gm-skill 2.0.1199 → 2.0.1201

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -35,7 +35,7 @@ An earlier generation fanned out fifteen per-platform downstream repos (gm-cc, g
35
35
 
36
36
  ## Version
37
37
 
38
- `2.0.1199` — auto-bumped from the canonical `gm` repo. Every push to `AnEntrypoint/gm` (or any cascading sibling crate) republishes this package.
38
+ `2.0.1201` — auto-bumped from the canonical `gm` repo. Every push to `AnEntrypoint/gm` (or any cascading sibling crate) republishes this package.
39
39
 
40
40
  ## Source of truth
41
41
 
@@ -1 +1 @@
1
- 0.1.439
1
+ 0.1.441
package/bin/plugkit.wasm CHANGED
Binary file
@@ -1 +1 @@
1
- 306dfe2ef8117175fae4c66b15fc14a4505ee76b631d5a0762e00999dbea04d2 plugkit.wasm
1
+ c97d3c5ccbfedfee3079bf561468355dc28ffe88ec41d0ecbb66a42e03887727 plugkit.wasm
package/gm.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "gm",
3
- "version": "2.0.1199",
3
+ "version": "2.0.1201",
4
4
  "description": "Spool-dispatch orchestration engine with unified state machine, skills, and automated git enforcement",
5
5
  "author": "AnEntrypoint",
6
6
  "license": "MIT",
@@ -17,5 +17,5 @@
17
17
  "publishConfig": {
18
18
  "access": "public"
19
19
  },
20
- "plugkitVersion": "0.1.439"
20
+ "plugkitVersion": "0.1.441"
21
21
  }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "gm-skill",
3
- "version": "2.0.1199",
3
+ "version": "2.0.1201",
4
4
  "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.",
5
5
  "author": "AnEntrypoint",
6
6
  "license": "MIT",
@@ -39,7 +39,7 @@
39
39
  "gm.json"
40
40
  ],
41
41
  "dependencies": {
42
- "gm-plugkit": "^2.0.1199"
42
+ "gm-plugkit": "^2.0.1201"
43
43
  },
44
44
  "engines": {
45
45
  "node": ">=16.0.0"
@@ -1,27 +1,19 @@
1
1
  ---
2
2
  name: gm-skill
3
- description: AI-native engineering harness. Plugkit-served instruction stream; three-layer admission filter (cost, bounds, direction) gates every mutation; PRD-DAG covers the destructive transform's closure; emit the mature artifact, not the scaffold.
3
+ description: Plugkit-served instruction stream. Three-layer admission (cost, bounds, direction) over every mutation. Closure on first emit; partial = non-monotonic.
4
4
  allowed-tools: Skill, Read, Write, Bash(node *), Bash(bun *)
5
5
  ---
6
6
 
7
- # gm — only plugkit
7
+ # gm
8
8
 
9
- Plugkit owns the discipline. Every turn: dispatch `instruction`, follow the prose. Every candidate operation traverses the three-layer admission filter L1 cost (empirical baseline; recall+codesearch fan-out probes it) → L2 bounds (`|F|=1` single-writer per surface; PRD/mutables/KV are the central stores) → L3 direction (Lyapunov criterion; mutations must monotonically decrease distance-to-goal; audit tuple `(id, hash, ts)` per accepted write). Reject → defer or discard.
9
+ Every turn: dispatch `instruction`, follow the prose. The discipline lives in plugkit; this file does not duplicate it.
10
10
 
11
- Read/Edit/Bash/Grep/Glob before the first `instruction` dispatch IS the failure this skill prevents — each is a step outside the loop, and the loop is the work.
12
-
13
- If `.gm/exec-spool/.status.json` is absent or stale (>15s), boot the watcher — the one direct action this skill permits:
11
+ Boot when `.gm/exec-spool/.status.json` is absent or stale (>15s):
14
12
 
15
13
  ```
16
14
  bun x gm-plugkit@latest spool > /dev/null 2>&1 &
17
15
  ```
18
16
 
19
- (`npx -y gm-plugkit@latest spool > /dev/null 2>&1 &` if `bun` missing.) Wait 2s, confirm fresh heartbeat, proceed.
20
-
21
- Now dispatch `instruction` (empty body → `in/instruction/<N>.txt`). Response carries the active phase prose, PRD, open mutables, prior recall, the three-layer framing for this phase, and every signal the next action needs. Follow imperatively. Exit condition met → `transition`. Chain runs PLAN → EXECUTE → EMIT → VERIFY → COMPLETE under plugkit's direction; this skill does not duplicate prose, enumerate verbs, or describe the dispatch ABI — plugkit serves all of it on demand.
22
-
23
- Maturity-first invariant: emit the closure of the destructive transform the request admits, not a scaffold + "Phase 2 next session" IOU. Partial emits are non-monotonic, L3-rejected. If closure exceeds session reach, that's a Maximal Cover decomposition (PRD-DAG enumeration), never a TODO-launder.
24
-
25
- Memory writes route through `memorize-fire` exclusively — surfaces outside it produce memos the recall index does not see. Questions to the user fire last, after the three layers, scope-expansion, and a `WebSearch`/`WebFetch` pack all close empty. Interactive-question tools admit destructive-irreversible-uncovered decisions only; their use to clarify already-authorized scope IS the L3 violation — narrative substituted for the audit tuple the orchestrator requires.
17
+ (`npx -y gm-plugkit@latest spool > /dev/null 2>&1 &` if `bun` missing.) Heartbeat fresh dispatch `instruction` (empty body → `in/instruction/<N>.txt`).
26
18
 
27
- Only plugkit.
19
+ Response body is not a mutation surface. Memory writes route through `memorize-fire` only.