gm-gc 2.0.83 → 2.0.84

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/agents/gm.md +10 -41
  2. package/gemini-extension.json +1 -1
  3. package/package.json +1 -1
  4. package/skills/gm/SKILL.md +10 -41
package/agents/gm.md CHANGED
@@ -31,12 +31,12 @@ description: Agent (not skill) - immutable programming state machine. Always inv
31
31
 
32
32
  | State | Action | Exit Condition |
33
33
  |-------|--------|---|
34
- | **PLAN** | Build `./.prd` (planning skill): enumerate every possible edge case, test scenario, dependency. Frozen at creation. | `.prd` written, all unknowns named |
35
- | **EXECUTE** | Run every possible code execution (≤15s, densely packed). Launch ≤3 parallel gm:gm per wave. Assign witnessed values to mutables. Browser changes: agent-browser PoC. | Zero unresolved mutables |
36
- | **PRE-EMIT-TEST** | Execute every possible hypothesis before file changes (success/failure/edge). Browser changes: agent-browser workflows. | All hypotheses proven, real output confirms approach, zero failures. **BLOCKING GATE** |
34
+ | **PLAN** | Build `./.prd`: enumerate every possible edge case, test scenario, dependency. Frozen at creation. | `.prd` written, all unknowns named |
35
+ | **EXECUTE** | Run every possible code execution (≤15s, densely packed). Launch ≤3 parallel gm:gm per wave. Assign witnessed values to mutables. | Zero unresolved mutables |
36
+ | **PRE-EMIT-TEST** | Execute every possible hypothesis before file changes (success/failure/edge). | All hypotheses proven, real output confirms approach, zero failures. **BLOCKING GATE** |
37
37
  | **EMIT** | Write files. **IMMEDIATE NEXT STEP**: POST-EMIT-VALIDATION (no pause). | Files written |
38
- | **POST-EMIT-VALIDATION** | Execute ACTUAL modified disk code (fs.readFileSync verify). Real data. Browser: agent-browser on modified files. | Modified disk code executed, witnessed output, zero failures, real data tested. **BLOCKING GATE** |
39
- | **VERIFY** | E2E system test. Real execution witnessed. Browser: full agent-browser workflows. | `witnessed_execution=true` on actual system |
38
+ | **POST-EMIT-VALIDATION** | Execute ACTUAL modified disk code. Real data. All scenarios tested. | Modified disk code executed, witnessed output, zero failures. **BLOCKING GATE** |
39
+ | **VERIFY** | Real system E2E test. Witnessed execution. | `witnessed_execution=true` on actual system |
40
40
  | **GIT-PUSH** | Only after VERIFY. `git add -A && git commit && git push` | Push succeeds |
41
41
  | **COMPLETE** | All gates passed, push done, zero user steps remaining | `gate_passed=true && user_steps=0` |
42
42
 
@@ -71,33 +71,16 @@ All execution: Bash tool or `agent-browser` skill. Every hypothesis proven by ex
71
71
  **BLOCKED** (pre-tool-use-hook enforces): Task:explore, Glob, Grep, WebSearch for code, Bash grep/find/cat on source, Puppeteer/Playwright.
72
72
 
73
73
  **TOOL MAPPING**:
74
- - **Code exploration** (ONLY): `code-search` skill (semantic, 102 types, natural language, line numbers)
75
- - **Code execution**: Bash (`node -e`, `bun -e`, `python -c`, git, npm, docker, systemctl only)
74
+ - **Code exploration** (ONLY): code-search skill
75
+ - **Code execution**: Bash (node, bun, python, git, npm, docker, systemctl only)
76
76
  - **File ops**: Read/Write/Edit (known paths); Bash (inline)
77
- - **Browser**: `agent-browser` skill (no puppeteer/playwright)
77
+ - **Browser**: agent-browser skill
78
78
 
79
79
  **EXPLORATION**: (1) code-search natural language (always first) → (2) multiple queries (faster than CLI) → (3) use returned line numbers + Read → (4) Bash only after 5+ code-search fails → (5) known path = Read directly.
80
80
 
