mindforge-cc 8.1.1 → 8.2.0

package/.mindforge/mirrors/mirror-sre-776a1cf9/.mindforge/skills-builder/learn-protocol.md

@@ -0,0 +1,161 @@
+# MindForge v2 — Learn Protocol
+
+## Purpose
+Convert any knowledge source (URL, local file/dir, or current session) into a
+reusable, validated, committed MindForge SKILL.md file.
+
+## Activation sources
+
+### Source type: URL
+```
+/mindforge:learn https://docs.prisma.io/concepts/components/prisma-schema
+```
+Use RESEARCH_MODEL (default: gemini-2.5-pro with 1M context) to ingest and
+analyse the documentation. For large documentation sets, Gemini 2.5 Pro can
+read the entire page including all examples at once.
+
+### Source type: local file or directory
+```
+/mindforge:learn ./docs/api-conventions.md
+/mindforge:learn ./docs/internal/
+```
+Read file(s) directly (no model call needed for reading). Use EXECUTOR_MODEL
+to analyse content and extract patterns.
+
+### Source type: session
+```
+/mindforge:learn --session
+```
+Analyse the current session's SUMMARY files, ADR files, debug reports, and
+HANDOFF.json implicit_knowledge to find patterns worth capturing.
+
+### Source type: npm package docs
+```
+/mindforge:learn npm:zod
+/mindforge:learn npm:prisma
+```
+Fetch from npmjs.com/package/[name] and read the README + linked docs.
+
+## Step-by-step learn protocol
+
+### Step 1: Read and understand the source
+For URLs: use `source-loader.js` to fetch content (with SSRF protection).
+For local: use `source-loader.js` to read file(s) with walkDir().
+For session: read all SUMMARY-*.md and HANDOFF.json implicit_knowledge.
+For npm: fetch README from npmjs.com API.
+
+Maximum context: 900K chars for Gemini (1M context); 50K chars for other models.
+
+### Step 2: Identify the top 10 reusable patterns or rules
+Ask the analysis model:
+```
+You are an expert at reading technical documentation and extracting reusable
+engineering rules and patterns.
+
+Read this documentation carefully:
+[source content]
+
+Identify exactly 10 reusable patterns, rules, or best practices that would
+be most valuable to inject into an AI agent before it works with this technology.
+
+For each pattern:
+- Give it a short title (≤ 60 chars)
+- Write a concise rule statement (≤ 150 chars, actionable)
+- Include a code example showing correct usage (TypeScript/JavaScript preferred)
+- Identify if there is a common anti-pattern to warn against
+- Rate importance: CRITICAL | HIGH | MEDIUM | LOW
+
+Format as JSON array: [{ title, rule, example, anti_pattern, importance }]
+```
+
+### Step 3: Identify 15-25 trigger keywords
+Ask the analysis model:
+```
+Based on the patterns above, identify 15-25 keywords that, if found in a
+task description or code file path, should trigger this skill to load.
+
+Rules for good trigger keywords:
+- 2-4 words each (single-word triggers are too broad)
+- Specific to this technology (not generic like "database" or "model")
+- Cover: package names, file extensions, common function names, config file names
+- Include both noun and verb forms where applicable
+
+Return as JSON array of strings: ["keyword1", "keyword2", ...]
+```
+
+### Step 4: Write the SKILL.md following the authoring template
+Use the standard MindForge SKILL.md format from `docs/skills-authoring-guide.md`.
+Populate all sections:
+- Frontmatter (name, version, status, triggers, description)
+- Purpose (why this skill exists)
+- Key patterns (from Step 2 — the 10 patterns)
+- Anti-patterns to avoid
+- Code examples (at least 3 complete, working examples)
+- Self-check checklist (5-10 items)
+- Version history
+
+### Step 5: Run Level 1 + Level 2 validation
+Level 1 (schema): frontmatter complete, triggers present, mandatory sections exist.
+Level 2 (content): no placeholder text, code examples parse, triggers are specific.
+
+Use `skill-scorer.js` to compute the quality score (target: ≥ 60 for register,
+≥ 80 for community publish).
+
+If score < 60: report the specific gaps and ask user whether to fix or discard.
+
+### Step 6: Present to user for review and approval
+
+Display:
+```
+📚 Skill Generated: [skill-name]
+─────────────────────────────────────────────────────
+Source:        [source type and location]
+Quality score: [score]/100 ([breakdown])
+Patterns:      [N] extracted
+Triggers:      [K] keywords
+Tier:          [Core/Org/Project]
+
+Preview (first 3 patterns):
+  1. [title]: [rule]
+  2. [title]: [rule]
+  3. [title]: [rule]
+
+Skill file: .mindforge/skills/[name]/SKILL.md
+
+[ y ] Register and commit
+[ n ] Discard
+[ e ] Edit before registering
+[ p ] Publish to community marketplace (requires quality score ≥ 80)
+```
+
+### Step 7: If approved — register and commit
+```bash
+# Register in MANIFEST.md (tier determined by target: project=T3, org=T2, core=T1)
+# Default for learned skills: Project tier (T3) unless explicitly set
+node bin/skills-builder/skill-registrar.js --tier project --name [skill-name]
+
+# Write AUDIT entry
+{
+  "event": "skill_learned",
+  "source_type": "url|local|session|npm",
+  "source": "[url or path]",
+  "skill_name": "[name]",
+  "quality_score": [score],
+  "pattern_count": [N],
+  "trigger_count": [K]
+}
+
+# Commit
+git add .mindforge/skills/[name]/SKILL.md .mindforge/org/skills/MANIFEST.md
+git commit -m "feat(skills): learn [skill-name] from [source type]"
+```
+
+## Session-based learning (`--session` flag)
+Analyse these sources in order:
+1. All SUMMARY-*.md files in .planning/phases/[current phase]/
+2. HANDOFF.json implicit_knowledge array (Level 2+ compaction entries)
+3. All ADR-*.md files created in the current phase
+4. RETROSPECTIVE-*.md if it exists in the current phase
+
+Ask: "What patterns emerged that would have been useful to know before this phase?"
+Generate up to 3 skills from this analysis (not more — quality over quantity).

