gm-skill 2.0.1547 → 2.0.1548

package/AGENTS.md

@@ -140,9 +140,7 @@ Every possible skill's `allowed-tools:` frontmatter is reduced to `Skill, Read,
 
 **rs-learn observability**: every learning-pipeline state change emits a structured `evt:{event,sess,ts,...}` line into `.gm/exec-spool/.watcher.log` + gm-log; recall replies carry `mode`/`namespace`/`derived_query`/per-hit `score`; gmsniff/ccsniff expose the taxonomy. Learning quality is observable, not a black box. Full event taxonomy + flag list in rs-learn (`recall: rs-learn observability taxonomy`).
 
-**SKILL.md auto-refresh**: `bootstrapPlugkit` sha256-compares the bundled SKILL.md against installed copies and atomically rewrites on mismatch, so the agent always sees the latest prose. Mechanism detail in rs-learn (`recall: SKILL.md auto-refresh`).
-
-**Skill-initiated bootstrap contract**: `lib/skill-bootstrap.js::bootstrapPlugkit(sessionId)` initializes wasm for skill-driven dispatch without hooks; failures are non-fatal (degraded fallback). Mechanism detail in rs-learn (`recall: skill-initiated bootstrap contract`).
+**Bootstrap contract (skill-init + SKILL.md auto-refresh + project wiring)**: `bootstrapPlugkit`/`ensureReady` initialize wasm hook-free (failures non-fatal), sha256-rewrite stale installed SKILL.md, and seed per-project `CLAUDE.md` (`@AGENTS.md`) + `.gm/next-step.md` — the wiring must live in `gm-plugkit/bootstrap.js::ensureReady` (the consumer-project watcher boot path), not only repo-root `bin`/`lib`. Detail in rs-learn (`recall: skill-initiated bootstrap contract`, `recall: SKILL.md auto-refresh`).
 
 ## Cascade pipeline
 
@@ -166,7 +164,7 @@ Orchestration state is tracked via `.gm/` marker files, not hook events; the CLI
 
 **Dead-watcher recovery uses `bun x gm-plugkit@latest spool`, never direct-node boot** (mechanism + wrapper-deploy verification in rs-learn: `recall: dead-watcher recovery bun x not direct-node`).
 
-**The first verb after a genuine multi-minute IDLE is `instruction`, to reset the long-gap clock** (mechanism in rs-learn: `recall: first verb after multi-minute wait instruction long-gap`). The gate fires on genuine idle only -- both >300s since the last instruction AND >300s since the previous dispatch of any verb -- so active back-to-back work verbs (a browser-heavy debugging stretch, a fan-out of exec/codesearch) keep the chain alive without an interleaved `instruction`; you do not inject defensive instruction dispatches between active work. A true wait (version download, overnight, long external CI watch with no dispatches) still trips it, and there the first verb back is `instruction`.
+**The first verb after a genuine multi-minute IDLE is `instruction`, to reset the long-gap clock** (mechanism in rs-learn: `recall: first verb after multi-minute wait instruction long-gap`). The gate fires on genuine idle only -- both >300s since the last instruction AND >300s since the previous dispatch of any verb -- so active back-to-back work verbs (a browser-heavy debugging stretch, a fan-out of exec/codesearch) keep the chain alive without an interleaved `instruction`; you do not inject defensive instruction dispatches between active work. A true wait (version download, overnight, long external CI watch with no dispatches) still trips it, and there the first verb back is `instruction`. When the wait is self-inflicted and predictable -- a blocking `TaskOutput`/`gh run watch` on a multi-minute workflow or CI run you yourself launched -- dispatch `instruction` immediately BEFORE entering the wait, not only after: prevention resets the clock so a sub-300s tail never trips the gate, where recovery-after only cleans up a deviation that already fired.
 