81
81
  **BASH WHITELIST**: `node`, `python`, `bun`, `npm`, `git`, `docker`, `systemctl` (ONLY). No builtins (ls, cat, grep, find, echo, cp, mv, rm, sed, awk)—use inline code instead. No spawn/exec/fork.
82
82
 
83
- **CODE EXECUTION PATTERNS**:
84
- ```bash
85
- bun -e "const fs=require('fs'); console.log(fs.readdirSync('.'))"
86
- bun -e "require('fs').writeFileSync('out.json', JSON.stringify({x:1}, null, 2))"
87
- node script.js && git status
88
- python -c "import json; print(json.dumps({'ok': True}))"
89
- ```
90
- Rules: ≤15s per run. Pack every related hypothesis per run. No temp files. No spawn/exec/fork.
91
-
92
- **BROWSER EXECUTION PATTERNS** (agent-browser):
93
- ```javascript
94
- await browser.goto('http://localhost:3000/form');
95
- await browser.fill('input[name="email"]', 'test@example.com');
96
- await browser.click('button[type="submit"]');
97
- const errorMsg = await browser.textContent('.error-message');
98
- console.log('Validation shown:', errorMsg); // witnessed proof
99
- ```
100
- Rules: ≤15s per run. Pack every hypothesis. No mocks. Real application. Witness behavior.
83
+ **EXECUTION**: Bash for code/git/npm/docker/python. agent-browser skill for browser/UI workflows. Rules: ≤15s per run. Pack every related hypothesis per run. No temp files. No mocks. Real data only.
101
84
 
102
85
 
103
86
  ## CHARTER 3: GROUND TRUTH
@@ -109,7 +92,6 @@ Real services, real timing, zero black magic. Discover mocks/stubs/fixtures →
109
92
  **CLI VALIDATION** (mandatory for CLI changes):
110
93
  - PRE-EMIT: Run CLI from source, capture output.
111
94
  - POST-EMIT: Run modified CLI from disk, verify all commands.
112
- - Examples: `./build/gm-cc/cli.js --version` (exit 0), `npm pack` (tarball created).
113
95
  - Document: command, actual output, exit code.
114
96
 
115
97
 
@@ -187,20 +169,7 @@ Never report complete with uncommitted/unpushed changes.
187
169
 
188
170
  ## CHARTER 9: PROCESS MANAGEMENT
189
171
 
190
- **ALL APPLICATIONS RUN VIA PM2.** Direct invocations (node, bun, python, npx) forbidden.
191
-
192
- **Pre-start**: `pm2 jlist`. If online: observe `pm2 logs <name>`. If stopped: restart. Only start if not found. Never duplicate.
193
-
194
- **PM2 config** (all processes): `autorestart: false, watch: ["src", "config"], ignore_watch: ["node_modules", ".git", "logs"], watch_delay: 1000`
195
-
196
- **Cross-platform**:
197
- - Windows: use `interpreter: "cmd", interpreter_args: "/c"` for npm scripts; resolve actual .js for globals; all spawned subprocesses need `windowsHide: true`
198
- - WSL polling: `watch_options: { usePolling: true, interval: 1000 }` for /mnt/c paths
199
- - Watch exhaustion: `echo fs.inotify.max_user_watches=524288 | sudo tee -a /etc/sysctl.conf && sudo sysctl -p`
200
-
201
- **Logs**: `pm2 logs <name>` (stream) | `pm2 logs <name> --lines 100` (last N) | `pm2 logs <name> --err` (errors only)
202
-
203
- **Cleanup**: `pm2 delete <name>` when complete. Not `stop`. Never leave orphaned. Ref `process-management` skill.
172
+ All applications run via process-management skill. Never direct invocations (node, bun, python, npx). Pre-start: check running processes. Cleanup: delete orphaned when complete. Ref process-management skill for config, cross-platform, logs, lifecycle.
204
173
 
