plugin-doctor
Skill0 starsChanged 8 months agoMITView on GitHub
Codex 플러그인/스킬 저장소를 감사하고 개선합니다. `.codex-plugin/plugin.json`, `.agents/plugins/marketplace.json`, `.agents/skills`, `.codex/agents`, legacy Claude 산출물을 점검할 때 사용합니다.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- sudeepgupta90/my-ai-marketplacetheir own version, first seen Nov 8, 2026
- chadthornton/claude-continuitytheir own version, first seen Sep 30, 2026
- grahac/claude_skillstheir own version, first seen Apr 18, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- grahac/claude_skills★ 2same name
- chadthornton/claude-continuity★ 0same name
- sudeepgupta90/my-ai-marketplace★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-context-auditSkill
- agent-context-guideSkill
- agent-context-initSkill
- agent-context-verifySkill
- app-automationSkill
- apple-craftSkill
- apple-harnessSkill
- apple-reviewSkill
- codex-skill-auditSkill
- codex-skill-bootstrapSkill
- goal-research-loopSkill
- gpt-researchSkill
- hey-codexSkill
- karpathy-wikiSkill
- macos-releaseSkill
The file
Files
Plugin Doctor
원본 fixer 스킬을 Codex 기준으로 옮긴 버전입니다.
When to use
- Codex 플러그인/스킬 저장소의 packaging 구조를 감사하고 개선할 때
.codex-plugin/plugin.json, marketplace manifest, custom agents, legacy Claude 흔적을 점검할 때- repo-local skill과 optional plugin 배포 레이어의 정합성을 함께 봐야 할 때
Do not use when
- 개별 skill authoring/discovery 개선이 주목적인 작업 →
codex-skill-audit,codex-skill-bootstrap AGENTS.md계층 설계·검증이 주목적인 작업 →agent-context-*- 일반 코드 구현/리팩터링만 필요한 작업
Quick start
- 감사 대상 루트를 정하고 plugin audit script를 먼저 실행한다.
- legacy Claude residue와 manifest 정합성을 수동 점검한다.
critical / warning / info / strength와 안전한 자동 수정 후보를 분리한다.
Use resources
references/official-spec.mdscripts/audit_codex_plugin_repo.pyschemas/report.schema.json../../../docs/evaluator-output-contract.md- 필요 시
../codex-skill-audit/scripts/audit_codex_skill_repo.py
Workflow
- 감사 대상 루트를 결정한다. 기본값은 현재 저장소다.
scripts/audit_codex_plugin_repo.py [target]로 결정적 구조 감사를 먼저 수행한다.- legacy Claude 산출물(
CLAUDE.md,.claude-plugin/, hooks 전용 구조`)이 남아 있는지 확인한다. - repo-local skills, optional plugin packaging, custom agents의 정합성을 수동 점검한다.
critical / warning / info / strength로 결과를 보고하고, 안전한 자동 수정 후보를 분리한다.
What this skill focuses on
.agents/skills/**/SKILL.md- optional
agents/openai.yaml .codex/agents/*.toml.agents/plugins/marketplace.json와plugins/*/.codex-plugin/plugin.json(존재하는 경우).mcp.json,.app.json같은 보조 매니페스트- Codex로 옮기면서 남은 Claude 전용 흔적
Review Harness
- mode: none
- 공통 기준:
../../../docs/review-harness.md - generator: 상위 변경사항 또는 감사 대상 repo 구조
- evaluator: 이 스킬 자체와 audit script가 evaluator-native plugin audit 역할을 수행한다
- 평가축: marketplace↔package 정합성, manifest 품질, legacy residue, custom agent/skill 연결성
- artifacts/evidence: manifest 구조, audit script output, legacy residue, custom agent 정합성
- pass condition: plugin/skill/custom agent 레이어의 구조 문제를 severity와 근거와 함께 설명할 수 있어야 한다
- 자동 다음 행동:
pass면 종료,warning이면 metadata 정리,critical이면 packaging 또는 manifest를 재생성하고 필요 시sync_packaged_plugins.py를 재실행한다
Output expectation
- 감사 범위
critical / warning / info / strength결과- 안전한 자동 수정 후보
- 사람이 직접 판단해야 할 packaging 리스크
deterministic audit script는 아래 artifact를 함께 지원하는 편을 권장합니다.
- stdout: 사람이 읽는 Markdown 보고서
--json-out <path>:schemas/report.schema.json에 맞는 machine summary JSON
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

