mindsystem-cc 4.2.0 → 4.3.0

package/commands/ms/help.md

@@ -136,6 +136,7 @@ Define requirements and create roadmap with phases.
 - Creates `.planning/ROADMAP.md` (phase breakdown)
 - Creates `.planning/STATE.md` (project memory)
 - Creates `.planning/phases/` directories
+- Evaluates subsystem coverage — proposes new subsystems if phases introduce unmatched domains
 
 Usage: `/ms:create-roadmap`
 

package/commands/ms/map-codebase.md

@@ -58,9 +58,8 @@ Check for .planning/STATE.md - loads context if project already initialized
    - Agent 4: concerns focus → writes CONCERNS.md
 4. Wait for agents to complete, collect confirmations (NOT document contents)
 5. Verify all 7 documents exist with line counts
-6. Commit codebase map
+6. Update last command and commit codebase map (together with STATE.md)
 7. Offer next steps (adapts: /ms:new-project if no PROJECT.md, /ms:doctor if PROJECT.md exists)
-8. **Update last command:** `ms-tools set-last-command "ms:map-codebase $ARGUMENTS"`
 </process>
 
 <success_criteria>

package/commands/ms/new-milestone.md

@@ -254,14 +254,12 @@ Milestone name: $ARGUMENTS (optional — will emerge during discovery if not pro
 
     Keep Accumulated Context (decisions, blockers) from previous milestone.
 
-17. **Git commit:**
+17. **Update state and commit:**
 
     ```bash
+    ms-tools set-last-command "ms:new-milestone $ARGUMENTS"
     git add .planning/PROJECT.md .planning/STATE.md .planning/MILESTONE-CONTEXT.md
-    git commit -m "$(cat <<'EOF'
-    docs: start milestone [Name]
-    EOF
-    )"
+    git commit -m "docs: start milestone [Name]"
     ```
 
 18. **Calculate next phase number:**
@@ -302,8 +300,6 @@ Milestone name: $ARGUMENTS (optional — will emerge during discovery if not pro
     ---
     ```
 
-20. **Update last command:** `ms-tools set-last-command "ms:new-milestone $ARGUMENTS"`
-
 </process>
 
 <success_criteria>

package/commands/ms/new-project.md

@@ -195,9 +195,11 @@ These values are used throughout the system for consistent categorization of sum
 
 <step name="commit">
 
-**First run:**
+**First run — update state and commit:**
 ```bash
+ms-tools set-last-command "ms:new-project"
 git add .planning/PROJECT.md .planning/config.json
+[ -f .planning/STATE.md ] && git add .planning/STATE.md
 git commit -m "$(cat <<'EOF'
 docs: initialize [project-name]
 
@@ -208,9 +210,10 @@ EOF
 )"
 ```
 