205
174
  ## CONSTRAINTS
206
175
 
package/gemini-extension.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "gm",
3
- "version": "2.0.83",
3
+ "version": "2.0.84",
4
4
  "description": "State machine agent with hooks, skills, and automated git enforcement",
5
5
  "author": "AnEntrypoint",
6
6
  "homepage": "https://github.com/AnEntrypoint/gm",
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "gm-gc",
3
- "version": "2.0.83",
3
+ "version": "2.0.84",
4
4
  "description": "State machine agent with hooks, skills, and automated git enforcement",
5
5
  "author": "AnEntrypoint",
6
6
  "license": "MIT",
package/skills/gm/SKILL.md CHANGED
@@ -33,12 +33,12 @@ enforce: critical
33
33
 
34
34
  | State | Action | Exit Condition |
35
35
  |-------|--------|---|
36
- | **PLAN** | Build `./.prd` (planning skill): enumerate every possible edge case, test scenario, dependency. Frozen at creation. | `.prd` written, all unknowns named |
37
- | **EXECUTE** | Run every possible code execution (≤15s, densely packed). Launch ≤3 parallel gm:gm per wave. Assign witnessed values to mutables. Browser changes: agent-browser PoC. | Zero unresolved mutables |
38
- | **PRE-EMIT-TEST** | Execute every possible hypothesis before file changes (success/failure/edge). Browser changes: agent-browser workflows. | All hypotheses proven, real output confirms approach, zero failures. **BLOCKING GATE** |
36
+ | **PLAN** | Build `./.prd`: enumerate every possible edge case, test scenario, dependency. Frozen at creation. | `.prd` written, all unknowns named |
37
+ | **EXECUTE** | Run every possible code execution (≤15s, densely packed). Launch ≤3 parallel gm:gm per wave. Assign witnessed values to mutables. | Zero unresolved mutables |
38
+ | **PRE-EMIT-TEST** | Execute every possible hypothesis before file changes (success/failure/edge). | All hypotheses proven, real output confirms approach, zero failures. **BLOCKING GATE** |
39
39
  | **EMIT** | Write files. **IMMEDIATE NEXT STEP**: POST-EMIT-VALIDATION (no pause). | Files written |
40
- | **POST-EMIT-VALIDATION** | Execute ACTUAL modified disk code (fs.readFileSync verify). Real data. Browser: agent-browser on modified files. | Modified disk code executed, witnessed output, zero failures, real data tested. **BLOCKING GATE** |
41
- | **VERIFY** | E2E system test. Real execution witnessed. Browser: full agent-browser workflows. | `witnessed_execution=true` on actual system |
40
+ | **POST-EMIT-VALIDATION** | Execute ACTUAL modified disk code. Real data. All scenarios tested. | Modified disk code executed, witnessed output, zero failures. **BLOCKING GATE** |
41
+ | **VERIFY** | Real system E2E test. Witnessed execution. | `witnessed_execution=true` on actual system |
42
42
  | **GIT-PUSH** | Only after VERIFY. `git add -A && git commit && git push` | Push succeeds |
43
43
  | **COMPLETE** | All gates passed, push done, zero user steps remaining | `gate_passed=true && user_steps=0` |
44
44
 
@@ -73,33 +73,16 @@ All execution: Bash tool or `agent-browser` skill. Every hypothesis proven by ex
73
73
  **BLOCKED** (pre-tool-use-hook enforces): Task:explore, Glob, Grep, WebSearch for code, Bash grep/find/cat on source, Puppeteer/Playwright.
74
74
 
75
75
  **TOOL MAPPING**:
76
- - **Code exploration** (ONLY): `code-search` skill (semantic, 102 types, natural language, line numbers)
77
- - **Code execution**: Bash (`node -e`, `bun -e`, `python -c`, git, npm, docker, systemctl only)
76
+ - **Code exploration** (ONLY): code-search skill
77
+ - **Code execution**: Bash (node, bun, python, git, npm, docker, systemctl only)
78
78
  - **File ops**: Read/Write/Edit (known paths); Bash (inline)
79
- - **Browser**: `agent-browser` skill (no puppeteer/playwright)
79
+ - **Browser**: agent-browser skill
80
80
 
81
81
  **EXPLORATION**: (1) code-search natural language (always first) → (2) multiple queries (faster than CLI) → (3) use returned line numbers + Read → (4) Bash only after 5+ code-search fails → (5) known path = Read directly.
82
82
 
83
83
  **BASH WHITELIST**: `node`, `python`, `bun`, `npm`, `git`, `docker`, `systemctl` (ONLY). No builtins (ls, cat, grep, find, echo, cp, mv, rm, sed, awk)—use inline code instead. No spawn/exec/fork.
84
84
 
85
- **CODE EXECUTION PATTERNS**:
86
- ```bash
87
- bun -e "const fs=require('fs'); console.log(fs.readdirSync('.'))"
88
- bun -e "require('fs').writeFileSync('out.json', JSON.stringify({x:1}, null, 2))"
89
- node script.js && git status
90
- python -c "import json; print(json.dumps({'ok': True}))"
91
- ```
92
- Rules: ≤15s per run. Pack every related hypothesis per run. No temp files. No spawn/exec/fork.
93
-
94
- **BROWSER EXECUTION PATTERNS** (agent-browser):
95
- ```javascript
96
- await browser.goto('http://localhost:3000/form');
97
- await browser.fill('input[name="email"]', 'test@example.com');
98
- await browser.click('button[type="submit"]');
99
- const errorMsg = await browser.textContent('.error-message');
100
- console.log('Validation shown:', errorMsg); // witnessed proof
101
- ```
102
- Rules: ≤15s per run. Pack every hypothesis. No mocks. Real application. Witness behavior.
85
+ **EXECUTION**: Bash for code/git/npm/docker/python. agent-browser skill for browser/UI workflows. Rules: ≤15s per run. Pack every related hypothesis per run. No temp files. No mocks. Real data only.
103
86
 
104
87
 
105
88
  ## CHARTER 3: GROUND TRUTH
@@ -111,7 +94,6 @@ Real services, real timing, zero black magic. Discover mocks/stubs/fixtures →
111
94
  **CLI VALIDATION** (mandatory for CLI changes):
112
95
  - PRE-EMIT: Run CLI from source, capture output.
113
96
  - POST-EMIT: Run modified CLI from disk, verify all commands.
114
- - Examples: `./build/gm-cc/cli.js --version` (exit 0), `npm pack` (tarball created).
115
97
  - Document: command, actual output, exit code.
116
98
 
117
99
 
@@ -189,20 +171,7 @@ Never report complete with uncommitted/unpushed changes.
189
171
 
190
172
  ## CHARTER 9: PROCESS MANAGEMENT
191
173
 
192
- **ALL APPLICATIONS RUN VIA PM2.** Direct invocations (node, bun, python, npx) forbidden.
193
-
194
- **Pre-start**: `pm2 jlist`. If online: observe `pm2 logs <name>`. If stopped: restart. Only start if not found. Never duplicate.
195
-
196
- **PM2 config** (all processes): `autorestart: false, watch: ["src", "config"], ignore_watch: ["node_modules", ".git", "logs"], watch_delay: 1000`
197
-
198
- **Cross-platform**:
199
- - Windows: use `interpreter: "cmd", interpreter_args: "/c"` for npm scripts; resolve actual .js for globals; all spawned subprocesses need `windowsHide: true`
200
- - WSL polling: `watch_options: { usePolling: true, interval: 1000 }` for /mnt/c paths
201
- - Watch exhaustion: `echo fs.inotify.max_user_watches=524288 | sudo tee -a /etc/sysctl.conf && sudo sysctl -p`
202
-
203
- **Logs**: `pm2 logs <name>` (stream) | `pm2 logs <name> --lines 100` (last N) | `pm2 logs <name> --err` (errors only)
204
-
205
- **Cleanup**: `pm2 delete <name>` when complete. Not `stop`. Never leave orphaned. Ref `process-management` skill.
174
+ All applications run via process-management skill. Never direct invocations (node, bun, python, npx). Pre-start: check running processes. Cleanup: delete orphaned when complete. Ref process-management skill for config, cross-platform, logs, lifecycle.
206
175
 
207
176
  ## CONSTRAINTS
208
177