package/.mindforge/mirrors/mirror-sre-776a1cf9/.mindforge/skills-builder/quality-scoring.md

@@ -0,0 +1,120 @@
+# MindForge v2 — Skill Quality Scoring
+
+## Purpose
+Every SKILL.md gets a quality score from 0-100 before registration.
+This score determines: whether it can be registered (≥ 60), whether it can
+be published to the community marketplace (≥ 80), and how prominently it
+is featured in search results.
+
+## Scoring dimensions (total: 100 points)
+
+### Dimension 1: Trigger Coverage (30 points)
+Measures: How many unique, specific trigger keywords the skill has.
+- 25-30 triggers: 30 points (full score)
+- 20-24 triggers: 24 points
+- 15-19 triggers: 18 points
+- 10-14 triggers: 12 points
+- 5-9 triggers: 6 points
+- < 5 triggers: 0 points
+
+Penalty: -2 points per generic trigger (words like "database", "api", "model"
+that would fire for almost any project). Triggers must be technology-specific.
+
+### Dimension 2: Mandatory Actions Completeness (25 points)
+Measures: Whether the skill has complete, actionable mandatory actions.
+Check for these mandatory sections:
+- [ ] At least 5 concrete "always do X" rules (5 pts)
+- [ ] At least 3 concrete "never do Y" rules (5 pts)
+- [ ] Security consideration section (5 pts)
+- [ ] Performance consideration section (5 pts)
+- [ ] Error handling guidance (5 pts)
+
+### Dimension 3: Code Examples (20 points)
+Measures: Quality and completeness of code examples.
+- 5+ complete, working code examples: 20 points
+- 3-4 examples: 14 points
+- 1-2 examples: 7 points
+- No examples: 0 points
+
+Bonus: +2 points if examples show both correct pattern AND anti-pattern side-by-side.
+
+### Dimension 4: Self-Check Checklist (15 points)
+Measures: Does the skill include a checklist an agent can use to verify its work?
+- 10+ checklist items: 15 points
+- 7-9 items: 10 points
+- 4-6 items: 7 points
+- 1-3 items: 3 points
+- No checklist: 0 points
+
+### Dimension 5: Injection Safety (10 points)
+Measures: Does the skill pass all injection guard checks?
+- No injection patterns detected: 10 points (full score)
+- Any injection pattern detected: 0 points (FAIL — skill cannot be registered)
+
+Injection patterns checked (same 8 as in skill-loader.md):
+IGNORE ALL PREVIOUS INSTRUCTIONS, DISREGARD YOUR INSTRUCTIONS, etc.
+
+### Dimension 6: No Placeholders (10 points)
+Measures: Absence of placeholder/template text that was never filled in.
+- Zero placeholders: 10 points
+- 1-2 placeholders: 5 points
+- 3+ placeholders: 0 points
+
+Placeholder patterns:
+`[your description here]`, `TODO`, `FIXME`, `<description>`, `...fill in...`
+
+### Dimension 7: Version History (10 points)
+Measures: Whether the skill has a changelog / version history.
+- Has ## Version History section with at least v1.0.0 entry: 10 points
+- Has frontmatter version but no history section: 5 points
+- No version information: 0 points
+
+Bonus: +2 points if skill has been updated more than once (shows maintenance).
+
+## Quality thresholds
+
+| Score | Status | Allowed actions |
+|---|---|---|
+| 90-100 | Excellent | Register, publish, featured in marketplace |
+| 80-89 | Good | Register, eligible to publish |
+| 70-79 | Acceptable | Register, not eligible for marketplace |
+| 60-69 | Minimum | Register with warning |
+| < 60 | Insufficient | Cannot register — must improve first |
+
+## `session_quality_lift` metric
+After a skill has been used in ≥ 5 sessions, compute:
+```
+lift = avg(session_quality_score when skill active)
+     - avg(session_quality_score when skill not active)
+```
+This is the most honest signal of skill value. A skill with quality_score=94
+but session_quality_lift=-2 is a misleading skill (it sounds good but hurts results).
+
+## Scoring output format
+```json
+{
+  "skill_name": "prisma-schema",
+  "version": "1.0.0",
+  "quality_score": 84,
+  "threshold_status": "good",
+  "can_register": true,
+  "can_publish": true,
+  "score_breakdown": {
+    "trigger_coverage": 27,
+    "mandatory_actions": 22,
+    "code_examples": 17,
+    "self_check": 12,
+    "injection_safe": 10,
+    "no_placeholders": 9,
+    "version_history": 8
+  },
+  "penalties_applied": [
+    { "dimension": "trigger_coverage", "reason": "1 generic trigger 'database'", "penalty": -2 }
+  ],
+  "improvement_suggestions": [
+    "Add 3 more trigger keywords to reach 25+ (currently 22)",
+    "Add performance considerations section (currently missing)",
+    "Add 3 more checklist items to reach 10+ (currently 7)"
+  ]
+}
+```

