gm-plugkit 2.0.1617 → 2.0.1619

package/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: gm-skill
+name: gm
 description: Plugkit-served instruction stream. Three-layer admission (witness, single-writer, direction) over every possible mutation; effort unbounded, never gated on cost. Closure on first emit; partial = non-monotonic.
 allowed-tools: Skill, Read, Write, Bash(bun *), Bash(npx *)
 ---

package/bootstrap.js

@@ -768,9 +768,9 @@ function ensureSkillMdFresh() {
   try {
     const candidates = [
       path.join(__dirname, 'SKILL.md'),
-      path.join(__dirname, '..', 'gm-skill', 'skills', 'gm-skill', 'SKILL.md'),
-      path.join(__dirname, '..', '..', 'gm-skill', 'skills', 'gm-skill', 'SKILL.md'),
-      path.join(__dirname, '..', 'skills', 'gm-skill', 'SKILL.md'),
+      path.join(__dirname, '..', 'gm-skill', 'skills', 'gm', 'SKILL.md'),
+      path.join(__dirname, '..', '..', 'gm-skill', 'skills', 'gm', 'SKILL.md'),
+      path.join(__dirname, '..', 'skills', 'gm', 'SKILL.md'),
     ];
     const bundledPath = candidates.find(p => {
       try { return fs.existsSync(p); } catch (_) { return false; }
@@ -787,9 +787,15 @@ function ensureSkillMdFresh() {
     const bundledHash = crypto.createHash('sha256').update(_norm(bundled)).digest('hex');
     const home = process.env.HOME || process.env.USERPROFILE || require('os').homedir();
     const targets = [
-      path.join(home, '.agents', 'skills', 'gm-skill', 'SKILL.md'),
-      path.join(home, '.claude', 'skills', 'gm-skill', 'SKILL.md'),
+      path.join(home, '.agents', 'skills', 'gm', 'SKILL.md'),
+      path.join(home, '.claude', 'skills', 'gm', 'SKILL.md'),
     ];
+    for (const legacy of [
+      path.join(home, '.agents', 'skills', 'gm-skill'),
+      path.join(home, '.claude', 'skills', 'gm-skill'),
+    ]) {
+      try { if (fs.existsSync(legacy)) fs.rmSync(legacy, { recursive: true, force: true }); } catch (_) {}
+    }
     const refreshed = [];
     for (const target of targets) {
       try {

package/instructions/emit.md

@@ -14,7 +14,7 @@ Feed search outputs into EMIT only when the digest matches the live filesystem;
 
 ## Write-then-verify
 
-One write per artifact, then a disk Read against every touched path to assert the change -- verified disk state IS the witness, not the tool-call return. On discrepancy, regress to root cause, do not retry.
+One write per artifact, then a disk Read against every touched path to assert the change -- you do not reason that the write succeeded, you run the read and witness it. Verified disk state IS the witness, not the tool-call return. On discrepancy, regress to root cause, do not retry.
 
 **Client-side artifacts: write-then-browser-witness, same turn.** If the artifact is `.html .js .jsx .ts .tsx .vue .svelte .mjs .css` or any browser-loaded path, the disk Read is necessary but not sufficient -- also dispatch a `browser` verb that `page.evaluate`s the invariant the artifact establishes (the page-side assertion is the real witness; the disk Read only witnesses serialization). Skipping it ships a green-checked stub. The COMPLETE gate refuses while any client-side file edited this session lacks its paired browser-witness (`deviation.client-edit-no-witness`, gates.rs); the missing witness is the next dispatch.
 

package/instructions/entry.md

@@ -41,11 +41,11 @@ The five phases are scheduling; the filter is the engine on every candidate, gat
 
 ## Token Discipline
 
-English describing intent is liability when code can encode it; comments are liability when names + structure encode the same; duplication that must sync is liability. Prose accomplishes the discipline by its structure, it does not narrate scenarios. Recognize the closure anti-shape by structure (a claim composed in prose displacing a dispatch). The response body is not a mutation surface.
+English describing intent is liability when code can encode it; comments are liability when names + structure encode the same; duplication that must sync is liability. The same economy governs reasoning: a thought you can run is liability when held as silent prose -- you reason by executing, not by narrating, so a hypothesis becomes a dispatch and its output is the conclusion. Prose accomplishes the discipline by its structure, it does not narrate scenarios. Recognize the closure anti-shape by structure (a claim composed in prose displacing a dispatch -- an unrun thought standing in for a witnessed one). The response body is not a mutation surface.
 
 ## Install
 
-`bun x skills add AnEntrypoint/gm-skill` -> `~/.agents/skills/<name>/SKILL.md` symlinked into `~/.claude/skills/<name>/`.
+`npx gm-skill install` copies the skill directory into `~/.claude/skills/gm/` (and `~/.agents/skills/gm/`), installed as `/gm`; `--yes` is the non-interactive form. No `skills` library.
 
