mindsystem-cc 3.22.1 → 4.0.0

package/commands/ms/compound.md

@@ -0,0 +1,64 @@
+---
+name: ms:compound
+description: Compound code changes into knowledge files
+argument-hint: "[commit, file path, or description]"
+allowed-tools:
+  - Read
+  - Write
+  - Bash
+  - Glob
+  - Grep
+  - Task
+  - AskUserQuestion
+---
+
+<objective>
+Compound code changes into the knowledge system. Use when work was done outside the Mindsystem pipeline and knowledge files need updating.
+
+Input modes:
+- **Git reference:** SHA, range (`HEAD~3..HEAD`), or any git ref
+- **File path:** Path to a changed file
+- **Description:** Free-text description of changes
+- **No args:** Infer from current conversation context
+</objective>
+
+<execution_context>
+@~/.claude/mindsystem/workflows/compound.md
+</execution_context>
+
+<process>
+
+<step name="parse_input">
+Determine input mode from $ARGUMENTS: git ref, file path, description, or no-args (conversation context).
+Validate active project: check `.planning/config.json` exists.
+</step>
+
+<step name="resolve_change_context">
+Gather lightweight change context. Git mode: diff stats. File mode: recent git log. Description mode: spawn Explore agents to find relevant changes.
+</step>
+
+<step name="determine_subsystems">
+Read config.json subsystems, match changes against subsystem names. Detect potential new subsystems.
+</step>
+
+<step name="confirm_with_user">
+Present affected subsystems and change summary. AskUserQuestion to confirm, adjust, or cancel.
+</step>
+
+<step name="spawn_compounder">
+Spawn ms-compounder with input mode, change reference, confirmed subsystems, and subsystem vocabulary.
+</step>
+
+<step name="finalize">
+Update config.json if new subsystems confirmed. Commit knowledge file changes. Set last command.
+</step>
+
+</process>
+
+<success_criteria>
+- [ ] No knowledge files or full diffs read in main context
+- [ ] User confirmed subsystem routing before compounder spawned
+- [ ] config.json updated if new subsystems detected and confirmed
+- [ ] Changes committed
+- [ ] Knowledge files updated for confirmed subsystems
+</success_criteria>

package/commands/ms/config.md

@@ -1,6 +1,6 @@
 ---
 name: ms:config
-description: Configure Mindsystem preferences — code reviewers, mockups, gitignore, git remote
+description: Configure Mindsystem preferences — code reviewers, mockups, gitignore, git remote, task tracker
 allowed-tools:
   - Read
   - Write
@@ -12,7 +12,7 @@ allowed-tools:
 
 Configure Mindsystem preferences for the current project.
 
-Manages code reviewer agents, mockup preferences, .gitignore patterns for `.planning/` artifacts, and git remote setup. Run anytime to reconfigure — idempotent.
+Manages code reviewer agents, mockup preferences, .gitignore patterns for `.planning/` artifacts, git remote setup, and task tracker integration. Run anytime to reconfigure — idempotent.
 
 </objective>
 
@@ -29,15 +29,10 @@ Manages code reviewer agents, mockup preferences, .gitignore patterns for `.plan
 # Check for PROJECT.md (tech stack detection)
 [ -f .planning/PROJECT.md ] && echo "HAS_PROJECT" || echo "NO_PROJECT"
 
