codymaster 5.2.0 → 7.0.0

package/skills/cm-skill-index/SKILL.md

@@ -1,10 +1,18 @@
 ---
 name: cm-skill-index
 description: "Progressive Disclosure skill index — efficient skill loading in 3 layers. Layer 1 (index, ~100 tokens) always loaded. Layer 2 (summary, ~300 tokens) loaded on context need. Layer 3 (full SKILL.md) loaded on execution only."
+token_budget: 800
+compressed: true
+deprecated: false
 ---
 
 # Skill Index — Progressive Disclosure Engine
 
+## TL;DR
+- **Use when** searching for a CodyMaster or community skill
+- **Layered**: L1 index (always loaded) → L2 summary → L3 full
+- **Includes**: discovery, search, mastery (consolidated in v6)
+
 > **Save 90%+ tokens.** Agents scan the index first, load full skills only when executing.
 > Inspired by Loki Mode's 3-Layer Progressive Disclosure memory architecture.
 

package/skills/cm-skill-mastery/SKILL.archive.md

@@ -0,0 +1,156 @@
+---
+name: cm-skill-mastery
+description: "Meta-skill for the Cody Master kit — when to invoke skills, how to create new skills, and skill discovery. Use at conversation start to establish skill discipline."
+---
+
+# Skill Mastery — Use + Create + Discover
+
+> **The meta-skill:** How to find, use, and create cm-* skills.
+
+## Part A: Using Skills
+
+### The Rule
+
+**Invoke relevant skills BEFORE any response or action.** Even 1% chance = check the skill.
+
+### Decision Flow
+
+```
+User message received
+  → Might any skill apply? (even 1%)
+    → YES: Read the skill → Follow it
+    → NO: Respond directly
+```
+
+### Skill Priority
+
+1. **Process skills first** (cm-planning, cm-debugging) — determine HOW to approach
+2. **Implementation skills second** (cm-tdd, cm-safe-deploy) — guide execution
+
+### Red Flags
+
+| Thought | Reality |
+|---------|---------|
+| "This is just a simple question" | Questions are tasks. Check for skills. |
+| "I need more context first" | Skill check BEFORE clarifying questions. |
+| "The skill is overkill" | Simple things become complex. Use it. |
+| "I remember this skill" | Skills evolve. Read current version. |
+| "Let me just do this one thing first" | Check BEFORE doing anything. |
+
+### Skill Types
+
+- **Rigid** (cm-tdd, cm-debugging): Follow exactly. Don't adapt away discipline.
+- **Flexible** (cm-planning): Adapt principles to context.
+
+---
+
+## Part B: Creating Skills
+
+### When to Create
+
+- Pattern repeated across 3+ projects
+- Complex process that needs documentation
+- Team convention that should be enforced
+
+### Skill Structure
+
+```markdown
+---
+name: cm-[skill-name]
+description: "One line: when to use this skill"
+---
+
+# [Skill Title]
+
+## Overview
+What and why. Core principle.
+
+## When to Use
+Specific triggers.
+
+## The Process
+Step-by-step instructions.
+
+## Red Flags
+What NOT to do.
+
+## Integration
+How it connects to other cm-* skills.
+```
+
+### Rules
+
+```
+✅ DO:
+- Keep under 400 lines (token optimization)
+- Use tables and code blocks for density
+- Include Red Flags section
+- Reference other cm-* skills by name
+- Test skill with real scenarios before deploying
+
+❌ DON'T:
+- Write prose when a table works
+- Duplicate content from other skills (reference instead)
+- Create skills for one-time tasks
+- Exceed 600 lines without good reason
+```
+
+### Token Optimization
+
+| Technique | Saves |
+|-----------|-------|
+| Tables over prose | ~40% |
+| Code blocks over explanation | ~30% |
+| Reference other skills vs duplicate | ~50% |
+| Remove obvious examples | ~20% |
+
+---
+
+## Part C: Discovering Skills
+
+### Adaptive Skills Discovery
+
+When you encounter something you don't have a skill for:
+
+```
+1. DETECT  → "I need to do X but no matching skill"
+2. SEARCH  → npx skills find "{keyword}"
+3. REVIEW  → Read the SKILL.md — safe? relevant?
+4. ASK     → "Found skill '{name}'. Install?"
+5. INSTALL → npx skills add {source} --skill {name} -a antigravity
+6. USE     → Apply the skill
+7. LOG     → Record in .cm-skills-log.json
+```
+
+### Safety Rules
+
+- Always show user what you found before installing
+- Prefer known repos (vercel-labs/agent-skills)
+- Project-level by default, global only if agreed
+- Check `npx skills list` to avoid duplicates
+- Never override existing cm-* skills with external ones
+
+---
+
+## The Cody Master Kit (14 skills)
+
+| # | Skill | Purpose |
+|---|-------|---------|
+| 1 | `cm-project-bootstrap` | Start new projects |
+| 2 | `cm-brainstorm-idea` | Strategic analysis gate for enhancements (9 Windows + Double Diamond) |
+| 3 | `cm-planning` | Brainstorm + write plans |
+| 4 | `cm-execution` | Execute plans (batch/subagent/parallel) |
+| 5 | `cm-tdd` | Test-driven development |
+| 6 | `cm-quality-gate` | Test + verify + frontend safety |
+| 7 | `cm-code-review` | Request + receive + finish branch |
+| 8 | `cm-safe-deploy` | 6-gate deploy pipeline |
+| 9 | `cm-safe-i18n` | i18n batching + safety |
+| 10 | `cm-debugging` | Systematic root-cause debugging |
+| 11 | `cm-terminal` | Terminal command monitoring |
+| 12 | `cm-git-worktrees` | Isolated workspaces |
+| 13 | `cm-skill-mastery` | This skill (meta) |
+| 14 | `cm-identity-guard` | Git/deploy identity safety |
+
+## The Bottom Line
+
+**Skills are discipline, not overhead. Use them. Create them. Never skip them.**