-**Update mode:**
+**Update mode — update state and commit:**
 ```bash
-git add .planning/PROJECT.md .planning/config.json
+ms-tools set-last-command "ms:new-project"
+git add .planning/PROJECT.md .planning/config.json .planning/STATE.md
 git commit -m "$(cat <<'EOF'
 docs: update [project-name] project context
 
@@ -268,12 +271,6 @@ Project updated:
 
 </step>
 
-<step name="update_last_command">
-```bash
-ms-tools set-last-command "ms:new-project"
-```
-</step>
-
 </process>
 
 <output>

package/commands/ms/progress.md

@@ -11,8 +11,6 @@ allowed-tools:
 
 <objective>
 Check project progress, summarize recent work and what's ahead, then intelligently route to the next action - either executing an existing plan or creating the next one.
-
-Provides situational awareness before continuing work.
 </objective>
 
 
@@ -77,7 +75,7 @@ Compare versions. Store result for the report step. If npm fails or versions mat
 - Read `.planning/STATE.md` for living memory (position, decisions, issues)
 - Read `.planning/ROADMAP.md` for phase structure and objectives
 - Read `.planning/PROJECT.md` for current state (What This Is, Core Value, Requirements)
-  </step>
+</step>
 
 <step name="recent">
 **Gather recent work context:**
@@ -85,7 +83,7 @@ Compare versions. Store result for the report step. If npm fails or versions mat
 - Find the 2-3 most recent SUMMARY.md files
 - Extract from each: what was accomplished, key decisions, any issues logged
 - This shows "what we've been working on"
-  </step>
+</step>
 
 <step name="position">
 **Parse current position:**
@@ -97,7 +95,7 @@ Compare versions. Store result for the report step. If npm fails or versions mat
 - Check for DESIGN.md: For UI-heavy phases, check if `{phase}-DESIGN.md` exists in phase directory
 - Count pending todos: `ls .planning/todos/*.md 2>/dev/null | wc -l`
 - Check for active debug sessions: `ls .planning/debug/*.md 2>/dev/null | grep -v resolved | wc -l`
-  </step>
+</step>
 
 <step name="report">
 **Present rich status report:**
@@ -205,48 +203,7 @@ Read its `<objective>` section.
 
 **Route B: Phase needs planning**
 
-Check if `{phase}-CONTEXT.md` exists in phase directory.
-
-**If CONTEXT.md exists:**
-
-```
----
-
-## ▶ Next Up
-
-**Phase {N}: {Name}** — {Goal from ROADMAP.md}
-<sub>✓ Context gathered, ready to plan</sub>
-
-`/ms:plan-phase {phase-number}`
-
-<sub>`/clear` first → fresh context window</sub>
-
----
-```
-
-**If CONTEXT.md does NOT exist:**
-
-```
----
-
-## ▶ Next Up
-
-**Phase {N}: {Name}** — {Goal from ROADMAP.md}
-
-`/ms:plan-phase {phase}`
-
-<sub>`/clear` first → fresh context window</sub>
-
----
-
-**Also available:**
-- `/ms:discuss-phase {phase}` — gather context first
-- `/ms:design-phase {phase}` — create UI/UX specifications
-- `/ms:research-phase {phase}` — investigate unknowns
-- `/ms:discuss-phase {phase}` — gather context and validate assumptions
-
----
-```
+Read `~/.claude/mindsystem/references/routing/next-phase-routing.md` and follow its instructions for the **current** phase (not next phase) to present "Next Up" with pre-work context from ROADMAP.md flags.
 
 ---
 
@@ -299,22 +256,11 @@ A milestone was completed and archived. Read `~/.claude/mindsystem/references/ro
 
 </step>
 
-<step name="edge_cases">
-**Handle edge cases:**
-
-- Phase complete but next phase not planned → offer `/ms:plan-phase [next]`
-- All work complete → offer milestone completion
-- Blockers present → highlight before offering to continue
-  </step>
-
 </process>
 
 <success_criteria>
 
-- [ ] Rich context provided (recent work, decisions, issues)
-- [ ] Current position clear with visual progress
-- [ ] What's next clearly explained
-- [ ] Smart routing: /ms:execute-phase if plan exists, /ms:plan-phase if not
-- [ ] User confirms before any action
-- [ ] Seamless handoff to appropriate mindsystem command
-      </success_criteria>
+- [ ] Report includes recent work, decisions, blockers, and pending counts
+- [ ] Smart routing: /ms:execute-phase if plan exists, ROADMAP pre-work flags consulted if not
+- [ ] Presents copy-paste command — never auto-executes the routed action
+</success_criteria>

package/commands/ms/remove-phase.md

@@ -259,14 +259,13 @@ Update any internal references to reflect new numbering.
 </step>
 
 <step name="commit">
-Stage and commit the removal:
+**Update state and commit:**
 
 ```bash
+ms-tools set-last-command "ms:remove-phase $ARGUMENTS"
 git add .planning/
 git commit -m "chore: remove phase {target} ({original-phase-name})"
 ```
-
-The commit message preserves the historical record of what was removed.
 </step>
 
 <step name="completion">
@@ -297,12 +296,6 @@ Would you like to:
 ```
 </step>
 
-<step name="update_last_command">
-```bash
-ms-tools set-last-command "ms:remove-phase $ARGUMENTS"
-```
-</step>
-
 </process>
 
 <anti_patterns>

package/commands/ms/research-milestone.md

@@ -285,10 +285,11 @@ Write Executive Summary (2-3 paragraphs) synthesizing all findings.
 
