mindsystem-cc 3.17.1 → 3.18.0

package/agents/ms-debugger.md

@@ -615,7 +615,7 @@ The cost of insufficient verification: bug returns, user frustration, emergency
 **2. Library/framework behavior doesn't match expectations**
 - Using library correctly but it's not working
 - Documentation contradicts behavior
-- **Action:** Check official docs (Context7), GitHub issues
+- **Action:** Check official docs (`ms-lookup docs`), GitHub issues
 
 **3. Domain knowledge gaps**
 - Debugging auth: need to understand OAuth flow
@@ -657,7 +657,7 @@ The cost of insufficient verification: bug returns, user frustration, emergency
 - Include version: `"react 18 useEffect behavior"`
 - Add "github issue" for known bugs
 
-**Context7 MCP:**
+**`ms-lookup docs`:**
 - For API reference, library concepts, function signatures
 
 **GitHub Issues:**
@@ -687,7 +687,7 @@ Is this an error message I don't recognize?
 └─ NO ↓
 
 Is this library/framework behavior I don't understand?
-├─ YES → Check docs (Context7 or official docs)
+├─ YES → Check docs (`ms-lookup docs` or official docs)
 └─ NO ↓
 
 Is this code I/my team wrote?

package/agents/ms-researcher.md

@@ -59,9 +59,9 @@ Claude's training data is 6-18 months stale. Treat pre-existing knowledge as hyp
 - Wrong (Claude misremembered or hallucinated)
 
 **The discipline:**
-1. **Verify before asserting** - Don't state library capabilities without checking Context7 or official docs
+1. **Verify before asserting** - Don't state library capabilities without checking `ms-lookup docs` or official docs
 2. **Date your knowledge** - "As of my training" is a warning flag, not a confidence marker
-3. **Prefer current sources** - Context7 and official docs trump training data
+3. **Prefer current sources** - `ms-lookup docs` and official docs trump training data
 4. **Flag uncertainty** - LOW confidence when only training data supports a claim
 
 ## Honest Reporting
@@ -197,7 +197,7 @@ When researching "best library for X":
 
 The CLI is at `~/.claude/mindsystem/scripts/ms-lookup-wrapper.sh`.
 
-### Library Documentation (Context7)
+### Library Documentation
 
 ```bash
 ~/.claude/mindsystem/scripts/ms-lookup-wrapper.sh docs <library> "<query>"
@@ -213,7 +213,7 @@ Example:
 
 **Response format:** JSON with results array containing title, content, source_url, tokens.
 
-### Deep Research (Perplexity)
+### Deep Research
 
 ```bash
 ~/.claude/mindsystem/scripts/ms-lookup-wrapper.sh deep "<query>"
@@ -255,7 +255,7 @@ WebSearch("[technology] vs [alternative] {current_year}")
 
 **Always include current year** in queries for freshness.
 
-**Why WebSearch over Perplexity search:** Free with Max subscription. Perplexity search costs $5/1k queries with marginal quality improvement for discovery tasks.
+**Why WebSearch over `ms-lookup deep`:** WebSearch is free. `ms-lookup deep` costs money per query — reserve it for high-value questions, not discovery.
 
 ## Token Limit Strategy (for ms-lookup)
 
@@ -264,7 +264,7 @@ WebSearch("[technology] vs [alternative] {current_year}")
 **Rationale:**
 - The 50% rule: Research must complete before hitting 100k tokens
 - At 2000 tokens/query, you can make ~50 queries
-- Context7 returns results ranked by relevance — first 3-4 snippets are most important
+- `ms-lookup docs` returns results ranked by relevance — first 3-4 snippets are most important
 - Query flexibility > per-query comprehensiveness
 
 **When to increase (`--max-tokens 4000-6000`):**
@@ -296,15 +296,15 @@ WebSearch("[technology] vs [alternative] {current_year}")
 
 | Level | Sources | Use |
 |-------|---------|-----|
-| HIGH | Context7, official documentation, official releases | State as fact |
+| HIGH | `ms-lookup docs`, official documentation, official releases | State as fact |
 | MEDIUM | WebSearch verified with official source, multiple credible sources agree | State with attribution |
 | LOW | WebSearch only, single source, unverified | Flag as needing validation |
 