package/skills/cm-skill-mastery/SKILL.md

@@ -1,156 +1,26 @@
 ---
 name: cm-skill-mastery
-description: "Meta-skill for the Cody Master kit — when to invoke skills, how to create new skills, and skill discovery. Use at conversation start to establish skill discipline."
+description: "[Deprecated] discovery and meta-skill merged. Use `cm-skill-index` instead."
+deprecated: true
+merged_into: cm-skill-index
 ---
 
-# Skill Mastery — Use + Create + Discover
+# cm-skill-mastery — Deprecated
 
-> **The meta-skill:** How to find, use, and create cm-* skills.
+> ⚠️ This skill is deprecated as of CodyMaster v6.0.0 and will be removed in v6.1.0.
+>
+> **Use `cm-skill-index` instead.** discovery and meta-skill merged.
+>
+> See [docs/migration-v2.md](../../docs/migration-v2.md) for the full mapping.
 
-## Part A: Using Skills
+The original content is preserved at [SKILL.archive.md](SKILL.archive.md) for reference.
 
-### The Rule
+## Migration
 
-**Invoke relevant skills BEFORE any response or action.** Even 1% chance = check the skill.
-
-### Decision Flow
-
-```
-User message received
-  → Might any skill apply? (even 1%)
-    → YES: Read the skill → Follow it
-    → NO: Respond directly
+```bash
+# Old:           cm <use this skill>
+# New (v6.0+):   cm skill-index <equivalent action>
 ```
 
-### Skill Priority
-
-1. **Process skills first** (cm-planning, cm-debugging) — determine HOW to approach
-2. **Implementation skills second** (cm-tdd, cm-safe-deploy) — guide execution
-
-### Red Flags
-
-| Thought | Reality |
-|---------|---------|
-| "This is just a simple question" | Questions are tasks. Check for skills. |
-| "I need more context first" | Skill check BEFORE clarifying questions. |
-| "The skill is overkill" | Simple things become complex. Use it. |
-| "I remember this skill" | Skills evolve. Read current version. |
-| "Let me just do this one thing first" | Check BEFORE doing anything. |
-
-### Skill Types
-
-- **Rigid** (cm-tdd, cm-debugging): Follow exactly. Don't adapt away discipline.
-- **Flexible** (cm-planning): Adapt principles to context.
-
----
-
-## Part B: Creating Skills
-
-### When to Create
-
-- Pattern repeated across 3+ projects
-- Complex process that needs documentation
-- Team convention that should be enforced
-
-### Skill Structure
-
-```markdown
----
-name: cm-[skill-name]
-description: "One line: when to use this skill"
----
-
-# [Skill Title]
-
-## Overview
-What and why. Core principle.
-
-## When to Use
-Specific triggers.
-
-## The Process
-Step-by-step instructions.
-
-## Red Flags
-What NOT to do.
-
-## Integration
-How it connects to other cm-* skills.
-```
-
-### Rules
-
-```
-✅ DO:
-- Keep under 400 lines (token optimization)
-- Use tables and code blocks for density
-- Include Red Flags section
-- Reference other cm-* skills by name
-- Test skill with real scenarios before deploying
-
-❌ DON'T:
-- Write prose when a table works
-- Duplicate content from other skills (reference instead)
