@zhixuan92/multi-model-agent 3.1.2 → 3.1.4
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/dist/skills/mma-audit/SKILL.md +1 -1
- package/dist/skills/mma-clarifications/SKILL.md +1 -1
- package/dist/skills/mma-context-blocks/SKILL.md +1 -1
- package/dist/skills/mma-debug/SKILL.md +1 -1
- package/dist/skills/mma-delegate/SKILL.md +1 -1
- package/dist/skills/mma-execute-plan/SKILL.md +1 -1
- package/dist/skills/mma-retry/SKILL.md +1 -1
- package/dist/skills/mma-review/SKILL.md +1 -1
- package/dist/skills/mma-verify/SKILL.md +1 -1
- package/dist/skills/multi-model-agent/SKILL.md +1 -1
- package/package.json +2 -2
|
@@ -10,7 +10,7 @@ when_to_use: >-
|
|
|
10
10
|
(superpowers:dispatching-parallel-agents, /security-review) points at an audit
|
|
11
11
|
task. Delegate via mmagent so the audit runs on independent workers — your
|
|
12
12
|
main context stays free to synthesize findings.
|
|
13
|
-
version: 3.1.
|
|
13
|
+
version: 3.1.4
|
|
14
14
|
---
|
|
15
15
|
|
|
16
16
|
## mma-audit
|
|
@@ -9,7 +9,7 @@ when_to_use: >-
|
|
|
9
9
|
terminal envelope has `proposedInterpretation` as a string (not a
|
|
10
10
|
NotApplicable sentinel). Read the proposal and call this skill to accept or
|
|
11
11
|
correct it. The batch resumes after the POST returns.
|
|
12
|
-
version: 3.1.
|
|
12
|
+
version: 3.1.4
|
|
13
13
|
---
|
|
14
14
|
|
|
15
15
|
## mma-clarifications
|
|
@@ -10,7 +10,7 @@ when_to_use: >-
|
|
|
10
10
|
field on mma-delegate / mma-execute-plan / mma-audit / mma-review / mma-verify
|
|
11
11
|
/ mma-debug. Cheaper and faster than inlining the same content in every
|
|
12
12
|
request body.
|
|
13
|
-
version: 3.1.
|
|
13
|
+
version: 3.1.4
|
|
14
14
|
---
|
|
15
15
|
|
|
16
16
|
## mma-context-blocks
|
|
@@ -10,7 +10,7 @@ when_to_use: >-
|
|
|
10
10
|
(superpowers:systematic-debugging) points at the investigation step. Delegate
|
|
11
11
|
the read/reproduce/trace work to a mmagent worker so your main context stays
|
|
12
12
|
focused on the hypothesis and the fix.
|
|
13
|
-
version: 3.1.
|
|
13
|
+
version: 3.1.4
|
|
14
14
|
---
|
|
15
15
|
|
|
16
16
|
## mma-debug
|
|
@@ -11,7 +11,7 @@ when_to_use: >-
|
|
|
11
11
|
parallel-safe, and keep main context free. If a plan file exists, use
|
|
12
12
|
mma-execute-plan; if the task is an audit/review/verify/debug, prefer the
|
|
13
13
|
matching mma-* skill instead.
|
|
14
|
-
version: 3.1.
|
|
14
|
+
version: 3.1.4
|
|
15
15
|
---
|
|
16
16
|
|
|
17
17
|
## mma-delegate
|
|
@@ -11,7 +11,7 @@ when_to_use: >-
|
|
|
11
11
|
or superpowers:subagent-driven-development / superpowers:executing-plans when
|
|
12
12
|
mmagent is running — delegated workers are cheaper and don't pollute main
|
|
13
13
|
context. Task descriptors must match the plan headings verbatim.
|
|
14
|
-
version: 3.1.
|
|
14
|
+
version: 3.1.4
|
|
15
15
|
---
|
|
16
16
|
|
|
17
17
|
## mma-execute-plan
|
|
@@ -9,7 +9,7 @@ when_to_use: >-
|
|
|
9
9
|
you want to re-try the failed indices only. Prefer this over redispatching the
|
|
10
10
|
whole batch or inline-retrying — it's idempotent and keeps the original
|
|
11
11
|
batch's diagnostics intact.
|
|
12
|
-
version: 3.1.
|
|
12
|
+
version: 3.1.4
|
|
13
13
|
---
|
|
14
14
|
|
|
15
15
|
## mma-retry
|
|
@@ -9,7 +9,7 @@ when_to_use: >-
|
|
|
9
9
|
more files OR a methodology skill (superpowers:requesting-code-review,
|
|
10
10
|
/review, /security-review) points at a review task. Delegate the reviewer pass
|
|
11
11
|
to mmagent workers — your main context stays free to decide what to merge.
|
|
12
|
-
version: 3.1.
|
|
12
|
+
version: 3.1.4
|
|
13
13
|
---
|
|
14
14
|
|
|
15
15
|
## mma-review
|
|
@@ -8,7 +8,7 @@ when_to_use: >-
|
|
|
8
8
|
superpowers:verification-before-completion) wants acceptance-criteria checked
|
|
9
9
|
against implemented work. Delegate the evidence-gathering to mmagent workers —
|
|
10
10
|
each checklist item is verified independently and in parallel.
|
|
11
|
-
version: 3.1.
|
|
11
|
+
version: 3.1.4
|
|
12
12
|
---
|
|
13
13
|
|
|
14
14
|
## mma-verify
|
|
@@ -11,7 +11,7 @@ when_to_use: >-
|
|
|
11
11
|
mmagent is running. Read this once, pick the matching mma-* skill, and
|
|
12
12
|
delegate there. Applies equally whether the user invoked a superpowers
|
|
13
13
|
methodology skill or just asked directly.
|
|
14
|
-
version: 3.1.
|
|
14
|
+
version: 3.1.4
|
|
15
15
|
---
|
|
16
16
|
|
|
17
17
|
## multi-model-agent overview
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@zhixuan92/multi-model-agent",
|
|
3
|
-
"version": "3.1.
|
|
3
|
+
"version": "3.1.4",
|
|
4
4
|
"type": "module",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"description": "Standalone HTTP server for multi-model-agent. Routes tool-invocation work to Claude, Codex, or OpenAI-compatible sub-agents with async-polling REST dispatch and installable skills for Claude Code, Gemini CLI, Codex CLI, and Cursor.",
|
|
@@ -52,7 +52,7 @@
|
|
|
52
52
|
},
|
|
53
53
|
"dependencies": {
|
|
54
54
|
"@asteasolutions/zod-to-openapi": "^8.5.0",
|
|
55
|
-
"@zhixuan92/multi-model-agent-core": "^3.1.
|
|
55
|
+
"@zhixuan92/multi-model-agent-core": "^3.1.4",
|
|
56
56
|
"gray-matter": "^4.0.3",
|
|
57
57
|
"minimist": "^1.2.8",
|
|
58
58
|
"zod": "^4.0.0"
|