 ## Source Prioritization
 
-**1. Context7 (highest priority)**
-- Current, authoritative documentation
-- Library-specific, version-aware
+**1. `ms-lookup docs` (highest priority)**
+- Current, authoritative library documentation
+- Version-aware, sourced from official docs
 - Trust completely for API/feature questions
 
 **2. Official Documentation**
@@ -526,7 +526,7 @@ Based on research question, identify what needs investigating:
 
 For each domain, follow tool strategy in order:
 
-1. **Context7 First** - Resolve library, query topics
+1. **`ms-lookup docs` First** - Query library documentation
 2. **Official Docs** - WebFetch for gaps
 3. **WebSearch** - Ecosystem discovery with year
 4. **Verification** - Cross-reference all findings
@@ -626,7 +626,7 @@ When research cannot proceed:
 Research is complete when:
 
 - [ ] Research question answered with actionable findings
-- [ ] Source hierarchy followed (Context7 → Official → WebSearch)
+- [ ] Source hierarchy followed (`ms-lookup docs` → Official → WebSearch)
 - [ ] All findings have confidence levels
 - [ ] Verification protocol checklist passed
 - [ ] Output file(s) created in correct format
@@ -636,7 +636,7 @@ Research is complete when:
 Research quality indicators:
 
 - **Specific, not vague:** "Three.js r160 with @react-three/fiber 8.15" not "use Three.js"
-- **Verified, not assumed:** Findings cite Context7 or official docs
+- **Verified, not assumed:** Findings cite `ms-lookup docs` or official docs
 - **Honest about gaps:** LOW confidence items flagged, unknowns admitted
 - **Actionable:** Developer could start work based on this research
 - **Current:** Year included in searches, publication dates checked

package/commands/ms/complete-milestone.md

@@ -62,96 +62,89 @@ Output: Milestone archived (roadmap + requirements), PROJECT.md evolved, git tag
    ✓ Milestone audit passed. Proceeding with completion.
    ```
 
-1. **Verify readiness:**
-
-   - Check all phases in milestone have completed plans (SUMMARY.md exists)
-   - Present milestone scope and stats
-   - Wait for confirmation
-
-1.5. **Clean up raw artifacts:**
-
-   Delete remaining raw artifacts from phase directories. Knowledge files are already current from phase-level consolidation in execute-phase.
+1. **Verify readiness and gather stats:**
 
    ```bash
-   ~/.claude/mindsystem/scripts/cleanup-phase-artifacts.sh $PHASE_START $PHASE_END
+   ~/.claude/mindsystem/scripts/gather-milestone-stats.sh $PHASE_START $PHASE_END
    ```
 
-2. **Gather stats:**
-
-   - Count phases, plans, tasks
-   - Calculate git range, file changes, LOC
-   - Extract timeline from git log
-   - Present summary, confirm
+   - If NOT READY: stop and report incomplete plans
+   - If READY: present readiness + stats summary, proceed
 
-3. **Extract accomplishments:**
+2. **Extract accomplishments:**
 
    - Read all phase SUMMARY.md files in milestone range
    - Extract 4-6 key accomplishments
-   - Present for approval
 
-4. **Archive milestone:**
+3. **Create MILESTONES.md entry:**
+
+   - Create or update `.planning/MILESTONES.md` using `templates/milestone.md`
+   - Prepend new entry (reverse chronological order)
+
+4. **Update PROJECT.md:**
+
+   - Full evolution review (What This Is, Core Value, Requirements audit, Key Decisions, Context)
+   - Move all shipped requirements to Validated
+   - Update "Last updated" footer
+
+5. **Archive milestone:**
 
    - Create `.planning/milestones/v{{version}}/` directory
-   - Create `.planning/milestones/v{{version}}/ROADMAP.md`
-   - Extract full phase details from ROADMAP.md
-   - Fill milestone-archive.md template
-   - Update ROADMAP.md to one-line summary with link
+   - Create `.planning/milestones/v{{version}}/ROADMAP.md` from template
+   - Delete ROADMAP.md
 
