gm-cc 2.0.455 → 2.0.456

package/.claude-plugin/marketplace.json

@@ -4,7 +4,7 @@
     "name": "AnEntrypoint"
   },
   "description": "State machine agent with hooks, skills, and automated git enforcement",
-  "version": "2.0.455",
+  "version": "2.0.456",
   "metadata": {
     "description": "State machine agent with hooks, skills, and automated git enforcement"
   },

package/AGENTS.md

@@ -0,0 +1,11 @@
+# AGENTS
+
+## Technical Notes
+
+Hook response format: `{"decision":"allow|block","reason":"text"}` with exit code 0.
+
+Tool names for this platform: `bash` → `Bash`, `write` → `Write`, `glob` → `Glob`, `grep` → `Grep`, `search` → `Search`
+
+When filtering transcript history by sessionId, use: `if (sessionId && entry.sessionId === sessionId)`
+
+Verification file `.gm-stop-verified` is auto-added to .gitignore and tracks session completion state.

package/CLAUDE.md

@@ -1,11 +1 @@
-# CLAUDE
-
-## Technical Notes
-
-Hook response format: `{"decision":"allow|block","reason":"text"}` with exit code 0.
-
-Tool names for this platform: `bash` → `Bash`, `write` → `Write`, `glob` → `Glob`, `grep` → `Grep`, `search` → `Search`
-
-When filtering transcript history by sessionId, use: `if (sessionId && entry.sessionId === sessionId)`
-
-Verification file `.gm-stop-verified` is auto-added to .gitignore and tracks session completion state.
+@AGENTS.md

package/agents/memorize.md

@@ -1,17 +1,17 @@
 ---
 name: memorize
-description: Background memory agent. Classifies context into memory/ dir and CLAUDE.md. Aggressively prunes stale/derivable/duplicate entries.
+description: Background memory agent. Classifies context into memory/ dir and AGENTS.md. Aggressively prunes stale/derivable/duplicate entries.
 agent: true
 ---
 
 # Memorize — Background Memory Agent
 
 Memory dir: C:/Users/user/.claude/projects/C--dev-plugforge/memory/
-CLAUDE.md: C:/dev/plugforge/CLAUDE.md
+AGENTS.md: C:/dev/plugforge/AGENTS.md
 
 ## STEP 1: READ
 
-Read memory dir contents and MEMORY.md index. Read all existing memory files. Read CLAUDE.md in full.
+Read memory dir contents and MEMORY.md index. Read all existing memory files. Read AGENTS.md in full.
 
 If memory dir does not exist, create it. If MEMORY.md does not exist, create it empty.
 
@@ -20,7 +20,7 @@ If memory dir does not exist, create it. If MEMORY.md does not exist, create it
 Run BEFORE writing any new content.
 
 Remove entries that are:
-- Contradicted or superseded by current CLAUDE.md or observable codebase facts
+- Contradicted or superseded by current AGENTS.md or observable codebase facts
 - Duplicates of other entries (merge into one)
 - Derivable at runtime via exec:codesearch: file paths, function names, API shapes, architecture patterns
 - Active task state, current progress, session narration
@@ -39,7 +39,7 @@ Examine the ## CONTEXT TO MEMORIZE section at the end of this prompt. For each f
 - reference: pointers to external systems, URLs, paths
 
 Discard:
-- Facts already covered in CLAUDE.md (exact or paraphrase)
+- Facts already covered in AGENTS.md (exact or paraphrase)
 - Obvious facts derivable from reading the code
 - Active task state or session progress
 
@@ -76,14 +76,14 @@ No frontmatter. Max 200 lines.
 
 ## STEP 6: CONSOLIDATE
 
-For each memory file: if its content is already fully covered by CLAUDE.md (exact or equivalent), delete the memory file and remove its line from MEMORY.md.
+For each memory file: if its content is already fully covered by AGENTS.md (exact or equivalent), delete the memory file and remove its line from MEMORY.md.
 
-## STEP 7: CLAUDE.md
+## STEP 7: AGENTS.md
 
 A non-obvious technical caveat qualifies if it required multiple failed runs to discover and would not be apparent from reading code or docs.
 
