gm-qwen 2.0.760 → 2.0.762

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.
Files changed (5) hide show
  1. package/bin/plugkit.sha256 +6 -6
  2. package/bin/plugkit.version +1 -1
  3. package/gm.json +2 -2
  4. package/package.json +1 -1
  5. package/skills/gm/SKILL.md +2 -0
package/bin/plugkit.sha256 CHANGED
@@ -1,6 +1,6 @@
1
- 6a915bc5c0926ec49acb4d1e5c995375eeabb06b50293cbe0a4bb86bcc6fe342 plugkit-win32-x64.exe
2
- 6fbb19058635d310ec294b6d80df44ec3f388db99dffb32c424d646bc73d9d1a plugkit-win32-arm64.exe
3
- 0c15f9bc21051157931a948989469703f8c5cd21d11a6ec07e9b57c0e7447ddb plugkit-darwin-x64
4
- 5ab363b5ba2ebf13b8e1da988414ed37f20863669a391efb65fa6aa479c4c915 plugkit-darwin-arm64
5
- db078a3810a17bd6eea8b160e78c8d72bf189962e17e7fdbfe1a65be00674a84 plugkit-linux-x64
6
- 4e0af3b31b3089a79c9f6e6f8d52d5fba56cb42911d479418db1aa9aad7cc858 plugkit-linux-arm64
1
+ 6f37a38d23215bec8b6e000dda95bebf41c8fd3d34f47efac8508ce436cea695 plugkit-win32-x64.exe
2
+ bf94a8d39ce8bb2e6565a347fa88ba0061ca471fa968e3bcd645bcabd82c90cf plugkit-win32-arm64.exe
3
+ 9257c8f7f351dae2a25fd706a75d0281aa20878b14b1ce38aa47b84568ea2dde plugkit-darwin-x64
4
+ 5330b8d2681db209d5789fb6d5b6edcb5270f9d50ceac4126751a36995bef435 plugkit-darwin-arm64
5
+ 1d4dc8afb691486a643ef92904bb91d59deb7c88d1f05161a8ab1e38e6f6536f plugkit-linux-x64
6
+ a99817799e17ca2d467cdf6fca7c72c38af2d8ac2a14083c14f9461d4a652719 plugkit-linux-arm64
package/bin/plugkit.version CHANGED
@@ -1 +1 @@
1
- 0.1.251
1
+ 0.1.252
package/gm.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "gm",
3
- "version": "2.0.760",
3
+ "version": "2.0.762",
4
4
  "description": "State machine agent with hooks, skills, and automated git enforcement",
5
5
  "author": "AnEntrypoint",
6
6
  "license": "MIT",
@@ -23,5 +23,5 @@
23
23
  "publishConfig": {
24
24
  "access": "public"
25
25
  },
26
- "plugkitVersion": "0.1.251"
26
+ "plugkitVersion": "0.1.252"
27
27
  }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "gm-qwen",
3
- "version": "2.0.760",
3
+ "version": "2.0.762",
4
4
  "description": "State machine agent with hooks, skills, and automated git enforcement",
5
5
  "author": "AnEntrypoint",
6
6
  "license": "MIT",
package/skills/gm/SKILL.md CHANGED
@@ -43,6 +43,8 @@ Multiple facts → parallel Agent calls in ONE message. End-of-turn: scan for un
43
43
 
44
44
  A written PRD is the user's authorization. Once it exists, EXECUTE owns the work to COMPLETE. Resolve every doubt that arises during execution by witnessed probe, by recall, or by re-reading the PRD — never by asking the user. Any question whose answer the agent could obtain itself is a question the agent owes itself, not the user.
45
45
 
46
+ **FINISH ALL REMAINING STEPS — HARD RULE**: when a request enumerates or implies multiple work items ("all", "any", "everything", "the rest", "remaining"), or after a covering family is constructed under MAXIMAL COVER, the agent finishes every witnessable item in the same turn. Stopping after one item to ask "which next?" is forbidden — the answer is *all of them*, in one chain, until `.gm/prd.yml` is empty and git is clean and pushed. Mid-chain "should I…", "want me to…", "which would you like…" prompts are forced closure; replace them with the next skill invocation.
47
+
46
48
  Asking is permitted only as a last resort, when the next action is destructive-irreversible AND the PRD does not cover it, OR when user intent is genuinely irrecoverable from PRD, memory, and code. The channel is structured: `exec:pause` (renames `.gm/prd.yml` → `.gm/prd.paused.yml`, question in header). In-conversation asking is last-resort beneath last-resort.
47
49
 
48
50
  The size of the task, the cost of context, and the duration of CI are never grounds to ask.