-5. **Archive requirements:**
+6. **Archive requirements:**
 
    - Create `.planning/milestones/v{{version}}/REQUIREMENTS.md`
-   - Mark all v1 requirements as complete (checkboxes checked)
-   - Note requirement outcomes (validated, adjusted, dropped)
-   - Delete `.planning/REQUIREMENTS.md` (fresh one created for next milestone)
+   - Mark all requirements as complete with outcomes
+   - Delete `.planning/REQUIREMENTS.md`
+
+7. **Archive milestone files:**
 
-5.5. **Archive research:**
+   ```bash
+   ~/.claude/mindsystem/scripts/archive-milestone-files.sh v{{version}}
+   ```
 
-   - If `.planning/research/` exists, move to `.planning/milestones/v{{version}}/research/`
-   - Skip silently if no research directory exists
+8. **Archive and cleanup phases:**
+
+   ```bash
+   ~/.claude/mindsystem/scripts/archive-milestone-phases.sh $PHASE_START $PHASE_END v{{version}}
+   ```
 
-6. **Update PROJECT.md:**
+9. **Update STATE.md:**
 
-   - Add "Current State" section with shipped version
-   - Add "Next Milestone Goals" section
-   - Archive previous content in `<details>` (if v1.1+)
+    - Update project reference with current core value and next focus
+    - Reset current position for next milestone
 
-7. **Commit and tag:**
+10. **Commit and tag:**
 
-   - Stage: MILESTONES.md, PROJECT.md, ROADMAP.md, STATE.md, archive files
-   - Commit: `chore: archive v{{version}} milestone`
-   - Tag: `git tag -a v{{version}} -m "[milestone summary]"`
-   - Ask about pushing tag
+    - Stage: MILESTONES.md, PROJECT.md, STATE.md, archive files, deletions
+    - Commit: `chore: archive v{{version}} milestone`
+    - Tag: `git tag -a v{{version}} -m "[milestone summary]"`
+    - Ask about pushing tag
 
-8. **Offer next steps:**
-   - `/ms:new-milestone` — discover goals and update PROJECT.md (includes optional discovery mode)
+11. **Offer next steps:**
+    - `/ms:new-milestone` — discover goals and update PROJECT.md
 
-9. **Update last command**
-   - Update `.planning/STATE.md` Last Command field
-   - Format: `Last Command: ms:complete-milestone $ARGUMENTS | YYYY-MM-DD HH:MM`
+12. **Update last command:**
+    - Format: `Last Command: ms:complete-milestone $ARGUMENTS | YYYY-MM-DD HH:MM`
 
 </process>
 
 <success_criteria>
 
-- Raw artifacts cleaned from phase directories (CONTEXT, DESIGN, RESEARCH, SUMMARY, UAT, VERIFICATION, EXECUTION-ORDER)
+- PROJECT.md full evolution review completed (What This Is, Core Value, Requirements, Key Decisions, Context)
+- All shipped requirements moved to Validated in PROJECT.md
+- Key Decisions updated with outcomes
 - Milestone archived to `.planning/milestones/v{{version}}/ROADMAP.md`
 - Requirements archived to `.planning/milestones/v{{version}}/REQUIREMENTS.md`
-- Research archived to `.planning/milestones/v{{version}}/research/` (if existed)
 - `.planning/REQUIREMENTS.md` deleted (fresh for next milestone)
-- ROADMAP.md collapsed to one-line entry
-- PROJECT.md updated with current state
 - Git tag v{{version}} created
-- Commit successful
-- User knows next steps (/ms:new-milestone)
   </success_criteria>
 
 <critical_rules>
 
-- **Load workflow first:** Read complete-milestone.md before executing
 - **Verify completion:** All phases must have SUMMARY.md files
-- **User confirmation:** Wait for approval at verification gates
 - **Archive before deleting:** Always create archive files (ROADMAP, REQUIREMENTS) before updating/deleting originals
 - **One-line summary:** Collapsed milestone in ROADMAP.md should be single line with link
-- **Context efficiency:** Archive keeps ROADMAP.md and REQUIREMENTS.md constant size per milestone
-- **Fresh requirements:** Next milestone starts with `/ms:create-roadmap`, not reusing old file
   </critical_rules>

package/mindsystem/references/routing/next-phase-routing.md

@@ -66,9 +66,9 @@ ELSE:
 
 | Pre-work | Status | Topics/Focus |
 |----------|--------|--------------|
-| Research | Likely | {research topics} |
 | Discuss | Likely | {discuss topics} |
 | Design | Likely | {design focus} |
+| Research | Likely | {research topics} |
 