 Merge overlapping findings. Resolve conflicts by preferring higher-confidence sources.
 
-## 7. Present Results and Commit
+## 7. Update state and commit:
 
 ```bash
-git add .planning/MILESTONE-RESEARCH.md
+ms-tools set-last-command "ms:research-milestone"
+git add .planning/MILESTONE-RESEARCH.md .planning/STATE.md
 git commit -m "$(cat <<'EOF'
 docs: complete milestone research
 
@@ -320,12 +321,6 @@ Key findings:
 ---
 ```
 
-## 8. Update Last Command
-
-```bash
-ms-tools set-last-command "ms:research-milestone"
-```
-
 </process>
 
 <success_criteria>

package/commands/ms/research-phase.md

@@ -40,7 +40,7 @@ Use `find-phase` output from context. **If phase not found (dir is null):** Erro
 ## 2. Check Existing Research
 
 ```bash
-ls .planning/phases/${PHASE}-*/RESEARCH.md 2>/dev/null
+ls ${PHASE_DIR}/*RESEARCH.md 2>/dev/null
 ```
 
 **If exists:** Offer: 1) Update research, 2) View existing, 3) Skip. Wait for response.
@@ -61,9 +61,9 @@ grep -A20 "Phase ${PHASE}:" .planning/ROADMAP.md
 # Requirements
 cat .planning/REQUIREMENTS.md 2>/dev/null
 
-# Phase-specific context and design
-cat .planning/phases/${PHASE}-*/${PHASE}-CONTEXT.md 2>/dev/null
-cat .planning/phases/${PHASE}-*/${PHASE}-DESIGN.md 2>/dev/null
+# Phase-specific context and design (PHASE_DIR from find-phase in <context>)
+cat ${PHASE_DIR}/*-CONTEXT.md 2>/dev/null
+cat ${PHASE_DIR}/*-DESIGN.md 2>/dev/null
 
 # Locked decisions
 grep -A30 "### Decisions Made" .planning/STATE.md 2>/dev/null
@@ -300,35 +300,35 @@ After all 3 agents return, read their structured outputs. Map findings to RESEAR
 
 Write RESEARCH.md to `.planning/phases/{phase}-{slug}/{phase}-RESEARCH.md` using the standard template structure (semantic XML tags: `<research_summary>`, `<standard_stack>`, `<architecture_patterns>`, `<dont_hand_roll>`, `<common_pitfalls>`, `<code_examples>`, `<sota_updates>`, `<open_questions>`, `<sources>`, `<metadata>`).
 
-## 7. Commit and Present
+## 7. Update state and commit:
 
 ```bash
-git add .planning/phases/${PHASE}-*/*-RESEARCH.md
+ms-tools set-last-command "ms:research-phase $ARGUMENTS"
+git add ${PHASE_DIR}/*-RESEARCH.md .planning/STATE.md
 git commit -m "docs: complete research for phase ${PHASE}"
 ```
 
-Display research summary. Read `~/.claude/mindsystem/references/prework-status.md` to show what's done vs still needed for this phase.
+Display research summary.
 
 **Post-synthesis routing:**
 
 Scan the synthesized RESEARCH.md for LOW confidence sections and significant open questions.
 
