gm-skill 2.0.1756 → 2.0.1757

package/AGENTS.md

@@ -88,6 +88,8 @@ Plugkit = stateful library the agent drives by verb dispatch -- never autonomous
 
 Every skill's `allowed-tools:` reduced to `Skill, Read, Write` (plus SKILL.md boot `Bash(bun *)`/`Bash(npx *)`); `Write` exclusively for spool dispatch. Every other side effect -- exec, git, browser, recall, memorize, codesearch -- routes spool -> plugkit. Never reach around plugkit; missing capability = new plugkit verb, not skill-side tool.
 
+**Subagent/Workflow-agent prompts delegate, never restate.** Any `Agent()` tool call or `Workflow` script `agent()`/`pipeline()`/`parallel()` call dispatching gm-driven work says only "use the gm skill for this" (or equivalent minimal pointer) plus the task-specific content -- target repo/path, what to investigate, what to report. Never inline verb names, spool paths, JSON body shapes, or phase-chain mechanics into the prompt string: `Skill(skill="gm")` already supplies all of that on invocation, so restating it is instructional content living outside plugkit+skill, the exact drift this file's own tool-surface rule exists to prevent. Applies identically to both surfaces -- a Workflow script author writing full gm-protocol prose into an `agent()` prompt is the same violation as an `Agent()` call doing it.
+
 ## Core Rules
 
 **Shared memory & search index are tracked, never ignored**: `.gm/rs-learn.db`, `.gm/code-search/` committed -- state shares cross-machine/session/CI. Never gitignore `.gm/`, `.gm/rs-learn.db`, `.gm/code-search/`, legacy `.code-search/`; transient `.gm/*` entries listed one-by-one between managed markers (parent-re-include caveat). Entry list + `ensureGitignored` mechanics: rs-learn (`recall: gm managed-gitignore mechanics`). Project-local persistent state -> `.gm/<name>/`, never top-level dotfile/dotdir.
@@ -150,13 +152,13 @@ Every skill's `allowed-tools:` reduced to `Skill, Read, Write` (plus SKILL.md bo
 
 Push to any rs-* sibling -> `cascade.yml` -> rs-plugkit `release.yml` -> single `plugkit.wasm` (npm `plugkit-wasm` + `plugkit-bin` Releases) -> auto-bump `gm.json::plugkitVersion` -> `publish.yml` ships gm-skill+gm-plugkit+SKILL.md mirror. Step sequence + PUBLISHER_TOKEN: rs-learn (`recall: cascade pipeline`).
 
-**Repos involved (push to any triggers cascade):** `AnEntrypoint/{rs-exec, rs-codeinsight, rs-search, rs-plugkit, rs-learn, gm}` -- rs-plugkit Cargo.toml = version source-of-truth, gm.json holds plugkitVersion. Three npm packages ship: `gm-skill`, `gm-plugkit`, `plugkit-wasm`. Per-repo roles + legacy-retirement: rs-learn (`recall: cascade repos involved roles`, `recall: legacy gm-skill variants retired`).
+**Repos involved (push to any triggers cascade):** `AnEntrypoint/{rs-exec, rs-codeinsight, rs-search, rs-plugkit, rs-learn, gm}`. Roles, npm package names, legacy-retirement detail: rs-learn (`recall: cascade repos involved roles`, `recall: legacy gm-skill variants retired`).
 
 **To update every possible thing**: push to the relevant repo. No manual version bumps, no local `cargo update`/`cargo build` -- push, let CI build.
 
 ## Spool-dispatch architecture replaces hooks
 
-Orchestration state tracked via `.gm/` marker files, not hook events; CLI's `checkDispatchGates()` gates Write/Edit/git pre-execution. Marker set (`prd.yml, mutables.yml, needs-gm, gm-fired-<sessionId>, residual-check-fired`) + SpoolDispatcher mechanism: rs-learn (`recall: gate enforcement layer`, `recall: spool dispatch gates marker files`).
+Orchestration state tracked via `.gm/` marker files, not hook events; CLI's `checkDispatchGates()` gates Write/Edit/git pre-execution. Marker set + SpoolDispatcher mechanism: rs-learn (`recall: gate enforcement layer`, `recall: spool dispatch gates marker files`).
 
