gm-skill 2.0.1831 → 2.0.1833

package/gm-plugkit/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gm-plugkit",
-  "version": "2.0.1831",
+  "version": "2.0.1833",
   "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": "2.0.1831",
+  "version": "2.0.1833",
   "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": "2.0.1831",
+  "version": "2.0.1833",
   "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

@@ -1,6 +1,6 @@
 ---
 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.
+description: The primary driver for any non-trivial coding, refactoring, debugging, or multi-step engineering task in a project using this harness -- use it first, for the whole task, not just a piece of it. 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. Not for the post-completion remaining-work check (that is `gm-continue`) or for drift-recovery mid-task (that is `wfgy-method`) -- this skill is the work itself.
 allowed-tools: Skill, Read, Write, Bash(bun *), Bash(npx *)
 ---
 
@@ -8,7 +8,7 @@ allowed-tools: Skill, Read, Write, Bash(bun *), Bash(npx *)
 
 **No tool call = stop; mid-chain stop = cardinal failure.** Agents read only tool calls + outputs -- prose-only turn ends the session. In-flight (`phase != COMPLETE OR prd_pending_count > 0`): every turn ends in a chain-advancing dispatch (`instruction`, the named next verb, or `transition`). No summaries, no "here's what I did," no closure narration. A turn-final sentence naming the next move instead of taking it is the same stop -- take the move. **A question asking permission to take the next move ("Should I dispatch X now?", "Ready to proceed -- want me to continue?") is the identical stop, worded as a question instead of a narration.** Standing approval already covers this turn's work (see below) -- dispatch the named verb instead of asking whether to. Decisions worth surfacing to the user go through `AskUserQuestion` (a real ambiguity with distinct answers) or `prd-add` (a discovered row), never a prose question about whether to continue the already-authorized chain.
 
-**At genuine `phase=COMPLETE AND prd_pending_count=0`, the only allowed next step is dispatching `Skill(skill="gm-continue")`, never a bare prose ending.** That dedicated skill does the remaining-work search and the `gm`/`wfgy-method` handoff decision -- do not inline that logic here or improvise it; dispatch the skill and follow what it does.
+**`gm` is only allowed to end by calling `gm-continue`; there is no other exit.** At genuine `phase=COMPLETE AND prd_pending_count=0`, the only allowed next step is dispatching `Skill(skill="gm-continue")` -- never a bare prose ending, never a stop for the user to re-prompt. This is absolute: no branch of `gm`'s own logic, no phase, no gate response ever authorizes ending a `gm`-driven turn any other way. Do not inline `gm-continue`'s remaining-work search or its `gm`/`wfgy-method` decision here or improvise around it -- dispatch the skill and follow exactly what it does.
 
 **Done is plugkit's word, never yours.** COMPLETE gate is the sole arbiter; not-COMPLETE = a next transition to seek, never a stopping point. Idle mid-chain is a deviation, not a pause. If uncertain what's next, dispatch `phase-status`, read the phase, then keep walking -- "uncertain" is never grounds to stop.
 

package/skills/gm-continue/SKILL.md

@@ -8,6 +8,8 @@ allowed-tools: Skill, Read, Write, Bash(bun *), Bash(npx *)
 
 This is the only allowed next step when a `gm` walk reaches `phase=COMPLETE AND prd_pending_count=0`. Never end that turn with prose alone -- dispatch this skill instead, every time, no exceptions for "it looks finished."
 
+**This skill itself has exactly two allowed ways to end, and no others.** (1) Dispatch `Skill(skill="gm")` with the remaining PRD rows (found reachable work, or reopened an `external`/`out-of-reach` row, or this is the first confirming pass this session) -- `gm` then runs and, when it reaches COMPLETE again, calls back into this same skill. (2) Confirm there are no remaining PRD rows and none can be added -- a real, witnessed check (steps 2-4 below actually run, not assumed), not a feeling of "probably done." There is no third path: no prose-only stop that isn't outcome (2), no deferring to the user to decide whether to continue, no partial confirmation. Every dispatch of this skill lands in exactly one of these two states before the turn ends.
+
 ## What this skill does
 
 1. Read `.gm/exec-spool/.turn-summary.json` for the current `phase`, `prd_pending`, and how many times this repo has already round-tripped through `gm-continue` this session (track via a counter file, see below).

package/skills/wfgy-method/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: wfgy-method
-description: Applies WFGY (Wan Fa Gui Yi), a portable reasoning discipline for reducing drift and incoherence across multi-step agent work, adapted from onestardao/WFGY's core mechanism. Compares each step against the stated goal, considers more than one approach before committing to ambiguous or high-stakes decisions, and checkpoints before risky steps so it can revert and bounded-retry instead of compounding a mistake. Records durable lessons in this project so future sessions inherit them. Use when starting any non-trivial multi-step task, when a task risks losing track of its original goal over many steps, when facing a decision with real alternatives worth comparing, or when the agent notices it has contradicted itself or gone in circles and needs a disciplined way to recover.
+description: Applies WFGY (Wan Fa Gui Yi), a portable reasoning discipline for reducing drift and incoherence across multi-step agent work, adapted from onestardao/WFGY's core mechanism. Compares each step against the stated goal, considers more than one approach before committing to ambiguous or high-stakes decisions, and checkpoints before risky steps so it can revert and bounded-retry instead of compounding a mistake. Records durable lessons in this project so future sessions inherit them. Use when starting any non-trivial multi-step task, when a task risks losing track of its original goal over many steps, when facing a decision with real alternatives worth comparing, or when the agent notices it has contradicted itself or gone in circles and needs a disciplined way to recover. Distinct from `gm-continue`: that skill is the specific post-`gm`-COMPLETE remaining-work check (a narrow, mechanical PRD scan); this skill is the general drift-recovery discipline `gm-continue` itself invokes when a `gm` walk keeps hitting the same gap across repeat cycles -- not a substitute for `gm-continue`'s own check.
 license: MIT
 compatibility: Designed for Claude Code. No external services, embedding models, or network access required for the core discipline.
 metadata: