is a ref-type entry (created via `spec-add --ref` and linked to a knowhow document), also delete the referenced knowhow file. Without this flag, ref-type removal leaves an orphan knowhow file.
 </context>
 
+<invariants>
+1. **Confirmation required** — MUST AskUserQuestion before deletion (unless -y flag); NEVER remove entries silently
+2. **Referential integrity** — before removing, check if other spec entries reference the target entry; warn user if references exist
+3. **Cascade explicit** — ref-type entries MUST NOT cascade-delete the linked knowhow file unless --cascade is explicitly passed; default leaves orphan knowhow intact
+4. **Atomic removal** — use `maestro wiki remove-entry` for atomic operation; NEVER manually edit spec files to remove entries
+5. **Index consistency** — wiki index MUST be auto-updated after removal; stale index entries are a hard failure
+6. **Output boundary** — file modifications MUST target ONLY the spec container file (.workflow/specs/*.md) and optionally the referenced knowhow file (.workflow/knowhow/*) when --cascade is used. NEVER modify source code or files outside these paths
+</invariants>
+
 <execution>
 Follow '~/.maestro/workflows/specs-remove.md' completely.
+
+### Phase Gates (MANDATORY, BLOCKING)
+
+**GATE 1: Parse → Lookup**
+- REQUIRED: Entry ID parsed from arguments.
+- BLOCKED if: E001 — no entry ID provided.
+
+**GATE 2: Lookup → Confirm**
+- REQUIRED: .workflow/specs/ directory exists.
+- REQUIRED: Entry found in wiki index as a spec sub-node.
+- REQUIRED: Entry content loaded for user preview.
+- BLOCKED if: E002 (specs not initialized), E003 (entry not found), E004 (wrong type).
+
+**GATE 3: Confirm → Remove**
+- REQUIRED: User confirmed removal via AskUserQuestion (unless -y flag).
+- REQUIRED: If --cascade and entry has ref attribute, user additionally confirmed knowhow file deletion.
+- BLOCKED if: user declines — abort without modification.
 </execution>
 
 <error_codes>