 **A stop-hook firing on a terminal chain does not authorize re-polling**: when a stop-hook or unsatisfiable condition fires while the chain is already at `phase=COMPLETE` AND `prd_pending_count=0`, re-dispatching `instruction` or `phase-status` to "re-confirm" terminality is itself a deviation, it emits `deviation.complete-chain-poll` (`instructions/mod.rs`) and marks the agent as polling a closed chain. COMPLETE already authorizes the prose-only turn; the hook cannot be satisfied by more poll dispatches over elapsed work, and re-running already-committed work to manufacture skill-driven activity is the fabrication `Nothing Fake` forbids. Two admissible responses only: (a) a prose-only turn (the COMPLETE pronouncement is in hand), or (b) genuinely new planned work opened with a FRESH `{"prompt":...}` body, which resets phase to PLAN and is driven through the skill from inception. Repeatedly answering the same already-acknowledged hook is a loop; state the terminal facts once and stop, or open new work.
 

package/gm-plugkit/bootstrap.js

@@ -74,6 +74,55 @@ function clearBootstrapError() {
   } catch (_) {}
 }
 
+function ensureNextStepWiring(cwd) {
+  const changes = [];
+  const gmDir = path.join(cwd, '.gm');
+  try { fs.mkdirSync(gmDir, { recursive: true }); }
+  catch (e) { obsEvent('bootstrap', 'next-step.wiring.target-failed', { target: gmDir, error: e.message }); }
+
+  const nextStepPath = path.join(gmDir, 'next-step.md');
+  const nextStepBody = '# Next step\n\nDispatch the `instruction` verb to plugkit by writing `.gm/exec-spool/in/instruction/<N>.txt` (any unique N) with body `{}` (or `{"prompt":"<user request>"}` on the first dispatch of the turn). Read the response from `.gm/exec-spool/out/<N>.json` and follow the imperative in the `instruction` field.\n\nThis file is auto-rewritten by plugkit on every instruction dispatch.\n';
+  try {
+    if (!fs.existsSync(nextStepPath)) {
+      fs.writeFileSync(nextStepPath, nextStepBody);
+      changes.push('seeded .gm/next-step.md');
+    }
+  } catch (e) { obsEvent('bootstrap', 'next-step.wiring.target-failed', { target: nextStepPath, error: e.message }); }
+
+  const claudeMdPath = path.join(cwd, 'CLAUDE.md');
+  try {
+    if (!fs.existsSync(claudeMdPath)) {
+      fs.writeFileSync(claudeMdPath, '@AGENTS.md\n');
+      changes.push('created CLAUDE.md');
+    } else {
+      const cur = fs.readFileSync(claudeMdPath, 'utf8');
+      const hasLine = cur.split(/\r?\n/).some(l => l.trim() === '@AGENTS.md');
+      if (!hasLine) {
+        fs.writeFileSync(claudeMdPath, '@AGENTS.md\n' + cur);
+        changes.push('prepended @AGENTS.md to CLAUDE.md');
+      }
+    }
+  } catch (e) { obsEvent('bootstrap', 'next-step.wiring.target-failed', { target: claudeMdPath, error: e.message }); }
+
+  const agentsMdPath = path.join(cwd, 'AGENTS.md');
+  try {
+    if (fs.existsSync(agentsMdPath)) {
+      const cur = fs.readFileSync(agentsMdPath, 'utf8');
+      const hasLine = cur.split(/\r?\n/).some(l => l.trim() === '@.gm/next-step.md');
+      if (!hasLine) {
+        const sep = cur.endsWith('\n') ? '' : '\n';
+        fs.writeFileSync(agentsMdPath, cur + sep + '\n@.gm/next-step.md\n');
+        changes.push('appended @.gm/next-step.md to AGENTS.md');
+      }
+    }
+  } catch (e) { obsEvent('bootstrap', 'next-step.wiring.target-failed', { target: agentsMdPath, error: e.message }); }
+
+  if (changes.length > 0) {
+    log(`next-step wiring: ${changes.join(', ')}`);
+    obsEvent('bootstrap', 'next-step.wiring.applied', { changes });
+  }
+}
+
 
 function cacheRoot() {
   const home = os.homedir();
@@ -812,6 +861,8 @@ async function ensureReady(opts) {
   opts = opts || {};
   const offline = opts.offline === true;
 
+  try { ensureNextStepWiring(process.env.CLAUDE_PROJECT_DIR || process.cwd()); } catch (_) {}
+
   if (!offline) {
     try {
       const selfStale = await probeSelfStaleness(2500);
@@ -1000,6 +1051,7 @@ function startSpoolDaemon() {
 module.exports = {
   bootstrap,
   ensureReady,
+  ensureNextStepWiring,
   gmToolsDir,
   getWasmPath,
   getBinaryPath,

package/gm-plugkit/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-plugkit",
-  "version": "2.0.1547",
+  "version": "2.0.1548",
   "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": "2.0.1547",
+  "version": "2.0.1548",
   "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": "2.0.1547",
+  "version": "2.0.1548",
   "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",