-- Create skills for one-time tasks
-- Exceed 600 lines without good reason
-```
-
-### Token Optimization
-
-| Technique | Saves |
-|-----------|-------|
-| Tables over prose | ~40% |
-| Code blocks over explanation | ~30% |
-| Reference other skills vs duplicate | ~50% |
-| Remove obvious examples | ~20% |
-
----
-
-## Part C: Discovering Skills
-
-### Adaptive Skills Discovery
-
-When you encounter something you don't have a skill for:
-
-```
-1. DETECT  → "I need to do X but no matching skill"
-2. SEARCH  → npx skills find "{keyword}"
-3. REVIEW  → Read the SKILL.md — safe? relevant?
-4. ASK     → "Found skill '{name}'. Install?"
-5. INSTALL → npx skills add {source} --skill {name} -a antigravity
-6. USE     → Apply the skill
-7. LOG     → Record in .cm-skills-log.json
-```
-
-### Safety Rules
-
-- Always show user what you found before installing
-- Prefer known repos (vercel-labs/agent-skills)
-- Project-level by default, global only if agreed
-- Check `npx skills list` to avoid duplicates
-- Never override existing cm-* skills with external ones
-
----
-
-## The Cody Master Kit (14 skills)
-
-| # | Skill | Purpose |
-|---|-------|---------|
-| 1 | `cm-project-bootstrap` | Start new projects |
-| 2 | `cm-brainstorm-idea` | Strategic analysis gate for enhancements (9 Windows + Double Diamond) |
-| 3 | `cm-planning` | Brainstorm + write plans |
-| 4 | `cm-execution` | Execute plans (batch/subagent/parallel) |
-| 5 | `cm-tdd` | Test-driven development |
-| 6 | `cm-quality-gate` | Test + verify + frontend safety |
-| 7 | `cm-code-review` | Request + receive + finish branch |
-| 8 | `cm-safe-deploy` | 6-gate deploy pipeline |
-| 9 | `cm-safe-i18n` | i18n batching + safety |
-| 10 | `cm-debugging` | Systematic root-cause debugging |
-| 11 | `cm-terminal` | Terminal command monitoring |
-| 12 | `cm-git-worktrees` | Isolated workspaces |
-| 13 | `cm-skill-mastery` | This skill (meta) |
-| 14 | `cm-identity-guard` | Git/deploy identity safety |
-
-## The Bottom Line
-
-**Skills are discipline, not overhead. Use them. Create them. Never skip them.**
+If you depend on a capability that didn't carry over, please file an issue:
+https://github.com/tody-agent/codymaster/issues

package/skills/cm-skill-search/SKILL.archive.md

@@ -0,0 +1,49 @@
+---
+name: cm-skill-search
+description: "Find the best CodyMaster skill using the shipped indexes, profiles, docs, and contextual suggestions."
+---
+
+# cm-skill-search
+
+Use this skill when you need to find the right CodyMaster skill quickly and avoid loading the wrong `SKILL.md`.
+
+## Search order
+
+1. Fast path
+   - `cm suggest --project .`
+2. Library index
+   - `docs/skills/index.md`
+   - `docs/skills/*.md` category pages
+3. Progressive disclosure
+   - `skills/cm-skill-index/SKILL.md`
+4. Raw filesystem search
+   - `rg -n "<keyword>" skills docs README.md`
+5. Fallback
+   - if nothing matches, use `cm-skill-health` to check whether the missing skill is docs drift or a real gap
+
+## Query workflow
+