-If all sections HIGH/MEDIUM confidence with no major gaps, use AskUserQuestion:
-1. Proceed to planning
-2. Dig deeper into specific area
-3. Review full research
+If all sections HIGH/MEDIUM confidence with no major gaps:
+
+Read `~/.claude/mindsystem/references/prework-status.md` and present what's done vs still needed for this phase.
+
+Also offer:
+- **Dig deeper** — into specific area
+- **Review full research** — display RESEARCH.md
 
 If any section has LOW confidence or significant open questions, flag the weak areas explicitly, then use AskUserQuestion:
 1. Dig deeper into [specific LOW area] — re-run targeted agent
 2. Try different research mode (e.g., ecosystem -> implementation)
-3. Proceed to planning with caveats noted
+3. Proceed with caveats noted
 4. Review full research
 
-## 8. Update Last Command
-
-```bash
-ms-tools set-last-command "ms:research-phase $ARGUMENTS"
-```
+When user selects "Proceed with caveats noted", read `~/.claude/mindsystem/references/prework-status.md` and present what's done vs still needed for this phase.
 
 </process>
 

package/commands/ms/verify-work.md

@@ -31,6 +31,11 @@ Phase: $ARGUMENTS (optional)
 - If provided: Test specific phase (e.g., "4")
 - If not provided: Check for active sessions or prompt for phase
 
+Resolve phase directory:
+```bash
+ms-tools find-phase "$ARGUMENTS"
+```
+
 @.planning/STATE.md
 @.planning/ROADMAP.md
 @.planning/PROJECT.md
@@ -49,9 +54,10 @@ Phase: $ARGUMENTS (optional)
    - Present tests via AskUserQuestion (Pass / Can't test / Skip / Other)
    - Process results — UAT.md updates happen via `ms-tools uat-update` (auto-recalculates progress)
    - **For each issue found:**
-     - Lightweight investigation (2-3 tool calls)
+     - On first issue: load knowledge files (match phase subsystem against `.planning/knowledge/*.md`)
+     - Lightweight investigation (2-3 tool calls, informed by knowledge)
      - If simple: Fix inline, commit (amend previous fix commit on retry when HEAD matches fix_commit), ask for re-test
-     - If complex: Spawn ms-verify-fixer subagent
+     - If complex: Spawn ms-verify-fixer subagent (with knowledge context in prompt)
      - 2 retries on failed re-test, then offer options
 8. **On batch transition:**
    - If new mock_type: Revert old mocks (`git checkout -- <mocked_files>`), apply new ones

package/mindsystem/references/browser-verification.md

@@ -32,7 +32,7 @@ Store the result as `{dev_url}`.
 If `HAS_STATE`:
 1. Open app headless at `{dev_url}`
 2. Check current URL — if redirected to a login/auth path, auth has expired
-3. If still on app pages: auth valid, proceed to Spawn
+3. If still on app pages: auth valid, proceed to Derive Browser Checklist
 
 If `NO_STATE` or auth expired:
 1. Close headless browser
@@ -47,30 +47,97 @@ If `NO_STATE` or auth expired:
    ```
 5. If user skips: proceed to code_review, skip browser verification
 
+## Derive Browser Checklist
+
+Transform SUMMARY.md accomplishments into a structured checklist for the browser verifier.
+
+**Step 1: Read summaries**
+
+Read all `*-SUMMARY.md` files from the phase directory.
+
+**Step 2: Extract per-summary**
+
+For each SUMMARY, extract:
+- **Accomplishments** section
+- **mock_hints** frontmatter (if present) — specifically `external_data` entries
+- **key-files** frontmatter (if present) — for route inference
+
+**Step 3: Derive checklist items**
+
+For each user-observable accomplishment, derive:
+- `name`: brief description of what to verify
+- `route`: URL path (infer from key-files paths, routing config, or component names)
+- `expected`: what should be visible on screen (be specific — "table with columns X, Y, Z", not "data displays")
+- `interaction`: optional action + expected result (e.g., "click Add button → modal opens with form fields A, B, C")
+- `needs_backend_data`: true/false (from mock_hints `external_data` entries)
+
+**Step 4: Filter**
+
+Include: UI renders, navigation, forms, data display, visual states, user interactions.
+Exclude: refactors, type changes, API internals, test files, build config, non-visual changes.
+
+**Step 5: Group and format**
+
+Group items by route for efficient navigation. Format as a numbered list:
+
+```
+1. **{name}**
+   Route: {route}
+   Expected: {expected}
+   Interaction: {interaction or "none"}
+   Needs backend data: {yes/no}
+
+2. **{name}**
+   ...
+```
+
 ## Spawn
 
