gm-skill 2.0.2459 → 2.0.2461

package/AGENTS.md

@@ -61,6 +61,8 @@ Record only non-obvious multi-run-cost caveats; prune stale; never document the
 
 **No changelog history in AGENTS.md.** Every entry is a present-tense rule about what must/must-not be the case in code now. Forbidden: `(FIXED)` markers, commit hashes, dated audit entries, `## Learning audit` sections, "(added 2026-...)" annotations, "we used to X, now Y". History belongs in `git log` and `CHANGELOG.md`.
 
+**A memo is prune-worthy, not durable, when it restates something the reader could get faster another way, or when it will go stale and mislead.** Three classes, checked on every `memorize-fire` and on sight in `.gm/memories/`: (a) config-derivable -- a value readable straight from `gm.config.json`/`graph.json`/any live config file belongs to that file, not a memo restating it; (b) trivially-discoverable-from-code -- a fact one `codesearch`/`Read` away needs no memory, since the code itself answers faster and can't drift out of sync with a stale copy; (c) state-of-tooling snapshot -- a specific version number, plugin-load state, or runtime status captured at one point in time will go stale and mislead a future session into treating it as still current. None of the three survive `memorize-prune`. What does survive: a debugging root-cause finding, a non-obvious invariant, or a cross-cutting method lesson -- each says something the source alone does not, and stays true regardless of when it is read.
+
 **Detail-heavy caveats live in the recall store (`.gm/memories/` corpus), not here.** Per-crate/OS/hook/workflow fact-base -> `recall`; AGENTS.md keeps top-level gm-repo-governing rules only. Cross-cutting policy stays; single-crate/single-platform mechanism drains.
 
 **gm's recall store (`.gm/memories/` project corpus) holds gm/rs-* method/tooling/invariants ONLY -- never target-project specifics.** A finding ABOUT a project gm merely drives ON (its paths, line numbers, `.gm/prd.yml`/`mutables.yml` contents, app internals, versions) belongs in THAT project's own `.gm` store -- pollutes every gm session's recall otherwise. Using gm != working on the driven project: scrub names/paths/state, keep only the generalizable gm-method lesson. Binds `mutable-resolve`/`prd-resolve` auto-memo too -- witness in gm-method terms, never by quoting foreign tree. (Code-side classifier reject rejected as too brittle -- false-rejects legit `.gm/prd.yml` mechanism citations -- so discipline + on-sight `memorize-prune` of foreign-specific memos is the enforcement.)

package/gm-plugkit/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-plugkit",
-  "version": "2.0.2459",
+  "version": "2.0.2461",
   "description": "Bootstrap and daemon-spawn tool for gm plugkit binary. Downloads the correct platform wasm, verifies SHA256, and launches agentplug-runner (the native wasm host) as the spool watcher daemon.",
   "main": "index.js",
   "bin": {

package/gm.json

@@ -1,6 +1,6 @@
 {
   "name": "gm",
-  "version": "2.0.2459",
+  "version": "2.0.2461",
   "description": "Spool-dispatch orchestration engine with unified state machine, skills, and automated git enforcement",
   "author": "AnEntrypoint",
   "license": "MIT",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-skill",
-  "version": "2.0.2459",
+  "version": "2.0.2461",
   "description": "Canonical universal harness — AI-native software engineering via skill-driven orchestration; bootstraps plugkit for task execution and session isolation. Install in any AI coding agent host.",
   "author": "AnEntrypoint",
   "license": "MIT",