 {If all Unlikely: "No pre-work flagged — ready to plan directly."}
 

package/mindsystem/templates/milestone-archive.md

@@ -89,7 +89,7 @@ Plans:
 
 ---
 
-_For current project status, see .planning/ROADMAP.md_
+_For current project status, see .planning/PROJECT.md_
 
 ---
 
@@ -117,7 +117,7 @@ _For current project status, see .planning/ROADMAP.md_
 
 **After archiving:**
 
-- Update ROADMAP.md to collapse completed milestone in `<details>` tag
-- Update PROJECT.md to brownfield format with Current State section
+- Delete ROADMAP.md (fresh one created for next milestone via `/ms:create-roadmap`)
+- Update PROJECT.md with full evolution review
 - Continue phase numbering in next milestone (never restart at 01)
   </guidelines>

package/mindsystem/templates/research-subagent-prompt.md

@@ -22,7 +22,7 @@ Templates for the 3 parallel agents spawned by `/ms:research-phase`. The orchest
 ## Template 1: External Docs (ms-researcher)
 
 **Focus:** Library documentation, APIs, verified code examples
-**Tools emphasized:** ms-lookup docs (Context7), ms-lookup deep (Perplexity), WebSearch, WebFetch
+**Tools emphasized:** ms-lookup docs, ms-lookup deep, WebSearch, WebFetch
 **Returns:** Structured findings (not files)
 
 ```markdown
@@ -118,7 +118,7 @@ The agent's built-in `<what_to_scan>` section handles the systematic scan checkl
 ## Template 3: Best Practices (ms-researcher)
 
 **Focus:** Community consensus, pitfalls, SOTA
-**Tools emphasized:** ms-lookup deep (Perplexity), WebSearch
+**Tools emphasized:** ms-lookup deep, WebSearch
 **Returns:** Structured findings (not files)
 
 ```markdown

package/mindsystem/templates/research.md

@@ -72,7 +72,7 @@ src/
 **When to use:** [conditions]
 **Example:**
 ```typescript
-// [code example from Context7/official docs]
+// [code example from official docs]
 ```
 
 ### Pattern 2: [Pattern Name]
@@ -131,19 +131,19 @@ Verified patterns from official sources:
 
 ### [Common Operation 1]
 ```typescript
-// Source: [Context7/official docs URL]
+// Source: [official docs URL]
 [code]
 ```
 
 ### [Common Operation 2]
 ```typescript
-// Source: [Context7/official docs URL]
+// Source: [official docs URL]
 [code]
 ```
 
 ### [Common Operation 3]
 ```typescript
-// Source: [Context7/official docs URL]
+// Source: [official docs URL]
 [code]
 ```
 </code_examples>
@@ -185,7 +185,7 @@ Things that couldn't be fully resolved:
 ## Sources
 
 ### Primary (HIGH confidence)
-- [Context7 library ID] - [topics fetched]
+- [ms-lookup docs library] - [topics fetched]
 - [Official docs URL] - [what was checked]
 
 ### Secondary (MEDIUM confidence)
@@ -479,10 +479,10 @@ function useVehicleControls(rigidBodyRef) {
 - Pitfalls: Performance, physics, feel
 
 **Confidence breakdown:**
-- Standard stack: HIGH - verified with Context7, widely used
+- Standard stack: HIGH - verified with ms-lookup docs, widely used
 - Architecture: HIGH - from official examples
 - Pitfalls: HIGH - documented in discourse, verified in docs
-- Code examples: HIGH - from Context7/official sources
+- Code examples: HIGH - from ms-lookup docs/official sources
 
 **Research date:** 2026-01-20
 **Valid until:** 2026-02-20 (30 days - R3F ecosystem stable)