+1. Normalize the intent into 2-5 keywords.
+2. Search category pages before opening full skills.
+3. Open only the top 1-3 candidate `SKILL.md` files.
+4. Prefer the skill whose triggers, outputs, and lifecycle placement best match the task.
+5. If two skills overlap:
+   - choose the earlier lifecycle gate first
+   - example: `cm-brainstorm-idea` before `cm-planning`
+
+## Tie-breakers
+
+- Need diagnosis before repair: choose `cm-skill-health`
+- Need to repair a skill: choose `cm-skill-evolution`
+- Need to distribute a skill pack: choose `cm-skill-share`
+- Need the general index first: choose `cm-skill-index`
+
+## Output
+
+```md
+## Skill Search Result
+- Task: ...
+- Best match: cm-...
+- Runner-up: cm-...
+- Why: ...
+```

package/skills/cm-skill-search/SKILL.md

@@ -1,49 +1,26 @@
 ---
 name: cm-skill-search
-description: "Find the best CodyMaster skill using the shipped indexes, profiles, docs, and contextual suggestions."
+description: "[Deprecated] discovery merged. Use `cm-skill-index` instead."
+deprecated: true
+merged_into: cm-skill-index
 ---
 
-# cm-skill-search
+# cm-skill-search — Deprecated
 
-Use this skill when you need to find the right CodyMaster skill quickly and avoid loading the wrong `SKILL.md`.
+> ⚠️ This skill is deprecated as of CodyMaster v6.0.0 and will be removed in v6.1.0.
+>
+> **Use `cm-skill-index` instead.** discovery merged.
+>
+> See [docs/migration-v2.md](../../docs/migration-v2.md) for the full mapping.
 
-## Search order
+The original content is preserved at [SKILL.archive.md](SKILL.archive.md) for reference.
 
-1. Fast path
-   - `cm suggest --project .`
-2. Library index
-   - `docs/skills/index.md`
-   - `docs/skills/*.md` category pages
-3. Progressive disclosure
-   - `skills/cm-skill-index/SKILL.md`
-4. Raw filesystem search
-   - `rg -n "<keyword>" skills docs README.md`
-5. Fallback
-   - if nothing matches, use `cm-skill-health` to check whether the missing skill is docs drift or a real gap
+## Migration
 
-## Query workflow
-
-1. Normalize the intent into 2-5 keywords.
-2. Search category pages before opening full skills.
-3. Open only the top 1-3 candidate `SKILL.md` files.
-4. Prefer the skill whose triggers, outputs, and lifecycle placement best match the task.
-5. If two skills overlap:
-   - choose the earlier lifecycle gate first
-   - example: `cm-brainstorm-idea` before `cm-planning`
-
-## Tie-breakers
-
-- Need diagnosis before repair: choose `cm-skill-health`
-- Need to repair a skill: choose `cm-skill-evolution`
-- Need to distribute a skill pack: choose `cm-skill-share`
-- Need the general index first: choose `cm-skill-index`
-
-## Output
-
-```md
-## Skill Search Result
-- Task: ...
-- Best match: cm-...
-- Runner-up: cm-...
-- Why: ...
+```bash
+# Old:           cm <use this skill>
+# New (v6.0+):   cm skill-index <equivalent action>
 ```
+
+If you depend on a capability that didn't carry over, please file an issue:
+https://github.com/tody-agent/codymaster/issues