-Spawn the browser verifier agent after auth is established:
+Spawn the browser verifier agent after auth is established and checklist is derived:
 
 ```
 Task(
   prompt="Run browser verification for phase {phase_number}.
 
 Phase directory: {phase_dir}
-Phase goal: {phase_goal}
-VERIFICATION.md: {verification_path}
 Dev URL: {dev_url}
 Auth state: .agent-browser-state.json
 Screenshots directory: {phase_dir}/screenshots
 
-Read VERIFICATION.md for observable truths. Test browser-testable ones.
-Save all screenshots to {phase_dir}/screenshots/.
-Fix issues inline. Return structured report.",
+## Browser Checklist
+
+{derived_checklist}
+
+## Backend Context
+
+{summary of which items need real backend data — from mock_hints external_data entries.
+Items needing backend data may show empty states or errors — mark as ENVIRONMENT_BLOCKED, not ISSUE.}
+
+Verify each checklist item. Save all screenshots to {phase_dir}/screenshots/.
+Fix trivial issues inline. Return structured report.",
   subagent_type="ms-browser-verifier"
 )
 ```
 
-**After verifier returns:**
+## Post-Verifier Handling
+
+Route based on the report's **Status** field:
+
+**`environment_blocked`:**
+Surface the blocker description and screenshot evidence to the user. Use AskUserQuestion:
+- header: "Browser verification blocked"
+- question: "The browser verifier hit an environment issue: {blocker description}. How to proceed?"
+- options: ["Re-run after fixing environment", "Skip browser verification"]
+
+**`has_fixes`:**
+Report: "Browser verification: {N} fixes applied, {M} issues found"
+Include the Fixes Applied section in the consolidator prompt (step `consolidate_knowledge`) so browser-discovered patterns are captured in knowledge files.
+
+**`has_issues`:**
+Report: "Browser verification: {N} issues found (see screenshots in {phase_dir}/screenshots/)"
+Note issues for verify-work — these are candidates for manual UAT.
 
-If fixes were made, include the report summary in the consolidator prompt (step `consolidate_knowledge`) so browser-discovered patterns are captured in knowledge files.
+**`all_passed`:**
+Report: "Browser verification: all {N} items passed"
 
 </browser_verification>

package/mindsystem/references/prework-status.md

@@ -22,7 +22,8 @@ Extract:
 Check what context files already exist:
 
 ```bash
-PHASE_DIR=$(ls -d .planning/phases/${PHASE}-* 2>/dev/null | head -1)
+ms-tools find-phase "${PHASE}"
+# Extract PHASE_DIR from the `dir` field of the JSON output
 [ -f "$PHASE_DIR"/*-CONTEXT.md ] && echo "CONTEXT_EXISTS"
 [ -f "$PHASE_DIR"/*-DESIGN.md ] && echo "DESIGN_EXISTS"
 [ -f "$PHASE_DIR"/*-RESEARCH.md ] && echo "RESEARCH_EXISTS"

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

@@ -1,17 +1,17 @@
 # Next Phase Routing
 
-Reference for presenting "Next Up" guidance when moving to the next phase. Used by execute-phase and verify-work.
+Reference for presenting "Next Up" guidance for a phase. Used by progress (current phase), execute-phase (next phase), and verify-work (next phase).
 
 ## Purpose
 
-Help user decide between Discuss/Research/Design/Plan for the NEXT phase without referencing external files.
+Help user decide between Discuss/Research/Design/Plan for a target phase using ROADMAP.md pre-work flags.
 
 ## Information to Extract
 
-From ROADMAP.md, get the next phase details:
+From ROADMAP.md, get the target phase details:
 