 ## Bootstrap
 

package/instructions/execute.md

@@ -12,7 +12,9 @@ Every code/file/symbol lookup is a `codesearch` dispatch -- never a platform Exp
 
 ## Witness
 
-The witness IS the distance measurement: artifact present in observable state means `d(state, goal)` decreased. An artifact composed only in prose, or success returned without doing the work, sits at high distance regardless of structure -- L3 rejects the next dispatch.
+You still reason as hard as ever -- you just think in code rather than in silent prose. A thought you cannot run is a guess; the hypothesis you form becomes an `exec_js`, a `codesearch`, a `page.evaluate`, and its output is the conclusion. The internal monologue that used to argue both sides of an unknown is replaced by the cheaper, truthful move: run it and read the real result. Hypothesize, execute, witness -- that loop IS your reasoning, and it leaves an artifact the next agent can trust.
+
+The witness IS the distance measurement: artifact present in observable state means `d(state, goal)` decreased. An artifact composed only in prose, or success returned without doing the work, sits at high distance regardless of structure -- a conclusion reasoned-to but never run-to is exactly that unwitnessed prose; L3 rejects the next dispatch.
 
 Witness code running on a non-default surface on that surface in the same turn; a passing test on surface A is not witness for code on surface B. For the browser surface, dispatch the `browser` verb (`in/browser/<N>.txt`, raw JS, globals `page`/`snapshot`/`screenshotWithAccessibilityLabels`/`state`; `session new|list|close <id>`).
 
@@ -36,7 +38,7 @@ First emit = closure of the transform; scaffold + IOU externalizes residual cost
 
 Data first -- get the structures and their invariants right and the code writes itself; convoluted control flow means the data model is wrong, so fix the model. Make invalid state unrepresentable -- pass parameters over hidden globals, encode the constraint in the type/shape so the bad combination cannot be constructed. Reason from physical constraints (latency, bandwidth, memory, coordination, the worst node) before designing within them. Keep the spine flat, each unit single-focus and understandable at its call site. Make misuse structurally impossible, not documented-against. Optimize the worst case, not the average; design every failure path explicitly (full -> degraded -> safe-fail -> explicit-error), never a silent catastrophic mode. Measure, do not assume -- profile before optimizing, implement both and compare on real input when in genuine dispute. When a change regresses something that worked, revert first and investigate second: restore green, then diagnose from a known-good base. Fail fast and loud over limping on bad state.
 
-**Process of elimination is the debugging paradigm on every surface, and manual labour against real services is how you witness.** Never guess-and-restart, a/b-test, or shotgun variants: enumerate the candidate causes as mutables, then eliminate each by a witness read against REAL input -- `exec_js` against the real service, `codesearch`/`Read` against the real source, the `browser` verb's `page.evaluate` against a `window.*` global on the live page. Each elimination reveals the next mutable; record it and keep going until one cause survives every other's refutation. Reading the live runtime once observes more than a hundred blind restarts. Profile on the real surface, not from intuition: wrap the suspect node and read the live numbers. In node, `exec_js` carries `duration_ms` for free, surfaces your own timing and `process.memoryUsage()` on stdout, and lands the thrown-error `stack` on stderr -- read both channels (numbers on stdout, stack on stderr). In the browser, a body prefixed `capture\n<script>` auto-returns `{result, debug:{console, pageErrors, network, performance}}` with zero boilerplate. When the slow node is not obvious, sample it bottom-up: `exec_js` with `opts.profile:true` and the browser `profile\n<script>` prefix both return `{result, profile:{timeframe:{start_us,end_us,total_us,sample_count}, culprits:[{location,function,self_us,self_pct,hits}]}}` -- the worst-20 `file:line` by self-time across init and code-execution, identical shape on both surfaces, so the culprit ranking points straight at the line to fix. Profile to LOCATE the slow/broken node, then eliminate hypotheses by live measurement. Verification is the same labour: run the real thing and witness the real output (the single mock-free `test.js`, the live page, the real service), never an automated unit/mock harness standing in for the real-services witness. Apparent tooling failure is part of this -- it is your mechanical self-recovery by elimination, never a question for the user.
+**Process of elimination is the debugging paradigm on every surface, and manual labour against real services is how you witness.** This is thinking-in-code at its sharpest: each candidate cause is a hypothesis, and you test the hypothesis by running it, not by reasoning around it. Never guess-and-restart, a/b-test, or shotgun variants: enumerate the candidate causes as mutables, then eliminate each by a witness read against REAL input -- `exec_js` against the real service, `codesearch`/`Read` against the real source, the `browser` verb's `page.evaluate` against a `window.*` global on the live page. Each elimination reveals the next mutable; record it and keep going until one cause survives every other's refutation. Reading the live runtime once observes more than a hundred blind restarts. Profile on the real surface, not from intuition: wrap the suspect node and read the live numbers. In node, `exec_js` carries `duration_ms` for free, surfaces your own timing and `process.memoryUsage()` on stdout, and lands the thrown-error `stack` on stderr -- read both channels (numbers on stdout, stack on stderr). In the browser, a body prefixed `capture\n<script>` auto-returns `{result, debug:{console, pageErrors, network, performance}}` with zero boilerplate. When the slow node is not obvious, sample it bottom-up: `exec_js` with `opts.profile:true` and the browser `profile\n<script>` prefix both return `{result, profile:{timeframe:{start_us,end_us,total_us,sample_count}, culprits:[{location,function,self_us,self_pct,hits}]}}` -- the worst-20 `file:line` by self-time across init and code-execution, identical shape on both surfaces, so the culprit ranking points straight at the line to fix. Profile to LOCATE the slow/broken node, then eliminate hypotheses by live measurement. Verification is the same labour: run the real thing and witness the real output (the single mock-free `test.js`, the live page, the real service), never an automated unit/mock harness standing in for the real-services witness. Apparent tooling failure is part of this -- it is your mechanical self-recovery by elimination, never a question for the user.
 