package/skills/cm-skill-share/SKILL.archive.md

@@ -0,0 +1,58 @@
+---
+name: cm-skill-share
+description: "Package, review, export, and import CodyMaster skill folders safely across machines or teams."
+---
+
+# cm-skill-share
+
+Use this skill when moving a CodyMaster skill between repos, machines, or teammates.
+
+## What to share
+
+Always treat a skill as a folder, not just `SKILL.md`.
+
+Check for:
+- `SKILL.md`
+- templates
+- scripts
+- references
+- assets
+- profile/index entries that must move with it
+
+## Export checklist
+
+1. Validate the source skill.
+   - `npm run validate:skills`
+2. Inspect companion files inside the skill folder.
+3. Note external dependencies the target repo must already have.
+4. Copy the entire folder.
+5. Update destination discovery surfaces if the skill becomes user-facing.
+
+## Import checklist
+
+1. Place the folder under `skills/cm-.../`
+2. Run:
+   - `npm run validate:skills`
+   - `npm run check:skills`
+3. Add it to:
+   - `skills/profiles/full.txt`
+   - docs skill index pages
+   - README only if the skill is part of the public catalog
+4. Verify referenced commands and files exist in the target repo.
+
+## Red flags
+
+- Do not import only the markdown file if the skill depends on scripts or templates.
+- Do not advertise the skill publicly before it is indexed and validated.
+- Do not overwrite an existing skill without comparing behavior and references first.
+
+## Output
+
+```md
+## Skill Share
+- Skill: cm-...
+- Direction: export | import
+- Companion files checked: yes | no
+- Discovery surfaces updated: yes | no
+- Validation: pass | fail
+```

package/skills/cm-skill-share/SKILL.md

@@ -1,58 +1,26 @@
 ---
 name: cm-skill-share
-description: "Package, review, export, and import CodyMaster skill folders safely across machines or teams."
+description: "[Deprecated] skill lifecycle merged. Use `cm-skill-evolution` instead."
+deprecated: true
+merged_into: cm-skill-evolution
 ---
 
-# cm-skill-share
+# cm-skill-share — Deprecated
 
-Use this skill when moving a CodyMaster skill between repos, machines, or teammates.
+> ⚠️ This skill is deprecated as of CodyMaster v6.0.0 and will be removed in v6.1.0.
+>
+> **Use `cm-skill-evolution` instead.** skill lifecycle merged.
+>
+> See [docs/migration-v2.md](../../docs/migration-v2.md) for the full mapping.
 
-## What to share
+The original content is preserved at [SKILL.archive.md](SKILL.archive.md) for reference.
 