package/.mindforge/mirrors/mirror-sre-776a1cf9/.mindforge/team/TEAM-PROFILE.md

@@ -0,0 +1,42 @@
+# MindForge Team Profile
+# Auto-generated by /mindforge:profile-team
+
+## IMPORTANT: Metrics usage policy
+Per ADR-014, data in this file and `.mindforge/metrics/` is for system
+improvement only, not developer performance evaluation.
+
+Use data for:
+- response personalization
+- skill loading improvements
+- compaction and planning tuning
+- process retrospectives (not people scoring)
+
+## Team composition
+| Name | Email | Primary role | Timezone | Experience |
+|---|---|---|---|---|
+| [Name] | [email] | [role] | [UTC+X] | [level] |
+
+## Tech stack preferences
+| Layer | Preferred | Comfortable | Learning |
+|---|---|---|---|
+| Backend | TypeScript/Node.js | Python | Go |
+| Frontend | React/Next.js | Vue | Svelte |
+| Database | PostgreSQL | MySQL | MongoDB |
+| Testing | Vitest | Jest | Playwright |
+
+## Working patterns
+- Average session length: [N] minutes
+- Peak working hours: [N-N]
+- Verify pass rate: [N%]
+- Common failure type: [from AUDIT]
+
+## Personalization rules
+- Verbosity: concise
+- Review style: direct
+- Preferred code organization: feature-based
+
+## Known strengths
+- [area]
+
+## Known growth areas
+- [area]

package/.mindforge/mirrors/mirror-sre-776a1cf9/.mindforge/team/multi-handoff.md

@@ -0,0 +1,23 @@
+# MindForge Team — Multi-Developer HANDOFF
+
+## Purpose
+Allow multiple developers or agent sessions to collaborate without silently
+ stomping shared state.
+
+## Shared coordination rules
+When a developer starts a plan, first check shared `HANDOFF.json` state. If the
+ same plan already appears under `active_developers`, stop and ask for
+ clarification before proceeding.
+
+Developers with `last_seen` older than 4 hours are considered stale and may be
+ removed automatically on the next session start.
+
+## Required shared state fields
+- `active_developers`
+- current phase and plan ownership
+- recent files
+- blockers and decisions needed
+
+## Audit discipline
+Each task completion or failure commit must include any new AUDIT entries so
+ shared history is not stranded in an uncommitted worktree.

package/.mindforge/mirrors/mirror-sre-776a1cf9/.mindforge/team/profiles/README.md

@@ -0,0 +1,13 @@
+# MindForge Per-Developer Profiles
+
+Use `PROFILE-[dev-id].md` files to store per-developer preferences and observed
+patterns. `dev-id` is a sanitized email.
+
+Template fields:
+- Identity (name/email/role/timezone)
+- Communication preferences
+- Technical preferences
+- Observed session metrics
+- Strengths and growth areas
+
+Privacy: include only professional, collaboration-relevant data.