-# Check for STACK.md (precise tech detection)
-[ -f .planning/codebase/STACK.md ] && echo "HAS_STACK" || echo "NO_STACK"
-
 # Check git remote
 git remote -v 2>/dev/null || echo "NO_REMOTE"
 ```
 
-**Run this before proceeding.**
-
 </step>
 
 <step name="git_remote">
@@ -67,21 +62,27 @@ If "Create with gh CLI":
 
 Show current code_review values from config.json (if loaded).
 
-**Default reviewers:** adhoc=`ms-code-simplifier`, phase=`ms-code-simplifier`, milestone=null
+**Default reviewers:** adhoc=`ms-code-simplifier`, phase=`ms-code-simplifier`, milestone=`ms-code-reviewer`
 
 Use AskUserQuestion:
 - header: "Code review"
 - question: "Which code reviewer configuration do you want?"
 - options:
-  - "Default (ms-code-simplifier)" — Generic reviewer for adhoc and phase tiers (Recommended)
+  - "Default" — ms-code-simplifier for adhoc/phase, ms-code-reviewer for milestone (Recommended)
   - "Skip code review" — Disable review for all tiers
   - "Custom" — I'll specify reviewers manually
 
-If "Custom": ask for each tier (adhoc, phase, milestone) individually.
+If "Custom": use AskUserQuestion for each tier (adhoc, phase, milestone) individually, offering available reviewer agents as options.
 
 If "Skip code review": set all three values to `"skip"`.
 
-Update config.json with selected values.
+Update config.json with selected values via jq:
+
+```bash
+jq '.code_review = {"adhoc": $a, "phase": $p, "milestone": $m}' \
+  --arg a "$ADHOC" --arg p "$PHASE" --arg m "$MILESTONE" \
+  .planning/config.json > .planning/config.tmp && mv .planning/config.tmp .planning/config.json
+```
 
 </step>
 
@@ -102,7 +103,12 @@ Use AskUserQuestion (multiSelect):
   - "Phase patch files (`.planning/phases/**/*.patch`)" — Large binary diffs, regeneratable
   - "Design mockups (`.planning/phases/**/*.html`)" — Generated HTML mockups from design-phase
 
-Apply selected patterns to `.gitignore`. Create the file if needed.
+Apply selected patterns to `.gitignore`. Create the file if needed:
+
+```bash
+echo '.planning/phases/**/*.patch' >> .gitignore  # if selected
+echo '.planning/phases/**/*.html' >> .gitignore   # if selected
+```
 
 If no selections: skip gitignore changes.
 
@@ -138,6 +144,48 @@ jq --arg v "$VALUE" '.open_mockups = $v' .planning/config.json > .planning/confi
 
 </step>
 
+<step name="task_tracker">
+
+Read current value:
+
+```bash
+CURRENT=$(cat .planning/config.json 2>/dev/null | jq -r '.task_tracker.type // "not configured"')
+echo "Current task_tracker: $CURRENT"
+```
+
+Use AskUserQuestion:
+- header: "Task tracker"
+- question: "Do you use a task tracker for this project?"
+- options:
+  - "Linear" — Integrate with Linear for ticket-driven adhoc work
+  - "None / not yet" — Skip task tracker integration
+
+If "Linear":
+
+Use AskUserQuestion:
+- header: "Linear CLI"
+- question: "Path to Linear CLI script?"
+- options:
+  - "Default (`uv run ~/.claude/skills/linear/scripts/linear.py`) (Recommended)" — Standard Mindsystem Linear skill location
+  - "Custom path" — I'll provide the CLI path
+
+If "Default": set `cli` to `uv run ~/.claude/skills/linear/scripts/linear.py`
+If "Custom path": ask user for path via AskUserQuestion.
+
+Write to config.json:
+
+```bash
+jq '.task_tracker = {"type": "linear", "cli": $cli}' --arg cli "$CLI_PATH" .planning/config.json > .planning/config.tmp && mv .planning/config.tmp .planning/config.json
+```
+
+If "None / not yet":
+
+```bash
+jq '.task_tracker = null' .planning/config.json > .planning/config.tmp && mv .planning/config.tmp .planning/config.json
+```
+
+</step>
+
 <step name="validation_summary">
 
 Show final config state:
@@ -149,6 +197,7 @@ Configuration updated:
 - Mockup open: [auto / ask / off]
 - Gitignore: [patterns added, or "no changes"]
 - Git remote: [remote URL, or "none configured"]
+- Task tracker: [type + cli path, or "none"]
 ```
 
 Check subsystems in config.json. If empty or missing, note:
@@ -172,45 +221,12 @@ EOF
 
 <step name="done">
 
-Present next steps:
-
-**If PROJECT.md exists:**
-
-```
----
-
-## ▶ Next Up
-
-`/ms:new-milestone` — Discover what to build next, create requirements and roadmap
-
-<sub>`/clear` first → fresh context window</sub>
-
----
-
-**Also available:**
-- `/ms:doctor` — Verify subsystems and artifact health
+Present next steps using the "Next Up" format:
 
----
-```
-
-**If no PROJECT.md:**
-
-```
----
-
-## ▶ Next Up
+- **If PROJECT.md exists:** recommend `/ms:new-milestone` — Discover what to build next, create requirements and roadmap
+- **If no PROJECT.md:** recommend `/ms:new-project` — Initialize project with business context and vision
 
