codex
Skill0 starsChanged 3 months agoMITView on GitHub
Talk to OpenAI Codex CLI for plan refinement, code review, research, and brainstorming. Use when user says "talk to codex", "ask codex", "have codex review", "continue with codex", or "follow up with codex". Uses gpt-5.4 with medium or high reasoning effort. Maintains conversation sessions for multi-turn discussions.
- Installs packages
135 other projects use a version of this.
Adopted by
Most recently taken up by
- holylight1979/AtomicMemory-ClaudeCodetheir own version, first seen Nov 8, 2026
- mxrsv/agents-skillstheir own version, first seen Nov 8, 2026
- hemal08ce094/DesignSkillsSwiftUItheir own version, first seen Nov 8, 2026
- choughton/feature-design-prompt-templatestheir own version, first seen Nov 8, 2026
- hurleywgly/skillstheir own version, first seen Nov 8, 2026
- puck-muling/peer-agenttheir own version, first seen Nov 8, 2026
Used with
Projects with it also use ios-sync, compare-screenshots and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Saqlain-811Skillios-sync
Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)
Also in 6 projects that use this
transitive-bullshitSkillcompare-screenshots
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
Also in 5 projects that use this
dzhngSkillimplement-spec-with-codex
Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with Codex, or to run implement-spec with Codex as the implementer.
Also in 4 projects that use this
Saqlain-811Skillios-clean
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)
Also in 5 projects that use this
john-data-chenSkilltouchdesigner-mcp
Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
Also in 7 projects that use this
math-incSkillminecraft-modpack-server
Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.
Also in 5 projects that use this
- +1 more from Saqlain-811
Other versions135 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 135
- NousResearch/hermes-agent★ 262ksame name
- garrytan/gstack★ 141ksame name
- dzhng/jevgrep★ 3.2ksame name
- ispc/ispc★ 3ksame name
- bergside/awesome-design-skills★ 2.9ksame name
- dataplat/dbatools★ 2.9ksame name
- Lilac-Labs/gini-agent★ 1.9ksame name
- Open-Curiosity/gini-agent★ 1.9ksame name
- dzhng/skills★ 1.5ksame name
- clice-io/clice★ 1.4ksame name
125 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 repository11 other files it gives its agents.
- email-strategySkill
- entity-consistency-sweepSkill
- framer-code-componentsSkill
- goalSkill
- hc-rankSkill
- humanizerSkill
- keyword-guidelinesSkill
- migration-analysisSkill
- roastSkill
- session-handoffSkill
- surfer-keyword-testerSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 111 edited versions we read keep these.
2
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 25
Run the script with a JSON prompt via stdin:
- Distinctive: line 41
Always uses gpt-5.4. Reasoning effort strategy:
“Common” is measured: kept by at least 6 in 10 of the 111 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
Codex CLI Integration
This skill enables multi-turn conversations with OpenAI Codex CLI for:
- Plan refinement and review
- Code review and debugging
- Research and brainstorming
- Getting a second opinion on approaches
How to Use
Starting a Conversation
Run the script with a JSON prompt via stdin:
echo '{"prompt": "Review this implementation plan and suggest improvements..."}' | python3 scripts/codex_chat.pyContinuing a Conversation
The script stores session IDs automatically. To continue the last conversation:
echo '{"prompt": "What about edge cases?", "continue_session": true}' | python3 scripts/codex_chat.pyReasoning Selection
Always uses gpt-5.4. Reasoning effort strategy:
- First message of a conversation: always use high
- Follow-up messages: choose based on conversation complexity so far
- high — Complex threads, deep analysis, architecture decisions
- medium — Simple follow-ups, clarifications, quick questions
echo '{"prompt": "...", "reasoning": "medium"}' | python3 scripts/codex_chat.pyBackground Execution
For long-running Codex tasks, use the Task tool with background mode:
When Codex might take a while:
1. Use Task tool with run_in_background: true
2. Pass the Bash command that runs the script
3. Continue other work
4. Check TaskOutput when readyInput JSON Schema
{
"prompt": "Required - the prompt to send to Codex",
"reasoning": "Optional - 'medium' or 'high' (default: high)",
"continue_session": "Optional - true to continue last conversation",
"working_directory": "Optional - project directory for context"
}Output JSON Schema
{
"response": "Codex's response text",
"session_id": "ID for continuing this conversation",
"model": "Model that was used",
"reasoning": "Reasoning level that was used",
"success": true
}Session Management
Sessions are stored in ~/.codex-claude-session.json. Each new conversation creates a new session unless continue_session: true is passed.
Important: Session continuation requires being in a git repository. New sessions can start anywhere, but to continue a session you need to be in a git repo (use working_directory to specify a project path).
Exit Codes
- 0: Success
- 1: Input/configuration error
- 2: Codex CLI error
- 3: Codex not installed
Examples
Basic plan review
echo '{"prompt": "Review this plan for implementing user authentication. Look for security issues and suggest improvements."}' | python3 scripts/codex_chat.pyQuick question with medium reasoning
echo '{"prompt": "What are the pros and cons of this approach?", "reasoning": "medium"}' | python3 scripts/codex_chat.pyContinue a conversation
echo '{"prompt": "What about the error handling I mentioned earlier?", "continue_session": true}' | python3 scripts/codex_chat.pyDoes 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.