package/.mindforge/mirrors/mirror-sre-776a1cf9/.mindforge/team/session-merger.md

@@ -0,0 +1,18 @@
+# MindForge Team — Session Merger
+
+## Purpose
+Merge concurrent session state safely after parallel work or multi-developer
+ execution.
+
+## Merge strategy
+1. Merge `HANDOFF.json` through git, not ad hoc overwrite
+2. Resolve conflicts explicitly when two sessions claim the same plan
+3. Preserve both sides' blockers and decisions until reconciled
+4. Keep AUDIT append-only; ensure entries were committed with the task commits
+
+Git merge conflicts are the correct mechanism for contested shared state.
+
+## Conflict rules
+- Same plan claimed by two developers: escalate for human resolution
+- Different plans touching shared files: merge carefully, then rerun verification
+- Stale active developer entry: prune if `last_seen` is older than 4 hours

package/.mindforge/mirrors/mirror-sre-776a1cf9/.planning/AUDIT.jsonl

@@ -0,0 +1,45 @@
+{"id":"243b022d-1be6-438c-a94b-23da9c097042","timestamp":"2026-04-11T14:31:41.594Z","event":"span_started","trace_id":null,"span_id":"sp_14e9b069e8a7","parent_span_id":null,"span_name":"span_stable","agent":"mf-researcher"}
+{"id":"8ba8a730-741e-4861-92b2-d0c56de239c4","timestamp":"2026-04-11T14:31:41.595Z","event":"span_started","trace_id":null,"span_id":"sp_128731ffa142","parent_span_id":null,"span_name":"span_drift","agent":"mf-researcher"}
+{"id":"37e94e6a-184a-4915-9a15-803af91d298c","timestamp":"2026-04-11T14:31:41.596Z","event":"reasoning_trace","trace_id":null,"span_id":"span_stable","agent":"mf-researcher","thought":"I will now analyze the dependencies and create a plan.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"46caf2ae-00ac-4c76-b0bf-ba14a71fba98","timestamp":"2026-04-11T14:31:41.596Z","event":"drift_remediation_event","trace_id":null,"span_id":"span_drift","score":0.055,"strategy":"NOT_REQUIRED","markers":{"density":0.05,"pattern":0.1,"contradiction":0},"validation":{"is_valid":false,"critique":"Reflection detected minor inconsistencies or self-doubt."}}
+{"id":"0b0a92c5-1742-4404-badf-d2128f14911e","timestamp":"2026-04-11T14:31:41.596Z","event":"reasoning_trace","trace_id":null,"span_id":"span_drift","agent":"mf-researcher","thought":"I am not sure how to proceed, maybe I should wait and check the goal again.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"1ca67414-69ff-48c2-a188-cf49277d951c","timestamp":"2026-04-11T14:32:03.705Z","event":"span_started","trace_id":null,"span_id":"sp_85db5e74eabd","parent_span_id":null,"span_name":"span_stable","agent":"mf-researcher"}
+{"id":"8bcf4d54-d141-46e7-99e2-9ccd7fbc32c2","timestamp":"2026-04-11T14:32:03.706Z","event":"span_started","trace_id":null,"span_id":"sp_9c2f90853a18","parent_span_id":null,"span_name":"span_drift","agent":"mf-researcher"}
+{"id":"5c4ae8fb-74a4-4bc4-b328-e727fbf81286","timestamp":"2026-04-11T14:32:03.706Z","event":"reasoning_trace","trace_id":null,"span_id":"span_stable","agent":"mf-researcher","thought":"I will now analyze the dependencies and create a plan.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"27f29f84-4f5b-457e-b61a-b922c1c9b143","timestamp":"2026-04-11T14:32:03.707Z","event":"drift_remediation_event","trace_id":null,"span_id":"span_drift","score":0.055,"strategy":"GOLDEN_TRACE_INJECTION","remediation_id":"rem_fuk65p","markers":{"density":0.05,"pattern":0.1,"contradiction":0},"validation":{"is_valid":false,"critique":"Reflection detected minor inconsistencies or self-doubt."}}
+{"id":"cf0160e2-42ab-4345-beb4-501eb117ad49","timestamp":"2026-04-11T14:32:03.707Z","event":"reasoning_trace","trace_id":null,"span_id":"span_drift","agent":"mf-researcher","thought":"I am not sure how to proceed, maybe I should wait and check the goal again.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"7fe4e1ee-897f-4084-9fac-ec63ef30573a","timestamp":"2026-04-11T14:32:20.188Z","event":"span_started","trace_id":null,"span_id":"sp_c57ab4324f72","parent_span_id":null,"span_name":"span_stable","agent":"mf-researcher"}
+{"id":"e52a7faa-cd3a-45ff-83b1-63d85ebd1a3b","timestamp":"2026-04-11T14:32:20.189Z","event":"span_started","trace_id":null,"span_id":"sp_81db2eb8f21c","parent_span_id":null,"span_name":"span_drift","agent":"mf-researcher"}
+{"id":"48a9ef82-4385-4b85-afbe-384d8da9bd7e","timestamp":"2026-04-11T14:32:20.189Z","event":"reasoning_trace","trace_id":null,"span_id":"span_stable","agent":"mf-researcher","thought":"I will now analyze the dependencies and create a plan.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"20ea33f3-5e3d-4da0-9871-c199ec7689f3","timestamp":"2026-04-11T14:32:20.190Z","event":"drift_remediation_event","trace_id":null,"span_id":"span_drift","score":0.055,"strategy":"GOLDEN_TRACE_INJECTION","remediation_id":"rem_1y8xnj","markers":{"density":0.05,"pattern":0.1,"contradiction":0},"validation":{"is_valid":false,"critique":"Reflection detected minor inconsistencies or self-doubt."}}
+{"id":"a1fc540f-3afb-4a86-8eee-d31dbfe8899f","timestamp":"2026-04-11T14:32:20.190Z","event":"reasoning_trace","trace_id":null,"span_id":"span_drift","agent":"mf-researcher","thought":"I am not sure how to proceed, maybe I should wait and check the goal again.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"2ba3c34a-1d69-4847-8236-e770c904b031","timestamp":"2026-04-11T14:32:52.215Z","event":"span_started","trace_id":null,"span_id":"sp_bab2aa708d2e","parent_span_id":null,"span_name":"span_stable","agent":"mf-researcher"}
+{"id":"e7bf437f-5c50-4dfc-bbf7-8270bcaaffff","timestamp":"2026-04-11T14:32:52.216Z","event":"span_started","trace_id":null,"span_id":"sp_37872254b0af","parent_span_id":null,"span_name":"span_drift","agent":"mf-researcher"}
+{"id":"bb2c97e8-0306-4c43-8884-7fc3959c04bc","timestamp":"2026-04-11T14:32:52.216Z","event":"reasoning_trace","trace_id":null,"span_id":"span_stable","agent":"mf-researcher","thought":"I will now analyze the dependencies and create a plan.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"47fe4db7-475f-451e-b4d7-4ddeb56d0d3e","timestamp":"2026-04-11T14:32:52.217Z","event":"drift_remediation_event","trace_id":null,"span_id":"span_drift","score":0.055,"strategy":"GOLDEN_TRACE_INJECTION","remediation_id":"rem_9ztj8g","markers":{"density":0.05,"pattern":0.1,"contradiction":0},"validation":{"is_valid":false,"critique":"Reflection detected minor inconsistencies or self-doubt."}}
+{"id":"a8bbaf5b-4185-4fd1-a5ab-7b43e22ca4ce","timestamp":"2026-04-11T14:32:52.217Z","event":"reasoning_trace","trace_id":null,"span_id":"span_drift","agent":"mf-researcher","thought":"I am not sure how to proceed, maybe I should wait and check the goal again.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"380b6488-205c-474f-b7df-31dc3647e6c3","timestamp":"2026-04-11T14:33:08.279Z","event":"span_started","trace_id":null,"span_id":"sp_1f7eff8f54c1","parent_span_id":null,"span_name":"span_stable","agent":"mf-researcher"}
+{"id":"06f5a154-a500-4c78-8133-3aed0918514f","timestamp":"2026-04-11T14:33:08.280Z","event":"span_started","trace_id":null,"span_id":"sp_02eca7cd627f","parent_span_id":null,"span_name":"span_drift","agent":"mf-researcher"}
+{"id":"79d95aab-9a1c-4c4c-ad44-3aba37663145","timestamp":"2026-04-11T14:33:08.281Z","event":"reasoning_trace","trace_id":null,"span_id":"span_stable","agent":"mf-researcher","thought":"I will now analyze the dependencies and create a plan.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"309bf1aa-89d4-4588-9201-d6e142e3f670","timestamp":"2026-04-11T14:33:08.281Z","event":"drift_remediation_event","trace_id":null,"span_id":"span_drift","score":0.055,"strategy":"GOLDEN_TRACE_INJECTION","remediation_id":"rem_904til","markers":{"density":0.05,"pattern":0.1,"contradiction":0},"validation":{"is_valid":false,"critique":"Reflection detected minor inconsistencies or self-doubt."}}
+{"id":"3db986a7-7905-495c-a732-2d0dde4cef06","timestamp":"2026-04-11T14:33:08.281Z","event":"reasoning_trace","trace_id":null,"span_id":"span_drift","agent":"mf-researcher","thought":"I am not sure how to proceed, maybe I should wait and check the goal again.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"6ed5319c-6c50-48cd-ba52-e497bc330031","timestamp":"2026-04-11T14:33:24.808Z","event":"span_started","trace_id":null,"span_id":"sp_74851c254d10","parent_span_id":null,"span_name":"span_stable","agent":"mf-researcher"}
+{"id":"fed8723c-52f3-41b0-8391-287be1864a8b","timestamp":"2026-04-11T14:33:24.809Z","event":"span_started","trace_id":null,"span_id":"sp_84bdb2ffb78e","parent_span_id":null,"span_name":"span_drift","agent":"mf-researcher"}
+{"id":"202f4c47-d26e-45ac-a35b-b864f71f57a5","timestamp":"2026-04-11T14:33:24.811Z","event":"reasoning_trace","trace_id":null,"span_id":"span_stable","agent":"mf-researcher","thought":"I will now analyze the dependencies and create a plan.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"6c387954-64c8-4491-9b5a-bfa36d0dc19a","timestamp":"2026-04-11T14:33:24.829Z","event":"drift_remediation_event","trace_id":null,"span_id":"span_drift","score":0.055,"strategy":"GOLDEN_TRACE_INJECTION","remediation_id":"rem_cv5ovc","markers":{"density":0.05,"pattern":0.1,"contradiction":0},"validation":{"is_valid":false,"critique":"Reflection detected minor inconsistencies or self-doubt."}}
+{"id":"184c1014-7ec5-4413-9d1a-30316b718f6a","timestamp":"2026-04-11T14:33:24.851Z","event":"reasoning_trace","trace_id":null,"span_id":"span_drift","agent":"mf-researcher","thought":"I am not sure how to proceed, maybe I should wait and check the goal again.","resolution":"none","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"a22f3437-e1ca-4617-90f8-0b01992f85c8","timestamp":"2026-04-11T14:49:35.976Z","event":"span_started","trace_id":"v8_test_trace","span_id":"sp_05bd390df397","parent_span_id":null,"span_name":"v8_test_span"}
+{"id":"94d1c1d0-aaa3-4422-a70a-5f4cefcd74c9","timestamp":"2026-04-11T14:49:35.990Z","event":"reasoning_trace","trace_id":"v8_test_trace","span_id":"sp_05bd390df397","agent":"mf-tester","thought":"This is a celestial persistence test.","resolution":"verified","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"221f8823-c6e6-4337-8f45-a471a06bafd4","timestamp":"2026-04-11T14:49:35.992Z","event":"span_completed","trace_id":"v8_test_trace","span_id":"sp_05bd390df397","status":"success"}
+{"id":"600c7d1f-8a7d-4d63-8cf0-6821a3285a07","timestamp":"2026-04-11T15:24:42.692Z","event":"span_started","trace_id":"v8_test_trace","span_id":"sp_89404b788505","parent_span_id":null,"span_name":"v8_test_span"}
+{"id":"221da918-2ce5-42fa-928a-d12a192f10af","timestamp":"2026-04-11T15:24:42.706Z","event":"reasoning_trace","trace_id":"v8_test_trace","span_id":"sp_89404b788505","agent":"mf-tester","thought":"This is a celestial persistence test.","resolution":"verified","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"6b9820f4-9b9c-4fdb-8dd1-a1a01bb92ab6","timestamp":"2026-04-11T15:24:42.707Z","event":"span_completed","trace_id":"v8_test_trace","span_id":"sp_89404b788505","status":"success"}
+{"id":"342d1804-6e39-4c9a-a933-d77bf6fecbb0","timestamp":"2026-04-11T15:25:08.603Z","event":"span_started","trace_id":"v8_trace_zqba2o","span_id":"sp_b7a4d7a69f27","parent_span_id":null,"span_name":"v8_span_zqba2o"}
+{"id":"68ea10ea-6a07-47c7-b7a8-22661c266b26","timestamp":"2026-04-11T15:25:08.614Z","event":"reasoning_trace","trace_id":"v8_trace_zqba2o","span_id":"sp_b7a4d7a69f27","agent":"mf-tester","thought":"Celestial persistence test zqba2o.","resolution":"verified","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"3dfe4f8f-134e-4bd1-a52a-eb2459d5405f","timestamp":"2026-04-11T15:25:08.615Z","event":"span_completed","trace_id":"v8_trace_zqba2o","span_id":"sp_b7a4d7a69f27","status":"success"}
+{"id":"2a3d0f02-f94d-4da6-850e-a18538a7dbe7","timestamp":"2026-04-11T15:25:59.124Z","event":"span_started","trace_id":"v8_trace_v7iw6q","span_id":"sp_8d5da7fa5a4e","parent_span_id":null,"span_name":"v8_span_v7iw6q"}
+{"id":"bc4fc8cb-1621-4f14-bb20-2ec2caa33c47","timestamp":"2026-04-11T15:25:59.134Z","event":"reasoning_trace","trace_id":"v8_trace_v7iw6q","span_id":"sp_8d5da7fa5a4e","agent":"mf-tester","thought":"Celestial persistence test v7iw6q.","resolution":"verified","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"64175075-d577-4316-a000-6f1471397587","timestamp":"2026-04-11T15:25:59.135Z","event":"span_completed","trace_id":"v8_trace_v7iw6q","span_id":"sp_8d5da7fa5a4e","status":"success"}
+{"id":"c3dcbe29-b557-4ebe-a943-6fac4d386c86","timestamp":"2026-04-11T15:30:34.347Z","event":"span_started","trace_id":"v8_trace_16x5wy","span_id":"sp_71c37487e73d","parent_span_id":null,"span_name":"v8_span_16x5wy"}
+{"id":"8aa00dc7-db48-4805-808c-a86fdc97f536","timestamp":"2026-04-11T15:30:34.356Z","event":"reasoning_trace","trace_id":"v8_trace_16x5wy","span_id":"sp_71c37487e73d","agent":"mf-tester","thought":"Celestial persistence test 16x5wy.","resolution":"verified","entropy":0,"is_stagnant":false,"drift_score":0.055}
+{"id":"42d507c4-6ded-47cf-a177-456610e0bc5a","timestamp":"2026-04-11T15:30:34.357Z","event":"span_completed","trace_id":"v8_trace_16x5wy","span_id":"sp_71c37487e73d","status":"success"}