-Always treat a skill as a folder, not just `SKILL.md`.
+## Migration
 
-Check for:
-- `SKILL.md`
-- templates
-- scripts
-- references
-- assets
-- profile/index entries that must move with it
-
-## Export checklist
-
-1. Validate the source skill.
-   - `npm run validate:skills`
-2. Inspect companion files inside the skill folder.
-3. Note external dependencies the target repo must already have.
-4. Copy the entire folder.
-5. Update destination discovery surfaces if the skill becomes user-facing.
-
-## Import checklist
-
-1. Place the folder under `skills/cm-.../`
-2. Run:
-   - `npm run validate:skills`
-   - `npm run check:skills`
-3. Add it to:
-   - `skills/profiles/full.txt`
-   - docs skill index pages
-   - README only if the skill is part of the public catalog
-4. Verify referenced commands and files exist in the target repo.
-
-## Red flags
-
-- Do not import only the markdown file if the skill depends on scripts or templates.
-- Do not advertise the skill publicly before it is indexed and validated.
-- Do not overwrite an existing skill without comparing behavior and references first.
-
-## Output
-
-```md
-## Skill Share
-- Skill: cm-...
-- Direction: export | import
-- Companion files checked: yes | no
-- Discovery surfaces updated: yes | no
-- Validation: pass | fail
+```bash
+# Old:           cm <use this skill>
+# New (v6.0+):   cm skill-evolution <equivalent action>
 ```
+
+If you depend on a capability that didn't carry over, please file an issue:
+https://github.com/tody-agent/codymaster/issues

package/skills/cm-sprint-bus/SKILL.md

@@ -1,9 +1,18 @@
 ---
 name: cm-sprint-bus
 description: "Use to run the full sprint pipeline: brainstorm → plan → design → tdd → build → review → qa → security → ship → monitor → retro."
+token_budget: 1500
+compressed: true
+deprecated: false
 ---
 # cm-sprint-bus — opinionated pipeline + artifacts
 
+## TL;DR
+- **Use to** drive the full sprint: brainstorm → ship → retro
+- **Phases**: brainstorm, plan, design, tdd, build, review, qa, security, ship, monitor, retro
+- **Each phase**: writes Markdown artifact + handoff JSON
+- **CLI**: cm sprint init|status|complete|skip|dry-run
+
 ## Pipeline
 
 `brainstorm → plan → design → tdd → build → review → qa → security → ship → monitor → retro`

package/skills/cm-start/SKILL.md

@@ -1,10 +1,18 @@
 ---
 name: cm-start
 description: Start the CM Workflow to execute your objective from idea to production code.
+token_budget: 1000
+compressed: true
+deprecated: false
 ---
 
 # Command: `/cm-start [your objective]`
 
+## TL;DR
+- **Use to** kick off a CM session — entry point
+- **Detects**: stack (Phase 2), suggests skills, reads continuity + learnings
+- **Next**: cm-brainstorm-idea or cm-planning
+
 > **Role: Workflow Orchestrator** — You assess complexity, select the right workflow depth, and drive execution from objective to production code.
 
 When this workflow is called, the AI Assistant should execute the following action sequence in the spirit of the **CodyMaster Kit**:
@@ -26,6 +34,15 @@ When this workflow is called, the AI Assistant should execute the following acti
       `npx skills find "{keyword}"` → review → ask user → install if approved
     - Log any discovered skills to `.cm-skills-log.json`
 
+0.6. **Stack & Tier Detection (Phase 2):**
+    - `cm stack detect --write` → writes `.cm/project-skills.md` (frameworks + suggested skills)
+    - `cm tier classify --write` → writes `.cm/project-tier.md` (LITE/STANDARD/PROFESSIONAL/ENTERPRISE)
+    - The tier sets the default Vibecoding mode and **adaptive depth**:
+      - LITE/STANDARD → render skill TL;DR only
+      - PROFESSIONAL/ENTERPRISE → render full protocol
+    - Inject the suggested-skills list into the skill chain shortlist
+    - These reports are token-light (~300 tok combined) and skipped if files exist and are <24h old
+
 0.7. **Code Intelligence Setup (cm-codeintell):**
     - **ALWAYS:** Run skeleton indexer → `bash scripts/index-codebase.sh` → `.cm/skeleton.md`
     - Read `.cm/skeleton.md` (~5K tokens) → instant codebase understanding

package/skills/cm-tdd/SKILL.md

@@ -1,10 +1,19 @@
 ---
 name: cm-tdd
 description: Use when implementing any feature or bugfix, before writing implementation code
+token_budget: 1500
+compressed: true
+deprecated: false
 ---
 
 # Test-Driven Development (TDD)
 
+## TL;DR
+- **Use when** writing or fixing any feature/bugfix
+- **Cycle**: red (failing test) → green (minimal code) → refactor
+- **No prod code** without a failing test first
+- **Next**: cm-execution or cm-code-review
+
 ## Overview
 
 Write the test first. Watch it fail. Write minimal code to pass.
@@ -352,6 +361,16 @@ Bug found? Write failing test reproducing it. Follow TDD cycle. Test proves fix
 
 Never fix bugs without a test.
 
+## Karpathy Discipline — Goal-Driven Execution
+
+TDD is the canonical form of goal-driven execution. Reinforce it:
+- **Translate vague tasks into verifiable goals before writing code.**
+  - "Add validation" → "Test invalid inputs fail; valid inputs pass."
+  - "Fix the bug" → "Test reproduces it red; fix turns it green."
+  - "Refactor X" → "Same tests green before and after."
+- **Strong success criteria let you loop independently.** Weak criteria ("make it work") force the user to babysit.
+- **Minimum code to pass.** Don't over-implement to "anticipate" the next test — write that test first.
+
 ## Final Rule
 
 ```