codex-system
Skill18 starsChanged 10 months agoMITView on GitHub
PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".
2 other projects use a version of this.
Adopted by
Most recently taken up by
- DeL-TaiseiOzaki/claude-code-orchestratheir own version, first seen Sep 10, 2026
- gaebalai/claude-code-orchestratorword for word, first seen Jan 31, 2026
Other versions2 projects use a version of this.
Word for word · 1
- gaebalai/claude-code-orchestrator★ 18100% same
Edited · 0
None found.
Wrote their own version · 1
- DeL-TaiseiOzaki/claude-code-orchestra★ 199same 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 repository13 other files it gives its agents.
- .codex/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- checkpointingSkill
- design-trackerSkill
- gemini-systemSkill
- initSkill
- planSkill
- research-libSkill
- simplifySkill
- startprojectSkill
- tddSkill
- update-designSkill
- update-lib-docsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 91
Ask Codex in English
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Codex System — Deep Reasoning Partner
Codex CLI (gpt-5.2-codex) is your highly capable supporter for deep reasoning tasks.
상세규칙:
.claude/rules/codex-delegation.md
Context Management (CRITICAL)
서브에이전트 경유 권장이다. 메인 오케스트레이터의 컨텍스트를 절약하기 위해.
| 상황 | 방법 |
| 자세한 설계 상담 | 서브 에이전트를 통해 (권장) |
| 디버그 분석 | 서브 에이전트를 통해 (권장) |
| 짧은 질문 (1-2 문 답변) | 직접 호출 확인 |
When to Consult (MUST)
| Situation | Trigger Examples |
| Design decisions | "어디 디자인?" "아키텍처" / "How to design?" |
| Debugging | "왜 움직이지 않는가?" "오류" / "Debug" "Error" |
| Trade-off analysis | "어느 쪽이 좋은가?" "비교해" / "Compare" "Which?" |
| Complex implementation | "구현 방법" "어떻게 만드는가?" / "How to implement?" |
| Refactoring | "리팩터" "간단하게" / "Refactor" "Simplify" |
| Code review | "리뷰하고" "확인하고" / "Review" "Check" |
When NOT to Consult
- Simple file edits, typo fixes
- Following explicit user instructions
- git commit, running tests, linting
- Tasks with obvious single solutions
How to Consult
Recommended: Subagent Pattern
Use Task tool with subagent_type='general-purpose' to preserve main context.
Task tool parameters:
- subagent_type: "general-purpose"
- run_in_background: true (optional, for parallel work)
- prompt: |
Consult Codex about: {topic}
codex exec --model gpt-5.2-codex --sandbox read-only --full-auto "
{question for Codex}
" 2>/dev/null
Return CONCISE summary (key recommendation + rationale).Direct Call (Short Questions Only)
For quick questions expecting 1-2 sentence answers:
codex exec --model gpt-5.2-codex --sandbox read-only --full-auto "Brief question" 2>/dev/nullWorkflow (Subagent)
- Spawn subagent with Codex consultation prompt
- Continue your work → Subagent runs in parallel
- Receive summary → Subagent returns concise insights
Sandbox Modes
| Mode | Use Case |
read-only | Analysis, review, debugging advice |
workspace-write | Implementation, refactoring, fixes |
Language Protocol
- Ask Codex in English
- Receive response in English
- Execute based on advice (or let Codex execute)
- Report to user in Korean
Task Templates
Design Review
codex exec --model gpt-5.2-codex --sandbox read-only --full-auto "
Review this design approach for: {feature}
Context:
{relevant code or architecture}
Evaluate:
1. Is this approach sound?
2. Alternative approaches?
3. Potential issues?
4. Recommendations?
" 2>/dev/nullDebug Analysis
codex exec --model gpt-5.2-codex --sandbox read-only --full-auto "
Debug this issue:
Error: {error message}
Code: {relevant code}
Context: {what was happening}
Analyze root cause and suggest fixes.
" 2>/dev/nullCode Review
See: references/code-review-task.md
Refactoring
See: references/refactoring-task.md
Integration with Gemini
| Task | Use |
| Need research first | Gemini → then Codex |
| Design decision | Codex directly |
| Library comparison | Gemini research → Codex decision |
Why Codex?
- Deep reasoning: Complex analysis and problem-solving
- Code expertise: Implementation strategies and patterns
- Consistency: Same project context via
context-loaderskill - Parallel work: Background execution keeps you productive
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.

