gm-cc 2.0.674 → 2.0.676

package/.claude-plugin/marketplace.json

@@ -4,7 +4,7 @@
     "name": "AnEntrypoint"
   },
   "description": "State machine agent with hooks, skills, and automated git enforcement",
-  "version": "2.0.674",
+  "version": "2.0.676",
   "metadata": {
     "description": "State machine agent with hooks, skills, and automated git enforcement"
   },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-cc",
-  "version": "2.0.674",
+  "version": "2.0.676",
   "description": "State machine agent with hooks, skills, and automated git enforcement",
   "author": "AnEntrypoint",
   "license": "MIT",

package/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "gm",
-  "version": "2.0.674",
+  "version": "2.0.676",
   "description": "State machine agent with hooks, skills, and automated git enforcement",
   "author": {
     "name": "AnEntrypoint",

package/skills/gm-emit/SKILL.md

@@ -22,6 +22,7 @@ For every claim landing in a file:
 2. **Repair legality** — local patch dressed as structural repair? Downgrade scope or snake to PLAN.
 3. **Lawful downgrade** — can a weaker, true statement replace it? PREFER the downgrade.
 4. **Alternative-route suppression** — live competing route being silenced? Preserve it.
+5. **Strongest objection** — if a reviewer pushed back on this change, what would the sharpest argument be? Articulate it. Cannot articulate = have not understood the alternatives = regress to `gm-execute`.
 
 Fail any → regress to `gm-execute` to witness what was missing, or `planning` if gap is structural.
 
@@ -56,6 +57,7 @@ console.log(await fn(realInput));
 - Post-emit matches pre-emit exactly
 - Hot reloadable; errors throw with context (no fallbacks, `|| default`, `catch { return null }`)
 - No mocks/fakes/stubs/scattered test files (delete on discovery)
+- Behavior change in this emit = a corresponding assertion in test.js (a change no test would catch is a change you cannot prove)
 - Files ≤200 lines
 - No duplicate concern (run exec:codesearch for primary concern after writing; any overlap → `planning`)
 - No comments; no hardcoded values; no adjectives in identifiers; no unnecessary files

package/skills/gm-execute/SKILL.md

@@ -32,9 +32,11 @@ Unresolved after 2 passes = regress to `planning`. Never narrate past an unresol
 Route candidates from PLAN = `weak_prior` only. Plausibility = right to TEST, not BELIEVE.
 weak_prior → witnessed probe → witnessed → feed to EMIT. "The plan says" / "obviously X" = prior, not fact.
 
-## LOAD-WEIGHTED VERIFICATION
+Claims in response prose stand or fall by their last witness. A claim with no witness in this session is a hypothesis, not a finding — say so when you state it, and say what would settle it. The next reader (you, next turn) needs to know which lines were earned and which were carried forward.
 
-Budget: spend on `.prd` items in descending order of `load × (1 − tier_confidence)`. Items with `load>0.75` MUST reach `confirmed` tier before EMIT. Items with `load>0.50` need a downgrade plan recorded.
+## VERIFICATION BUDGET
+
+Spend on `.prd` items in descending order of consequence-if-wrong × distance-from-witnessed. Items whose failure would collapse the headline finding must reach witnessed status before EMIT; items with sub-argument-level consequence need at minimum a stated fallback path.
 
 ## CODE EXECUTION