package/.mindforge/mirrors/mirror-sre-776a1cf9/.planning/HANDOFF.json

@@ -0,0 +1,8 @@
+{
+  "_warning": "DO NOT ADD SECRETS OR SENSITIVE DATA TO THIS FILE. IT IS SYNCED ACROSS SESSIONS.",
+  "schema_type": "HANDOFF",
+  "schema_version": "2.0.0",
+  "handoffs": [],
+  "current_context": "",
+  "last_updated": "2026-03-25T00:00:00Z"
+}

package/.mindforge/mirrors/mirror-sre-776a1cf9/.planning/PROJECT.md

@@ -0,0 +1,33 @@
+# [Project Name]
+
+> One sentence describing what this project does and for whom.
+
+## Status
+🚧 In development — Phase 0 (not started)
+
+## Problem statement
+[What pain does this solve? Be specific.]
+
+## Target users
+[Who uses this? Describe them precisely. Avoid "developers" — say "solo developers
+building production apps with Claude Code who want structured AI workflows."]
+
+## Tech stack
+| Layer      | Technology  | Version | Rationale                        |
+|------------|-------------|---------|----------------------------------|
+|            |             |         |                                  |
+
+## v1 Scope — IN
+- [ ] [Feature 1]
+- [ ] [Feature 2]
+
+## v1 Scope — OUT (explicitly excluded)
+- [Item 1] — reason: [why not v1]
+- [Item 2] — reason: [why not v1]
+
+## Success criteria
+[How will you know v1 is done? Be specific and measurable.]
+
+## Key constraints
+- [Constraint 1]
+- [Constraint 2]

package/.mindforge/mirrors/mirror-sre-776a1cf9/.planning/RELEASE-CHECKLIST.md

@@ -0,0 +1,68 @@
+# MindForge v1.0.0 — Release Checklist
+
+Use this file to record verification results for the 50-point production
+readiness checklist in `.mindforge/production/production-checklist.md`.
+
+## Metadata
+- Target version: v1.0.0
+- Release date: 2026-03-22
+- Release manager: [name]
+
+## Verification log
+| Item | Result | Verified by | Date | Notes |
+|---|---|---|---|---|
+| A01 |  |  |  |  |
+| A02 |  |  |  |  |
+| A03 |  |  |  |  |
+| A04 |  |  |  |  |
+| A05 |  |  |  |  |
+| A06 |  |  |  |  |
+| A07 |  |  |  |  |
+| A08 |  |  |  |  |
+| A09 |  |  |  |  |
+| A10 |  |  |  |  |
+| B01 |  |  |  |  |
+| B02 |  |  |  |  |
+| B03 |  |  |  |  |
+| B04 |  |  |  |  |
+| B05 |  |  |  |  |
+| B06 |  |  |  |  |
+| B07 |  |  |  |  |
+| B08 |  |  |  |  |
+| B09 |  |  |  |  |
+| B10 |  |  |  |  |
+| C01 |  |  |  |  |
+| C02 |  |  |  |  |
+| C03 |  |  |  |  |
+| C04 |  |  |  |  |
+| C05 |  |  |  |  |
+| C06 |  |  |  |  |
+| C07 |  |  |  |  |
+| C08 |  |  |  |  |
+| C09 |  |  |  |  |
+| C10 |  |  |  |  |
+| D01 |  |  |  |  |
+| D02 |  |  |  |  |
+| D03 |  |  |  |  |
+| D04 |  |  |  |  |
+| D05 |  |  |  |  |
+| D06 |  |  |  |  |
+| D07 |  |  |  |  |
+| D08 |  |  |  |  |
+| D09 |  |  |  |  |
+| D10 |  |  |  |  |
+| E01 |  |  |  |  |
+| E02 |  |  |  |  |
+| E03 |  |  |  |  |
+| E04 |  |  |  |  |
+| E05 |  |  |  |  |
+| E06 |  |  |  |  |
+| E07 |  |  |  |  |
+| E08 |  |  |  |  |
+| E09 |  |  |  |  |
+| E10 |  |  |  |  |
+| F01 |  |  |  |  |
+| F02 |  |  |  |  |
+| F03 |  |  |  |  |
+| F04 |  |  |  |  |
+| F05 |  |  |  |  |

