review-external-worker-run

Use when an external-worker evidence bundle needs independent Codex review, adjudication, repair routing, or final acceptance assessment.

Skill by MAbbara

IndexedApache-2.0

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mabbara-review-external-worker-run

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Use when an external-worker evidence bundle needs independent Codex review, adjudication, repair routing, or final acceptance assessment.

Use cases: agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/review-external-worker-run

What's inside

Skill name: review-external-worker-run
Description: Use when an external-worker evidence bundle needs independent Codex review, adjudication, repair routing, or final acceptance assessment.
License: Apache-2.0
Instructions: 11 lines in SKILL.md · view on GitHub

Files (3)

SKILL.md
openai.yaml · agents/
inline-reviewers.md · references/

SKILL.md (first lines)

# Review an External Worker Run

1. Require the task contract, starting commit, full diff, relevant files, deterministic results, repository conventions, and UI evidence when applicable. Exclude the worker summary initially.
2. Load `reviewers/review-request.json`. Fail closed when a required reviewer is missing.
3. Run the repo mapper first when architecture context is absent. Run independent correctness, maintainability, tests, security, UI-technical, and task-fit reviews in parallel as applicable. Use installed `k3_*` agents; otherwise use `references/inline-reviewers.md` with built-in agents.
4. Validate every response against `schemas/reviewer-finding.schema.json`. Reject unsupported preferences and require concrete evidence.
5. Adjudicate rather than vote: deduplicate, preserve disagreement, identify pre-existing issues, and decide which findings block.
6. Permit one bounded worker repair or choose Sol takeover/discard. Rerun affected checks and reviewers after repair.
7. Keep patch quality distinct from delegation quality. UI aesthetic desirability belongs to the human gate, not the technical UI reviewer.

From MAbbara/codex-kimi-worker, Apache-2.0.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Jul 16, 2026 (3 months ago)
Last release: Jul 16, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/MAbbara/codex-kimi-worker
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from MAbbara

Cite this page

review-external-worker-run skill. Agent Mart. https://agentmart.dev/skills/mabbara-review-external-worker-run (last updated 2026-10-24)