gm-oc 2.0.403 → 2.0.404

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-oc",
-  "version": "2.0.403",
+  "version": "2.0.404",
   "description": "State machine agent with hooks, skills, and automated git enforcement",
   "author": "AnEntrypoint",
   "license": "MIT",

package/skills/gm/SKILL.md

@@ -141,13 +141,15 @@ These rules apply to ALL phases. Violations trigger immediate snake to planning.
 - Clean ALL files not required for the program to function
 
 **CODE QUALITY**:
-- ALWAYS scan codebase (exec:codesearch) before editing to find existing implementations — resolve duplicates immediately, NEVER duplicate existing functionality
-- DRY/clean/generalized/forward-thinking architecture — immediately solve architectural issues, CONTINUOUSLY reorganize to be maximally concise/simple without losing functionality
-- Every extra symbol = technical debt — enforce clean short concise functional code
-- ALWAYS write dynamic/modular code using ground truth — ZERO hardcoded values
+- ALWAYS scan codebase (exec:codesearch) before editing — find everything that touches the same concern
+- **Duplicate concern = snake to planning**: overlapping responsibility, similar logic in different places, parallel implementations, or code that could be consolidated. Snake to `planning` with consolidation instructions
+- After every file write: run exec:codesearch for the primary function/concern you just wrote. If ANY other code serves the same concern → snake to `planning` with consolidation instructions. This is not optional — it is a gate
+- When a native feature, stdlib function, or convention replaces custom code → delete the custom code. When it would add code → do not use it
+- When a naming convention, directory structure, or auto-discovery pattern can replace explicit registration or configuration → replace it
+- ZERO hardcoded values — all values derived from ground truth, config, or convention
 - NO adjectives/descriptive language in code (variable/function names must be terse and functional)
 - No mocks/simulations/fallbacks/hardcoded/fake elements — delete on discovery
-- Set client-side debugging globals to make ALL client-side data accessible via simple REPL (window.__debug or similar)
+- Client-side code: expose all state via debug globals (window.__debug or similar)
 
 **ERROR HANDLING**:
 - Every error must throw and propagate with clear context
@@ -159,17 +161,17 @@ These rules apply to ALL phases. Violations trigger immediate snake to planning.
 - Check git history (`git log`, `git diff`) for troubleshooting known regressions — never revert, use differential comparisons and edit new code manually
 - Keep execution logs concise (<4k chars ideal, 30k max)
 - Clear cache before playwright/browser debugging
-- Test locally when possible over live
 
-**DOCUMENTATION**:
-- CLAUDE.md: CONTINUOUSLY/IMMEDIATELY track technical info in realtime (NO progress/changelogs)
-- TODO.md: CONTINUOUSLY track persistent todos — MUST completely clear/empty/delete before stopping
-- CHANGELOG.md: CONTINUOUSLY append concise change summaries
-- Deploy if deployable, publish to npm if package is on npm
+**DOCUMENTATION** (update at every phase transition, not at the end):
+- CLAUDE.md: after each structural change, update technical info. NO progress/changelogs
+- TODO.md: add items when discovered, remove when done. File must not exist at completion
+- CHANGELOG.md: append entry after each commit
+- After push: deploy if deployable, publish if npm package
 
 **PROCESS**:
 - Only persistent background shells for long-running CLI processes
-- Manual testing ONLY — NO test files ever
+- Test via exec: and browser skill — NO test files ever
+- Test locally before live
 
 ## CONSTRAINTS
 
@@ -178,6 +180,6 @@ These rules apply to ALL phases. Violations trigger immediate snake to planning.
 **Tier 2**: no_duplication, no_hardcoded_values, modularity
 **Tier 3**: no_comments, convention_over_code
 
-**Never**: `Bash(node/npm/npx/bun)` | skip planning | sequential independent items | screenshot before JS exhausted | narrate past unresolved mutables | stop while .prd has items | ask the user what to do next while work remains | create fallback/demo modes | silently swallow errors | duplicate existing code | leave comments | create test files
+**Never**: `Bash(node/npm/npx/bun)` | skip planning | sequential independent items | screenshot before JS exhausted | narrate past unresolved mutables | stop while .prd has items | ask the user what to do next while work remains | create fallback/demo modes | silently swallow errors | duplicate concern | leave comments | create test files | leave stale architecture when changes reveal restructuring opportunity
 
-**Always**: invoke named skill at every transition | snake to planning on any new unknown | witnessed execution only | scan codebase before edits | keep going until .prd deleted and git clean
+**Always**: invoke named skill at every transition | snake to planning on any new unknown | snake to planning when duplicate concern or restructuring opportunity discovered | witnessed execution only | scan codebase before edits | keep going until .prd deleted and git clean

package/skills/gm-complete/SKILL.md

@@ -127,8 +127,8 @@ Before declaring complete, sweep the entire codebase for violations:
 3. **Test files** (.test.js, .spec.js, __tests__/) → delete
 4. **Mock/stub/simulation files** → delete
 5. **Unnecessary doc files** (not CHANGELOG/CLAUDE/README/TODO.md) → delete
-6. **Duplicate code** → consolidate
-7. **Hardcoded values** → extract to config/constants
+6. **Duplicate concern** (overlapping responsibility, similar logic, parallel implementations, consolidatable code) → snake to `planning` with restructuring instructions — do not patch locally
+7. **Hardcoded values** → derive from ground truth, config, or convention
 8. **Fallback/demo modes** → remove, fail loud instead
 9. **TODO.md** → must be empty/deleted before completion
 10. **CHANGELOG.md** → must have entries for this session's changes

package/skills/gm-emit/SKILL.md

@@ -74,7 +74,7 @@ Pre-emit revealing unexpected behavior → new unknown → snake to `planning`.
 - Errors throw with clear context — no fallbacks, demo modes, silent swallowing, `|| default`, `catch { return null }`
 - No mocks/fakes/stubs/simulations/test files anywhere — delete on discovery
 - Files ≤200 lines — split immediately if over, do not advance
-- No duplicate code — scan codebase for existing implementations before writing
+- No duplicate concern — after writing, run exec:codesearch for the primary concern. If ANY other code serves the same concern → do NOT advance, snake to `planning` with consolidation instructions
 - No comments — remove any found
 - No hardcoded values — dynamic/modular code using ground truth only
 - No adjectives/descriptive language in variable/function names
@@ -99,7 +99,7 @@ Invoke `browser` skill. Escalation: (1) `exec:browser\n<js>` → (2) `browser` s
 
 ## SELF-CHECK (before and after each file)
 
-File ≤200 lines | No duplication | Pre-emit passed | No mocks | No comments | Docs match | All spotted issues fixed
+File ≤200 lines | No duplicate concern | Pre-emit passed | No mocks | No comments | Docs match | All spotted issues fixed
 
 ## DO NOT STOP
 

package/skills/gm-execute/SKILL.md

@@ -116,7 +116,7 @@ Invoke `browser` skill. Escalation — exhaust each before advancing:
 
 Real services, real data, real timing. Mocks/fakes/stubs/simulations = delete immediately. No .test.js/.spec.js. Delete on discovery. No fallback/demo modes — errors must fail loud with clear logs.
 
-**SCAN BEFORE EDIT**: Before modifying or creating any file, search the codebase (exec:codesearch) for existing implementations of the same functionality. Resolve duplicates immediately — NEVER duplicate existing code.
+**SCAN BEFORE EDIT**: Before modifying or creating any file, search the codebase (exec:codesearch) for existing implementations of the same concern. "Duplicate" means overlapping responsibility, similar logic, or parallel implementations — not just identical files. If consolidation is possible, snake to `planning` with restructuring instructions instead of continuing.
 
 **HYPOTHESIZE VIA EXECUTION**: Always troubleshoot and validate hypotheses through witnessed execution BEFORE editing files. Never edit based on assumptions — run the code first, observe the actual behavior, then edit with ground truth.
 

package/skills/planning/SKILL.md

@@ -39,7 +39,7 @@ Planning = exhaustive mutable discovery. For every aspect of the task ask:
 
 Categories of unknowns to enumerate: file existence | API shape | data format | dependency versions | runtime behavior | environment differences | error conditions | concurrency | integration points | backwards compatibility | rollback paths | deployment steps | verification criteria
 
-**MANDATORY CODEBASE SCAN**: Before planning any new implementation, search (exec:codesearch) for existing code that already does what you need. Add `existingImpl=UNKNOWN` mutable for every new feature — resolve by searching. Duplicating existing functionality is a Tier 2 violation.
+**MANDATORY CODEBASE SCAN**: For every planned item, add `existingImpl=UNKNOWN` mutable. Resolve by running exec:codesearch for the concern (not the implementation). If existing code serves the same concern → the .prd item becomes a consolidation task, not an addition. The plan restructures existing code to absorb the new requirement — never bolt new code alongside existing code that does related work.
 
 ## .PRD FORMAT