 For each qualifying fact from context:
-- If CLAUDE.md already covers it → skip
+- If AGENTS.md already covers it → skip
 - If genuinely non-obvious → append to the appropriate section
 
 Never add: obvious patterns, active task progress, redundant restatements.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-cc",
-  "version": "2.0.455",
+  "version": "2.0.456",
   "description": "State machine agent with hooks, skills, and automated git enforcement",
   "author": "AnEntrypoint",
   "license": "MIT",
@@ -39,7 +39,8 @@
     ".gitignore",
     ".editorconfig",
     "CONTRIBUTING.md",
-    "CLAUDE.md"
+    "CLAUDE.md",
+    "AGENTS.md"
   ],
   "keywords": [
     "claude-code",

package/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "gm",
-  "version": "2.0.455",
+  "version": "2.0.456",
   "description": "State machine agent with hooks, skills, and automated git enforcement",
   "author": {
     "name": "AnEntrypoint",

package/skills/gm-complete/SKILL.md

@@ -118,7 +118,7 @@ gh run view <run_id> --log-failed
 
 5. All runs must reach `conclusion: success` before advancing. A failed CI run is a KNOWN mutable that blocks completion — never ignore it.
 
-**Cascade awareness**: pushes to this repo may trigger downstream workflows (see CLAUDE.md Rust Binary Update Pipeline). After local CI passes, check downstream repos for triggered runs:
+**Cascade awareness**: pushes to this repo may trigger downstream workflows (see AGENTS.md Rust Binary Update Pipeline). After local CI passes, check downstream repos for triggered runs:
 ```
 exec:bash
 gh run list --repo AnEntrypoint/<downstream-repo> --limit 3 --json databaseId,name,status,conclusion

package/skills/planning/SKILL.md

@@ -111,7 +111,7 @@ Invoke `browser` skill. Escalation: (1) `exec:browser <js>` → (2) browser skil
 
 ## MANDATORY DEV WORKFLOW
 
-No comments. No test files. 200-line limit — split before continuing. Fail loud. No duplication. Scan before every edit. Duplicate concern = regress to PLAN. Errors throw with context — no `|| default`, no `catch { return null }`. `window.__debug` exposes all client state. CLAUDE.md via memorize only. CHANGELOG.md: append per commit.
+No comments. No test files. 200-line limit — split before continuing. Fail loud. No duplication. Scan before every edit. Duplicate concern = regress to PLAN. Errors throw with context — no `|| default`, no `catch { return null }`. `window.__debug` exposes all client state. AGENTS.md via memorize only. CHANGELOG.md: append per commit.
 
 **Minimal code / maximal DX process**: Before writing any logic, run this process in order — stop at the first step that resolves the need:
 1. **Native first** — does the language or runtime already do this? Use it exactly as designed.

package/skills/update-docs/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: update-docs
-description: UPDATE-DOCS phase. Refresh README.md, CLAUDE.md, and docs/index.html to reflect changes made this session. Commits and pushes doc updates. Terminal phase — declares COMPLETE.
+description: UPDATE-DOCS phase. Refresh README.md, AGENTS.md, and docs/index.html to reflect changes made this session. Commits and pushes doc updates. Terminal phase — declares COMPLETE.
 ---
 
 # GM UPDATE-DOCS — Documentation Refresh
@@ -35,7 +35,7 @@ Witness which files changed. Identify doc-sensitive changes: new skills, new sta
 ```
 exec:nodejs
 const fs = require('fs');
-['README.md', 'CLAUDE.md', 'docs/index.html',
+['README.md', 'AGENTS.md', 'docs/index.html',
  'gm-starter/agents/gm.md'].forEach(f => {
   try { console.log(`=== ${f} ===\n` + fs.readFileSync(f, 'utf8')); }
   catch(e) { console.log(`MISSING: ${f}`); }
@@ -50,7 +50,7 @@ Write only sections that changed. Do not rewrite unchanged content. Rules per fi
 
 **README.md**: platform count matches adapters in `platforms/`, skill tree diagram matches current state machine, quick start commands work.
 
-**CLAUDE.md**: Launch memorize sub-agent in background with session learnings. Do not inline-edit CLAUDE.md — the memorize agent handles extraction, deduplication, and writing. Use: `Agent(subagent_type='memorize', model='haiku', run_in_background=true, prompt='## CONTEXT TO MEMORIZE\n<session learnings>')`
+**AGENTS.md**: Launch memorize sub-agent in background with session learnings. Do not inline-edit AGENTS.md — the memorize agent handles extraction, deduplication, and writing. Use: `Agent(subagent_type='memorize', model='haiku', run_in_background=true, prompt='## CONTEXT TO MEMORIZE\n<session learnings>')`
 
 **docs/index.html**: `PHASES` array matches current skill state machine phases. Platform lists match `platforms/` directory. State machine diagram updated if new phases added.