 ## Memorize
 

package/instructions/plan.md

@@ -6,7 +6,7 @@ L1 baseline + L2 covering family. You loaded prior memory on entry via `instruct
 
 ## Orient
 
-First non-trivial dispatch = a single-message parallel fan-out of `recall` + `codesearch` against the request's nouns. Hits are your baseline; misses delimit fresh ground to investigate. Skip orient and you commit to an unobserved envelope.
+First non-trivial dispatch = a single-message parallel fan-out of `recall` + `codesearch` against the request's nouns. This is where planning-thought becomes executed query rather than recalled-from-memory assumption: what you would otherwise assume about the codebase, you instead hypothesize and look up. Hits are your baseline; misses delimit fresh ground to investigate. Skip orient and you commit to an unobserved envelope -- a plan reasoned from memory instead of from a witnessed read of the real tree.
 
 ## Cover
 

package/instructions/verify.md

@@ -16,7 +16,7 @@ The `git_push` verb is the only admissible push surface, any repo, any cwd; it r
 
 ## CI
 
-The push IS the validation dispatch. Local proof covers one platform; the matrix covers all. Red = a divergent observation that holds the trajectory until you name the cause and push green; toolchain skew is an observation to converge, not stop.
+Verification is thinking run rather than reasoned: the question "is this correct?" is not argued in prose, it is executed -- the real test, the real matrix, the real page answer it. The push IS the validation dispatch. Local proof covers one platform; the matrix covers all. Red = a divergent observation that holds the trajectory until you name the cause and push green; toolchain skew is an observation to converge, not stop.
 
 ## Integration witness
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-plugkit",
-  "version": "2.0.1617",
+  "version": "2.0.1619",
   "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/plugkit-wasm-wrapper.js

@@ -1062,6 +1062,13 @@ function startManagedBrowser(pw, profileDir) {
     '--disable-default-apps',
     '--disable-gpu-process-crash-limit',
   ];
+  // In containers where unprivileged user namespaces are disabled, Chromium's
+  // sandbox cannot initialize and the remote-debugging port never binds (the CDP
+  // "did not become ready" failure). Opt in to running without the sandbox (plus
+  // the small-/dev/shm workaround common in containers) via GM_BROWSER_NO_SANDBOX=1.
+  if (process.env.GM_BROWSER_NO_SANDBOX === '1') {
+    args.push('--no-sandbox', '--disable-setuid-sandbox', '--disable-dev-shm-usage');
+  }
   if (headless) {
     args.push('--headless=new');
   } else {
@@ -3598,9 +3605,9 @@ async function runSpoolWatcher(instance, spoolDir) {
     try {
       const skillCandidates = [
         path.join(wrapperDir, 'SKILL.md'),
-        path.join(wrapperDir, '..', 'gm-skill', 'skills', 'gm-skill', 'SKILL.md'),
-        path.join(wrapperDir, '..', '..', 'gm-skill', 'skills', 'gm-skill', 'SKILL.md'),
-        path.join(wrapperDir, '..', 'skills', 'gm-skill', 'SKILL.md'),
+        path.join(wrapperDir, '..', 'gm-skill', 'skills', 'gm', 'SKILL.md'),
+        path.join(wrapperDir, '..', '..', 'gm-skill', 'skills', 'gm', 'SKILL.md'),
+        path.join(wrapperDir, '..', 'skills', 'gm', 'SKILL.md'),
       ];
       const bundledPath = skillCandidates.find(p => { try { return fs.existsSync(p); } catch (_) { return false; } });
       if (!bundledPath) return;
@@ -3608,8 +3615,8 @@ async function runSpoolWatcher(instance, spoolDir) {
       const bundledHash = crypto.createHash('sha256').update(bundled).digest('hex');
       const home = process.env.HOME || process.env.USERPROFILE || os.homedir();
       const targets = [
-        path.join(home, '.agents', 'skills', 'gm-skill', 'SKILL.md'),
-        path.join(home, '.claude', 'skills', 'gm-skill', 'SKILL.md'),
+        path.join(home, '.agents', 'skills', 'gm', 'SKILL.md'),
+        path.join(home, '.claude', 'skills', 'gm', 'SKILL.md'),
       ];
       const refreshed = [];
       for (const target of targets) {