-`/ms:new-project` — Initialize project with business context and vision
-
-<sub>`/clear` first → fresh context window</sub>
-
----
-
-**Also available:**
-- `/ms:doctor` — Verify subsystems and artifact health
-
----
-```
+Also list: `/ms:doctor` — Verify subsystems and artifact health
 
 </step>
 
@@ -225,5 +241,6 @@ Present next steps:
 - [ ] Validation summary displayed
 - [ ] Config.json code_review values set (or preserved if skipped)
 - [ ] Config.json open_mockups value set (or preserved if skipped)
+- [ ] Config.json task_tracker value set (or preserved if skipped)
 
 </success_criteria>

package/commands/ms/create-roadmap.md

@@ -132,13 +132,14 @@ Task(
 
 <instructions>
 1. Derive REQUIREMENTS.md from milestone context (apply requirements_derivation process)
-2. Derive phases from those requirements (don't impose structure)
-3. **Start phase numbering at $START_PHASE** (not 1, unless this is the first milestone)
-4. Map every v1 requirement to exactly one phase
-5. Derive 2-5 success criteria per phase (observable user behaviors)
-6. Validate 100% coverage
-7. Write files immediately (REQUIREMENTS.md, ROADMAP.md, STATE.md)
-8. Return ROADMAP CREATED with combined requirements + roadmap summary
+2. If PROJECT.md has a Deferred section, consider those items as v1 candidates for this milestone
+3. Derive phases from those requirements (don't impose structure)
+4. **Start phase numbering at $START_PHASE** (not 1, unless this is the first milestone)
+5. Map every v1 requirement to exactly one phase
+6. Derive 2-5 success criteria per phase (observable user behaviors)
+7. Validate 100% coverage
+8. Write files immediately (REQUIREMENTS.md, ROADMAP.md, STATE.md)
+9. Return ROADMAP CREATED with combined requirements + roadmap summary
 
 Write files first, then return. This ensures artifacts persist even if context is lost.
 </instructions>

package/commands/ms/doctor.md

@@ -13,7 +13,7 @@ allowed-tools:
 ---
 
 <objective>
-Run health checks on project configuration. Detect and fix structural drift across 9 categories: subsystem vocabulary, milestone directory structure, milestone naming convention, phase archival, knowledge files, phase summaries, PLAN cleanup, CLI wrappers, and research API keys.
+Run health checks on project configuration. Detect and fix structural drift across 10 categories: subsystem vocabulary, milestone directory structure, milestone naming convention, phase archival, knowledge files, phase summaries, PLAN cleanup, CLI wrappers, research API keys, and Mindsystem version.
 
 Idempotent.
 </objective>
@@ -59,7 +59,8 @@ If MISSING, create from template structure:
     "adhoc": null,
     "phase": null,
     "milestone": null
-  }
+  },
+  "task_tracker": null
 }
 ```
 
@@ -79,6 +80,28 @@ ms-tools doctor-scan
 Capture the full output. Parse each check's Status (PASS/FAIL/SKIP/WARN) and detail lines.
 </step>
 
+<step name="check_version">
+Check for Mindsystem updates:
+
+```bash
+# Installed version
+cat "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/mindsystem/VERSION" 2>/dev/null || cat ./.claude/mindsystem/VERSION 2>/dev/null
+```
+
+```bash
+# Latest from npm
+npm view mindsystem-cc version 2>/dev/null
+```
+
+Compare versions:
+- installed == latest → PASS, "v{installed} (latest)"
+- installed > latest → PASS, "v{installed} (development)"
+- installed < latest → WARN, "v{installed} → v{latest} available — run `/ms:update`"
+- npm fetch failed → SKIP, "Could not reach npm registry"
+
+Include as an extra row ("Mindsystem version") in the results table.
+</step>
+
 <step name="present_results">
 Display results as a markdown table:
 
@@ -96,9 +119,10 @@ Display results as a markdown table:
 | PLAN cleanup             | FAIL   | 9 leftover PLAN.md files         |
 | CLI wrappers             | FAIL   | ms-tools not on PATH             |
 | Research API Keys        | WARN   | PERPLEXITY_API_KEY not set        |
+| Mindsystem version       | WARN   | v3.21.0 → v3.22.1 available       |
 ```
 
-Populate Result and Details from scan output. Use concise detail summaries.
+Populate Result and Details from scan output and version check. Use concise detail summaries.
 
 If all PASS (or WARN only) → go to `report`.
 If any FAIL → go to `confirm_action`.
@@ -155,6 +179,7 @@ Final summary table:
 | PLAN cleanup             | PASS   | ...                              |
 | CLI wrappers             | PASS   | ...                              |
 | Research API Keys        | PASS   | ...                              |
+| Mindsystem version       | PASS   | ...                              |
 
 All checks passed.
 ```
@@ -170,6 +195,6 @@ Include counts: checks total, passed, warned, fixed during this run.
 - [ ] Re-scan verifies all checks pass after fixes
 - [ ] Each fix group committed atomically
 - [ ] Fixes applied in dependency order: subsystems → dirs → milestone naming → archival → cleanup → knowledge
-- [ ] All 9 categories reported with PASS/FAIL/WARN/SKIP
+- [ ] All 10 categories reported with PASS/FAIL/WARN/SKIP
 - [ ] Clean project reports all PASS with no fix prompts
 </success_criteria>

package/commands/ms/help.md

@@ -47,14 +47,11 @@ Output ONLY the reference content below. Do NOT add:
 Mindsystem evolves fast. Check for updates periodically:
 
 ```
-/ms:release-notes
+/ms:update
 ```
 
-Shows full release notes with update status. Update with:
-
-```bash
-npx mindsystem-cc@latest
-```
+Shows current vs latest version. Updates non-interactively if behind.
+Release notes: `/ms:release-notes`
 
 ## Core Workflow
 
@@ -298,15 +295,6 @@ Archive completed milestone and prepare for next.
 Usage: `/ms:complete-milestone`
 Usage: `/ms:complete-milestone "MVP"`
 
-**`/ms:plan-milestone-gaps`**
-Create phases to close gaps identified by milestone audit.
-
-- Reads MILESTONE-AUDIT.md and groups gaps into logical phases
-- Prioritizes by requirement importance (must/should/nice)
-- Creates phase entries in ROADMAP.md automatically
-
-Usage: `/ms:plan-milestone-gaps`
-
 ### Progress Tracking
 
 **`/ms:progress`**
@@ -340,44 +328,32 @@ Usage: `/ms:debug` (resume active session)
 ### Todo Management
 
 **`/ms:add-todo [description]`**
-Capture idea or task as todo from current conversation.
+Capture idea or task as todo with priority, estimate, and subsystem (Linear-inspired).
 
 - Use when: you discover work that’s real but not the right thing to do right now.
 - Extracts context from conversation (or uses provided description)
-- Creates structured todo file in `.planning/todos/pending/`
-- Infers area from file paths for grouping
-- Checks for duplicates before creating
-- Updates STATE.md todo count
+- Infers priority (1-4), estimate (XS-XL), and subsystem from context
+- Confirms inferred metadata before creating (adjust if needed)
+- Creates structured todo file in `.planning/todos/`
+- Use `/ms:adhoc` to address todos anytime
 
 Usage: `/ms:add-todo` (infers from conversation)
 Usage: `/ms:add-todo Add auth token refresh`
 
-**`/ms:check-todos [area]`**
-List pending todos and select one to work on.
-
-- Use when: you want to pick up deferred work and route it into the right place (do now vs schedule vs plan into a phase).
-- Lists all pending todos with title, area, age
-- Optional area filter (e.g., `/ms:check-todos api`)
-- Loads full context for selected todo
-- Routes to appropriate action (work now, add to phase, brainstorm)
-- Moves todo to done/ when work begins
-
-Usage: `/ms:check-todos`
-Usage: `/ms:check-todos api`
-
 ### Adhoc Work
 
 **`/ms:adhoc <description>`**
-Execute small discovered work without phase overhead (max 2 tasks).
+Execute discovered work with knowledge-aware planning and execution.
 
-- Use when: you discover small work mid-session that needs to be done now but doesn't warrant a full phase.
-- Bridges the gap between `/ms:add-todo` (capture for later) and `/ms:insert-phase` (full planning)
-- Maximum 2 tasks — refuses and suggests `/ms:insert-phase` for larger work
-- Creates lightweight artifacts in `.planning/adhoc/` for audit trail
-- Updates STATE.md with adhoc work entry
-- Single git commit with all changes
+- Use when: you discover work mid-session that can be completed in a single context window without multi-phase orchestration.