 **gm tool-use sequencing**: `Skill(skill="gm")` clears needs-gm gate. One shipped skill, no subagent variant. Marker mechanics: rs-learn (`recall: gm-skill tool-use sequencing mechanics`).
 

package/gm-plugkit/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-plugkit",
-  "version": "2.0.1756",
+  "version": "2.0.1757",
   "description": "Bootstrap and daemon-spawn tool for gm plugkit binary. Downloads the correct platform binary, verifies SHA256, and starts the spool watcher daemon. Includes plugkit-wasm-wrapper for WASM-based spool watching.",
   "main": "index.js",
   "bin": {

package/gm.json

@@ -1,6 +1,6 @@
 {
   "name": "gm",
-  "version": "2.0.1756",
+  "version": "2.0.1757",
   "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": "2.0.1756",
+  "version": "2.0.1757",
   "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",

package/skills/gm/SKILL.md

@@ -91,7 +91,9 @@ Chain isn't COMPLETE until changes are on origin. Commit+push at end of every se
 
 **CONSOLIDATE is git consolidation + CI/CD validation, the closing phase before COMPLETE.** Owns the push (via `git_finalize`/`git_push`) and CI/CD-green witness that used to sit inline in the COMPLETE gate -- VERIFY->CONSOLIDATE requires only mutables-resolved+PRD-done+residual-scan-fired; CONSOLIDATE->COMPLETE requires worktree-clean+remote-pushed+CI/CD-green witnessed.
 
-**Memory is project-resident, never platform-resident.** Refuse the platform's own auto-memory dir (`~/.claude/projects/*/memory/`, `~/.codex/`, `~/.cursor/*`) -- doesn't transport, invisible to gmsniff/recall. Two portable surfaces: (a) `memorize-fire` through spool (embeds `.gm/rs-learn.db`, surfaces via `recall`+auto-recall); (b) `AGENTS.md` for project-tracked hard rules, edited inline. Complementary -- memorize-fire for recall-time reinforcement, AGENTS.md for the hard rule. About to Write under a platform memory dir: stop, dispatch `memorize-fire` instead. Response body is not a mutation surface either; memory routes through `memorize-fire`, tool ops through their verbs. **Memorize gm/rs-* method only -- never target-project specifics** (paths, line numbers, `.gm/prd.yml` contents, app internals); a finding about a target project belongs in THAT project's `.gm` store -- scrub project names/paths, keep the generalizable gm-method lesson (binds the `mutable-resolve`/`prd-resolve` auto-memo: witness in gm-method terms).
+**Memory is project-resident, never platform-resident.** Refuse the platform's own auto-memory dir (`~/.claude/projects/*/memory/`, `~/.codex/`, `~/.cursor/*`) -- doesn't transport, invisible to gmsniff/recall. `memorize-fire` through spool (embeds `.gm/rs-learn.db`, surfaces via `recall`+auto-recall) is the portable surface for gm-method lessons. A driven project's own AGENTS.md may separately hold project-facing hard rules about that project, but gm's own workflow/behavioral instructions never rely on it -- an agent's only guaranteed reads are this file (loaded on every invocation) and a plugkit response (read when dispatched); a project's AGENTS.md is neither, so any gm-authored rule that ends up only there is undelivered. About to Write under a platform memory dir: stop, dispatch `memorize-fire` instead. Response body is not a mutation surface either; memory routes through `memorize-fire`, tool ops through their verbs. **Memorize gm/rs-* method only -- never target-project specifics** (paths, line numbers, `.gm/prd.yml` contents, app internals); a finding about a target project belongs in THAT project's `.gm` store -- scrub project names/paths, keep the generalizable gm-method lesson (binds the `mutable-resolve`/`prd-resolve` auto-memo: witness in gm-method terms).
+
+**Transferable topic-specific rules route to `discipline-note`, not `memorize-fire`.** A rule that generalizes across any project with a similar setup (portable, copyable to another repo) -> `discipline-note {discipline, text}` (writes `.gm/disciplines/<name>/policy.md`, terse-gated + deduped); `instruction`'s response surfaces active policy automatically. A fact tied to this project only -> `memorize-fire` as before.
 
 **Suppress mundane output; strip to the bone.** Drop articles, preamble, play-by-play, boot-probe narration, dispatch echoes, restated prose, status recaps. Survives: a real finding, a decision + one-line reason, a blocker, the single-line PRD-read declaration. Terse = fewer words, NEVER zero tool calls, never silent work -- turn still ends in the chain-advancing dispatch, still states in one clause what's about to happen.
 
@@ -110,3 +112,5 @@ Deslop: ∀x: x∈StronglyNormalized ∧ x∈Total ∧ x∈ConstantTime ∧ ¬
 Always maximize orthagnolatity across all surfaces
 
 If instructions imply more than one step, use or create a workflow, or track a goal; if subagents are available, fan out subagents that use gm for everything, up to 8 in parallel.
+
+**Subagent prompts delegate, never restate.** A dispatched subagent's own SKILL.md load is its instruction source -- prompt text says only "use the gm skill for this" plus the task (target, scope, report shape). Never inline verb names, spool paths, JSON shapes, or phase-chain mechanics into the prompt string; that's duplicating what invocation already supplies, the same class of drift as inlining `instruction`'s served prose here.