 ```bash
-grep -A 25 "### Phase ${NEXT_PHASE}:" .planning/ROADMAP.md
+grep -A 25 "### Phase ${TARGET_PHASE}:" .planning/ROADMAP.md
 ```
 
 Extract:
@@ -26,7 +26,8 @@ Extract:
 Check for existing context files:
 
 ```bash
-PHASE_DIR=$(ls -d .planning/phases/${NEXT_PHASE}-* 2>/dev/null | head -1)
+ms-tools find-phase "${TARGET_PHASE}"
+# Extract PHASE_DIR from the `dir` field of the JSON output
 [ -f "$PHASE_DIR"/*-CONTEXT.md ] && echo "CONTEXT_EXISTS"
 [ -f "$PHASE_DIR"/*-DESIGN.md ] && echo "DESIGN_EXISTS"
 [ -f "$PHASE_DIR"/*-RESEARCH.md ] && echo "RESEARCH_EXISTS"

package/mindsystem/workflows/adhoc.md

@@ -132,7 +132,12 @@ Present a summary to the user:
 - Key files affected
 - Must-Haves checklist
 
-Allow the user to approve, request edits, or abort. If edits requested, apply them directly to the plan file.
+**AskUserQuestion** with options:
+- Approve and execute
+- Request edits (let me describe)
+- Abort
+
+If edits requested, apply them directly to the plan file, then re-present and ask again. If aborted, clean up `${exec_dir}` and stop.
 </step>
 
 <step name="spawn_executor">
@@ -202,8 +207,14 @@ The consolidator reads `adhoc-01-SUMMARY.md`, extracts knowledge (key-decisions,
 
 **Finalize todo (when detected):** Follow the **Finalization**, **Commit Message Suffix**, and **Report Additions** sections from the loaded todo reference.
 
-**Commit knowledge updates:**
+**Update STATE.md** "Recent Adhoc Work" section:
+- Find or create "### Recent Adhoc Work" under "## Accumulated Context"
+- Add entry at top: `- [YYYY-MM-DD]: [description] ({exec_dir}/adhoc-01-SUMMARY.md)`
+- Keep last 5 entries (remove older ones from list)
+
+**Update state and commit:**
 ```bash
+ms-tools set-last-command "ms:adhoc ${slug}"
 git add .planning/knowledge/*.md "${exec_dir}/adhoc-01-SUMMARY.md" .planning/STATE.md
 # Only include patch if it was generated
 [ -f "${exec_dir}/adhoc-01-changes.patch" ] && git add "${exec_dir}/adhoc-01-changes.patch"
@@ -215,16 +226,6 @@ EOF
 )"
 ```
 
-**Update STATE.md** "Recent Adhoc Work" section:
-- Find or create "### Recent Adhoc Work" under "## Accumulated Context"
-- Add entry at top: `- [YYYY-MM-DD]: [description] ({exec_dir}/adhoc-01-SUMMARY.md)`
-- Keep last 5 entries (remove older ones from list)
-
-**Set last command:**
-```bash
-ms-tools set-last-command "ms:adhoc $ARGUMENTS"
-```
-
 **Report completion:**
 ```
 Adhoc work complete: [description]
@@ -242,9 +243,7 @@ Artifacts:
 ```
 ---
 
-Continue with current work or check project status:
-- `/ms:progress` — see project status
-- `/ms:execute-phase` — continue phase execution
+Check `/ms:progress` to see project status and next steps.
 ```
 </step>
 

package/mindsystem/workflows/compound.md

@@ -19,7 +19,7 @@ fi
 ```
 