package/.mindforge/mirrors/mirror-sre-776a1cf9/.planning/REQUIREMENTS.md

@@ -0,0 +1,23 @@
+# Core Requirements Registry (MindForge v6.5.0)
+
+This registry contains the canonical requirements that all autonomous reasoning waves must align with. This file is parsed by the `ReasonSourceAligner` (RSA).
+
+## [REQ-001] Component Isolation
+
+All newly created engine components must be contained within the `bin/engine/` directory and follow a single-responsibility modular architecture.
+
+## [REQ-002] Intelligence-Drift Coupling (IDC)
+
+The system must proactively detect "logic loops" or reasoning stagnation and trigger compute resource upgrades (MIR tier elevation) when drift exceeds a critical threshold.
+
+## [REQ-003] Context Entropy Guard (CEG)
+
+The framework must actively suppress redundant reasoning thoughts (>85% similarity) and compress stagnant loops into high-density semantic digests before session handoff.
+
+## [REQ-004] Reason-Source Alignment (RSA)
+
+Every reasoning thought in an autonomous wave must be traceable back to at least one REQUIREMENT ID. Waves with <60% alignment must be flagged for refocusing.
+
+## [REQ-005] Zero-Trust Verification
+
+Implementation plans must include a verification phase with automated shell scripts or browser-based UAT to confirm success before claiming feature completion.

package/.mindforge/mirrors/mirror-sre-776a1cf9/.planning/ROADMAP.md

@@ -0,0 +1,12 @@
+# MindForge Roadmap
+
+### Phase 1: MindForge Enterprise Stabilization
+
+**Goal:** [To be planned]
+**Requirements**: TBD
+**Depends on:** Phase 0
+**Plans:** 0 plans
+
+Plans:
+
+- [ ] TBD (run /mindforge-plan-phase 1 to break down)

package/.mindforge/mirrors/mirror-sre-776a1cf9/.planning/ROI.jsonl

@@ -0,0 +1,2 @@
+{"timestamp":"2026-03-27T20:44:37.178Z","planId":"test-plan-001","task":"Implement Auth","model":"claude-3-5-sonnet","costTier":"medium","inputTokens":1000,"outputTokens":500,"durationMs":1200,"status":"completed","goalAchieved":1,"estimatedCostUSD":0.010499999999999999}
+{"timestamp":"2026-03-27T20:54:21.126Z","planId":"test-plan-001","task":"Implement Auth","model":"claude-3-5-sonnet","costTier":"medium","inputTokens":1000,"outputTokens":500,"durationMs":1200,"status":"completed","goalAchieved":1,"estimatedCostUSD":0.010499999999999999}

package/.mindforge/mirrors/mirror-sre-776a1cf9/.planning/STATE.md

@@ -0,0 +1,31 @@
+# MindForge — Project State
+
+## Status
+🔴 Not started
+
+## IMPORTANT
+HANDOFF.json is committed to git. Never write secrets or credentials into it.
+Write "see .env" or "stored in secrets manager" if a note needs to reference credentials.
+
+
+## Current phase
+None
+
+## Last completed task
+None — project not yet initialised.
+
+## Next action
+Run `/mindforge:init-project` to initialise this project.
+
+## Decisions made
+None yet.
+
+## Active blockers
+None.
+
+## Context for next session
+Fresh MindForge install. No project has been initialised yet.
+Start by running `/mindforge:init-project`.
+
+## Last updated
+[ISO 8601 timestamp on first use]

package/.mindforge/mirrors/mirror-sre-776a1cf9/.planning/approvals/.gitkeep

@@ -0,0 +1 @@
+

package/.mindforge/mirrors/mirror-sre-776a1cf9/.planning/archive/.gitkeep

@@ -0,0 +1 @@
+