+- Bridges the gap between `/ms:add-todo` (capture for later) and `/ms:insert-phase` (multi-plan coordination)
+- Knowledge-aware: loads relevant knowledge files before planning, consolidates learnings after execution
+- Spawns Explore agents for codebase understanding, ms-adhoc-planner for plan creation, ms-executor for execution
+- Creates per-execution artifacts in `.planning/adhoc/{timestamp}-{slug}/`
+- Updates knowledge files via ms-consolidator after execution
 
 Usage: `/ms:adhoc Fix auth token not refreshing on 401`
+Usage: `/ms:adhoc Refactor API error handling to use consistent format`
 
 ### Utility Commands
 
@@ -392,6 +368,31 @@ Health check and fix project configuration — subsystems, milestone structure,
 
 Usage: `/ms:doctor`
 
+**`/ms:compound [input]`**
+Compound code changes into knowledge files.
+
+- Use when: work was done outside the Mindsystem pipeline and knowledge files need updating
+- Accepts: git reference (SHA, range), file path, description, or no args (infers from conversation)
+- Updates existing knowledge files for affected subsystems
+- Creates new subsystem knowledge files if warranted
+- Extends config.json subsystem list if new subsystem detected
+
+Usage: `/ms:compound abc123` (commit)
+Usage: `/ms:compound HEAD~3..HEAD` (range)
+Usage: `/ms:compound src/auth/login.ts` (file)
+Usage: `/ms:compound "Added JWT auth with refresh tokens"` (description)
+Usage: `/ms:compound` (infer from conversation context)
+
+**`/ms:update`**
+Check for updates and install latest Mindsystem version.
+
+- Detects local vs global install mode automatically
+- Compares installed version against npm registry
+- Runs non-interactive install with --force flag
+- After update: restart Claude Code, then run `/ms:doctor`
+
+Usage: `/ms:update`
+
 **`/ms:help`**
 Show this command reference.
 
@@ -415,11 +416,12 @@ Usage: `/ms:release-notes`
 ├── config.json           # Workflow settings
 ├── research/             # Domain ecosystem research
 ├── todos/                # Captured ideas and tasks
-│   ├── pending/          # Todos waiting to be worked on
+│   ├── *.md              # Pending todos (flat files)
 │   └── done/             # Completed todos
-├── adhoc/                # Small work executed via /ms:adhoc
-│   ├── *-PLAN.md         # Lightweight plans
-│   └── *-SUMMARY.md      # Completion summaries
+├── adhoc/                # Work executed via /ms:adhoc
+│   └── {date}-{slug}/    # Per-execution subdirectory
+│       ├── adhoc-01-PLAN.md    # Execution plan (deleted after consolidation)
+│       └── adhoc-01-SUMMARY.md # Completion summary
 ├── debug/                # Active debug sessions
 │   └── resolved/         # Archived resolved issues
 ├── codebase/             # Codebase map (brownfield projects)
@@ -489,8 +491,8 @@ Usage: `/ms:release-notes`
 ```
 /ms:debug "form submission fails silently"    # Systematic investigation (persists across /clear)
 # Then decide where the fix belongs:
-# - If it's small (1-2 tasks) and needed now:
-/ms:adhoc "Fix auth token refresh on 401"   # Quick fix with audit trail
+# - If it fits in a single context window:
+/ms:adhoc "Fix auth token refresh on 401"   # Knowledge-aware fix with consolidation
 # - If it's required to satisfy the current phase goal: add more plans to the current phase
 /ms:plan-phase 5                              # (or: /ms:plan-phase 5 --gaps after verification)
 /ms:execute-phase 5
@@ -532,10 +534,9 @@ Common options:
 **Closing gaps from audit:**
 
 ```
-/ms:audit-milestone             # Finds gaps
-/ms:plan-milestone-gaps         # Creates phases to fix them
-/ms:plan-phase 6                # Plan first gap closure phase
-/ms:execute-phase 6
+/ms:audit-milestone             # Finds gaps → review MILESTONE-AUDIT.md
+/ms:adhoc "fix dashboard auth"  # Discovered gaps (single context)
+/ms:add-phase "Wire API auth"   # Larger coherent gaps
 /ms:audit-milestone             # Re-audit when done
 ```
 