 **Mode detection:**
-- If `$ARGUMENTS` empty: **description mode** — deduce from conversation context. Summarize what was discussed/changed in the current session.
+- If `$ARGUMENTS` empty: **conversation mode** — reflect on current conversation to build change summary. No Explore agents needed.
 - If matches git SHA pattern (7-40 hex chars), contains `..`, or starts with `HEAD`: **git mode**
 - If matches existing file path (`test -e "$ARGUMENTS"`): **file mode**
 - Otherwise: **description mode** — treat `$ARGUMENTS` as free-text description
@@ -42,7 +42,25 @@ git log --oneline -5 -- <path>
 ```
 Capture file path for passing to compounder.
 
-**Description mode (including no-args):**
+**Conversation mode (no args):**
+Build change summary from conversation context and git data.
+
+1. **Reflect on conversation:** Summarize what was discussed, changed, and decided
+   in the current session. Include rationale and key decisions.
+2. **Supplement with git data:**
+   ```bash
+   git diff --stat          # uncommitted changes
+   git log --stat -5        # recent commits with file lists
+   ```
+3. **Thin-context guard:** If conversation reflection produces little substance
+   (e.g., fresh context, unrelated discussion), use AskUserQuestion:
+   - "Describe what changed" — enter free-text, then proceed as description mode (spawn Explore agents)
+   - "Compound recent commits" — use git log output as change context
+   - "Cancel" — abort
+4. **Combine into change summary:** Merge conversation insights with git file paths
+   into a concise summary covering: what changed, why, which files, key decisions.
+
+**Description mode (free-text argument provided):**
 Spawn 1 Explore agent to find relevant code changes. If changes span multiple unrelated areas, spawn a second agent for the additional area. They return:
 - Which files changed or are relevant
 - Which subsystems are likely affected
@@ -60,7 +78,7 @@ ms-tools config-get subsystems
 
 **Git/file mode:** Match file paths from diff stats against subsystem names via keyword matching.
 
-**Description mode:** Use Explore agent findings for subsystem matching.
+**Description/conversation mode:** Use Explore agent findings or conversation summary for subsystem matching.
 
 **Detect potential new subsystems:** Changes in file areas that don't match any existing subsystem.
 
@@ -82,8 +100,8 @@ AskUserQuestion: "Compound knowledge for these subsystems?" with options:
 
 <step name="spawn_compounder">
 Spawn ms-compounder via Task tool with:
-- Input mode (`git`, `file`, or `description`)
-- Change reference (git ref/range, file path, or description + exploration findings)
+- Input mode (`git`, `file`, or `description` — conversation mode passes as `description`)
+- Change reference (git ref/range, file path, description + exploration findings, or conversation summary)
 - Confirmed affected subsystems list
 - Config.json subsystem vocabulary
 
@@ -91,26 +109,19 @@ Agent reads changes, reads affected knowledge files, writes updates, returns rep
 </step>
 
 <step name="finalize">
-**Update config.json** (if new subsystems were confirmed in step 4):
+**Update config.json** (if new subsystems were confirmed in confirm_with_user step):
 ```bash
 # Add new subsystem to config.json
 ms-tools config-set subsystems --append "new-subsystem"
 ```
 
-**Commit changes:**
+**Update state and commit:**
 ```bash
-git add .planning/knowledge/*.md
+ms-tools set-last-command "ms:compound $ARGUMENTS"
+git add .planning/knowledge/*.md .planning/STATE.md
 # Only add config.json if modified
 git add .planning/config.json 2>/dev/null
-git commit -m "$(cat <<'EOF'
-docs: compound knowledge from <description>
-EOF
-)"
-```
-
-**Set last command:**
-```bash
-ms-tools set-last-command "ms:compound $ARGUMENTS"
+git commit -m "docs: compound knowledge from <description>"
 ```
 
 **Report:** Subsystems updated, entries added/changed/removed, new subsystems created (if any).

package/mindsystem/workflows/define-requirements.md

@@ -258,7 +258,8 @@ If "adjust": Return to scope_categories or identify_gaps as appropriate.
 </step>
 
 <step name="git_commit">
-Commit requirements:
+
+**Update state and commit:**
 
 ```bash
 git add .planning/REQUIREMENTS.md