gm-skill 2.0.1569 → 2.0.1570

package/AGENTS.md

@@ -118,6 +118,8 @@ Every skill's `allowed-tools:` is reduced to `Skill, Read, Write` (plus the SKIL
 
 **AGENTS.md / CLAUDE.md are inline-edited AND dual-written to the store**: edit them inline for structural rules (the only doc surviving context summarization), AND `memorize-fire` the same rule so `recall`/`auto_recall` surface it later -- complementary, not alternatives. Never `namespace:"AGENTS.md"`; load-bearing rules go to the default namespace. Mechanics in rs-learn (`recall: memorize-fire ingestion classifier`).
 
+**A memorized workaround is a tool defect; transform it, never accumulate it**: we work USING gm, not ON it, so a `recall` memo framed as a workaround, known-limitation, or internal-advice is tribal knowledge a fresh user/LLM lacks -- the tool then surprises them, and surprises are never allowed; everything must be abundantly predictable at face value. Resolve every such memo one of three ways, then prune it: (a) already covered by the standing prose (SKILL.md / instruction bundle) -> prune the redundant recall; (b) prose-worthy but absent -> add the rule to the prose, then prune; (c) genuine surprising behavior -> fix the code so it is predictable, then prune. `recall` carries project work-context (what the work surfaced about the user's problem), never tool-operation advice -- the tool's prose + behavior alone make every operation predictable. Witnessed transforms: CRLF/LF const-drift -> sync LF-normalization; codesearch cwd-scope -> the search-routing prose clause.
+
 **Behavioral discipline lives in plugkit's `instruction` verb**: dispatch `instruction` for the live phase-specific prose (Three-Layer Admission Filter, maturity-first emit, closure anti-shapes, code invariants); do not duplicate it here. Enumeration in rs-learn (`recall: instruction-verb behavioral discipline invariants`).
 
 **The agent IS the LLM rs-learn calls**: rs-learn never reaches a separate judge model for a quality score, relevance, prune, route, or loss signal -- plugkit IS the harness and the agent IS the model, each an inline decision reported through the spool. Per-core internals in rs-learn (`recall: rs-learn self-report core internals`).

package/gm-plugkit/instructions/entry.md

@@ -81,7 +81,7 @@ Route KV writes to `<cwd>/.gm/disciplines/<ns>/`. `@<name>` prefix sets namespac
 
 ## Inspection routing
 
-`Read` for runtime-state files (spool response JSON, `.status.json`); `codesearch` verb for every code/file/symbol search -- Glob/Grep/Explore and host-native search are blocked, the verb is the surface. Bash only for the boot probe and shell-only non-git tooling (`npm`, `bun x`, `curl`). Spool responses are synchronous; poll external state via `until <check>; do sleep N; done`.
+`Read` for runtime-state files (spool response JSON, `.status.json`); `codesearch` verb for every code/file/symbol search (it indexes the CURRENT cwd only -- sibling-repo source is `Read` by path, never expected from `codesearch`) -- Glob/Grep/Explore and host-native search are blocked, the verb is the surface. Bash only for the boot probe and shell-only non-git tooling (`npm`, `bun x`, `curl`). Spool responses are synchronous; poll external state via `until <check>; do sleep N; done`.
 
 ## Memorize
 

package/gm-plugkit/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-plugkit",
-  "version": "2.0.1569",
+  "version": "2.0.1570",
   "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": "2.0.1569",
+  "version": "2.0.1570",
   "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": "2.0.1569",
+  "version": "2.0.1570",
   "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/SKILL.md

@@ -24,7 +24,7 @@ Every turn: dispatch `instruction`, read it, follow the imperative, dispatch the
 
 **The live page is the debugger -- expose globals, evaluate in-browser, never blind-restart.** Surface relevant state as a `window.*` global and read it live via the `browser` verb's `page.evaluate`, running experiments in the page. A global plus one evaluate reads real runtime state in one dispatch; the restart-and-eyeball loop observes almost nothing and burns a turn. The same `browser` surface that witnesses an edit also diagnoses it.
 
-**Search routes through the spool, never a platform search agent.** Any code/file/symbol lookup ("where is X", "what calls Y", grep the tree) is the `codesearch` verb (`{"query":"..."}`); prior knowledge is `recall`. Never the platform Explore agent, a Task/general-purpose search subagent, or raw `grep`/`Glob` -- they bypass the spool, the committed index, and recall-grounding, and do not transport across harnesses. Orient at PLAN is `recall` + `codesearch` in parallel; every mid-EXECUTE lookup is a `codesearch` too.
+**Search routes through the spool, never a platform search agent.** Any code/file/symbol lookup ("where is X", "what calls Y", grep the tree) is the `codesearch` verb (`{"query":"..."}`); prior knowledge is `recall`. Never the platform Explore agent, a Task/general-purpose search subagent, or raw `grep`/`Glob` -- they bypass the spool, the committed index, and recall-grounding, and do not transport across harnesses. Orient at PLAN is `recall` + `codesearch` in parallel; every mid-EXECUTE lookup is a `codesearch` too. `codesearch` indexes the CURRENT cwd only -- sibling-repo or other-checkout source is read by path via `Read`/`exec_js`, never expected from `codesearch` (a cross-repo query returns nothing by design, not a bug).
 
 **Class rule: every platform-native capability that has a plugkit verb is forbidden in favor of the verb.** code/file/symbol search -> `codesearch`; prior knowledge -> `recall`; URL/web fetch -> `fetch`; running code -> `exec_js`; a real browser -> `browser`; persisting memory -> `memorize-fire`; **any git op -> the git verbs** (`git_status`/`git_log`/`git_diff`/`git_show`/`git_branch` inspect; `git_add`/`git_commit`/`git_finalize`/`git_push` stage-commit-push; `git_checkout`/`git_fetch`/`git_rm`/`git_revert`/`git_reset` mutate). `git_finalize {message}` bundles add->commit->porcelain-gate->push in one dispatch and is the COMPLETE push surface; a `bash`/`sh`/`powershell` body invoking git is gated (`deviation.bash-git-bypass`). The native tool bypasses the ledger, the index, and portability. If no verb exists, that is a missing verb to add, not license to reach around the spool.