ask-codex
Skill0 starsChanged 3 months agoMITView on GitHub
Consult OpenAI's Codex (ChatGPT) for a second opinion during planning, architecture decisions, code review, or any situation where a diverse AI perspective adds value. Runs `codex exec` and returns Codex's response for critical evaluation.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- maxatwork/skillstheir own version, first seen Nov 8, 2026
- finalize/skillstheir own version, first seen Nov 1, 2026
- madeordinary/serel-memorytheir own version, first seen Nov 1, 2026
- PolyArch/humanizetheir own version, first seen Oct 8, 2026
- BackToCimaCoppi/Praxistheir own version, first seen Sep 23, 2026
- Yumeno/add_codexclitheir own version, first seen Sep 19, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- PolyArch/humanize★ 1.5ksame name
- Sateezg/codex-bridge★ 248same name
- bookSiYi1412/ask-codex★ 9same name
- s977043/river-review★ 7same name
- BackToCimaCoppi/Praxis★ 6same name
- yeaight7/agent-powerups★ 6same name
- WebisityStudio/claude-codex-mcp-bridge★ 2same name
- madeordinary/serel-memory★ 1same name
- finalize/skills★ 0same name
- maxatwork/skills★ 0same name
1 more not listed
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 repository27 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- buildSkill
- cleanup-worktreeSkill
- db-querySkill
- db-searchSkill
- dd-errorsSkill
- devops-wiki-updateSkill
- devops-workitem-createSkill
- devops-workitem-readSkill
- devops-workitem-updateSkill
- finalize-taskSkill
- find-codeSkill
- merge-mainSkill
- panel-review-fixSkill
- panel-reviewSkill
- prSkill
- rebase-mainSkill
- starttaskSkill
- testSkill
- ask-geminiSkill
- councilSkill
- dailySkill
- find-sessionSkill
- merged-prsSkill
- mm-notifySkill
- optimize-promptSkill
- qSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
6
Distinctive
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 12
Use this skill when you need Codex's opinion during planning, architecture decisions, code review, or any situation where a diverse AI …
- Distinctive: line 17
Run the command below with your prompt
- Distinctive: line 29
Always include sufficient context in the prompt (project details, constraints, what's already been decided)
- Distinctive: line 31
When Codex's response conflicts with your own analysis, flag the disagreement for council discussion
- Distinctive: line 32
Do NOT blindly accept Codex's output — treat it as one voice in the council
- Distinctive: line 34
Keep prompts under 4000 characters for best results
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ask Codex
Consult OpenAI's Codex (ChatGPT) for its perspective on a topic.
Usage
Use this skill when you need Codex's opinion during planning, architecture decisions, code review, or any situation where a diverse AI perspective adds value.
Instructions
- Formulate a clear, specific prompt that includes relevant context
- Run the command below with your prompt
- Parse and critically evaluate Codex's response
- Incorporate useful insights into your reasoning
Command
codex exec --skip-git-repo-check "<your prompt here>"Guidelines
- Always include sufficient context in the prompt (project details, constraints, what's already been decided)
- Frame questions to get actionable, specific answers rather than generic advice
- When Codex's response conflicts with your own analysis, flag the disagreement for council discussion
- Do NOT blindly accept Codex's output — treat it as one voice in the council
- For multi-part questions, break them into separate calls for clearer responses
- Keep prompts under 4000 characters for best results
- Timeout: allow up to 60 seconds for a response
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.