@@ -544,8 +545,7 @@ Common options:
 ```
 /ms:add-todo                    # Capture from conversation context
 /ms:add-todo Fix modal z-index  # Capture with explicit description
-/ms:check-todos                 # Review and work on todos
-/ms:check-todos api             # Filter by area
+/ms:adhoc Fix modal z-index     # Work on a todo right now
 ```
 
 ## Getting Help

package/commands/ms/new-milestone.md

@@ -66,7 +66,8 @@ Milestone name: $ARGUMENTS (optional — will emerge during discovery if not pro
 1. **Load context:**
    - Read PROJECT.md (existing project, validated requirements, decisions)
    - Read MILESTONES.md (what shipped previously)
-   - Read STATE.md (pending todos, blockers)
+   - Read STATE.md (blockers)
+   - Scan `.planning/todos/` for pending todos
    - Read config.json (project settings)
    - Identify previous milestone name from MILESTONES.md (e.g., last shipped was "MVP")
 
@@ -111,9 +112,9 @@ Milestone name: $ARGUMENTS (optional — will emerge during discovery if not pro
    - Tech debt from TECH-DEBT.md, MILESTONE-AUDIT.md, or knowledge file Pitfalls sections
    - Settled decisions and patterns from knowledge files
    - Untested assumptions from previous audit
-   - Unaddressed requirements from previous milestones
+   - Deferred items from PROJECT.md `## Deferred` section (carried forward from previous milestones)
    - Strategic features inferred from PROJECT.md: Who It's For, Core Problem, How It's Different
-   - Pending todos from STATE.md
+   - Pending todos from `.planning/todos/`
 
    If no meaningful artifacts exist (first milestone), base suggestions purely on PROJECT.md.
 

package/commands/ms/progress.md

@@ -38,7 +38,7 @@ Reconstruct STATE.md from artifacts:
 1. Read PROJECT.md → Extract "What This Is" and Core Value
 2. Read ROADMAP.md → Determine phases, find current position
 3. Scan *-SUMMARY.md files → Extract recent decisions, concerns
-4. Count pending todos in .planning/todos/pending/
+4. Count pending todos in .planning/todos/
 
 Write reconstructed STATE.md, then proceed to "load" step.
 
@@ -55,6 +55,22 @@ This means a milestone was completed and archived. Go to **Route F** (between mi
 If missing both ROADMAP.md and PROJECT.md: suggest `/ms:new-project`.
 </step>
 
+<step name="check_version">
+**Check for Mindsystem updates (non-blocking):**
+
+```bash
+# Installed version
+cat "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/mindsystem/VERSION" 2>/dev/null || cat ./.claude/mindsystem/VERSION 2>/dev/null
+```
+
+```bash
+# Latest from npm
+npm view mindsystem-cc version 2>/dev/null
+```
+
+Compare versions. Store result for the report step. If npm fails or versions match, skip — do not block progress.
+</step>
+
 <step name="load">
 **Load full project context:**
 
@@ -79,7 +95,7 @@ If missing both ROADMAP.md and PROJECT.md: suggest `/ms:new-project`.
 - Note any blockers or concerns
 - Check for CONTEXT.md: For phases without PLAN.md files, check if `{phase}-CONTEXT.md` exists in phase directory
 - Check for DESIGN.md: For UI-heavy phases, check if `{phase}-DESIGN.md` exists in phase directory
-- Count pending todos: `ls .planning/todos/pending/*.md 2>/dev/null | wc -l`
+- 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>
 
@@ -109,12 +125,16 @@ DESIGN: [✓ if DESIGN.md exists | - if not]
 - [any blockers or concerns from STATE.md]
 
 ## Pending Todos
-- [count] pending — /ms:check-todos to review
+- [count] pending — /ms:add-todo to capture, /ms:adhoc to work on
 
 ## Active Debug Sessions
 - [count] active — /ms:debug to continue
 (Only show this section if count > 0)
 
+## Update Available
+⬆ v{installed} → v{latest} — run `/ms:update`
+(Only show this section if installed < latest)
+
 ## What's Next
 [Next phase/plan objective from ROADMAP]
 ```