Skip to content
Skills Library
AI & agents · Tool integration

Codex Integration

/Codex Integration

Use this skill when delegating complex coding tasks to OpenAI Codex CLI and coordinating work between Claude and Codex.

Licence
MIT
Last repository change
03.06.2026

Assessment and security

90/ 100Class: good
Format15 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
4
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 03.06.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use this skill when delegating complex coding tasks to OpenAI Codex CLI and coordinating work between Claude and Codex.

Original author description

Use this skill when delegating complex coding tasks to OpenAI Codex CLI and coordinating work between Claude and Codex.

How it works

  1. Pre-check
  2. Default configuration
  3. When to delegate
  4. Interaction modes
  5. Session handling
  6. Model selection
  7. Prompt guidance
  8. Best practices
  9. References
Original SKILL.md headings · 73 lines, 308 words
SKILL.md preview
---
name: Codex Integration
description: Use this skill when delegating complex coding tasks to OpenAI Codex CLI and coordinating work between Claude and Codex.
---

# Codex Integration Skill

This skill defines delegation patterns for Codex-assisted coding.

## Pre-check

Before Codex operations:
1. Check for `.codex/config.toml`.
2. If missing, ask user before bootstrapping.
3. Bootstrap using `skills/codex-ecosystem/SKILL.md` guidance after confirmation.

## Default configuration

```toml
model = "gpt-5.4"
model_reasoning_effort = "xhigh"
sandbox_mode = "workspace-write"
approval_policy = "on-request"
```

## When to delegate

Delegate when tasks are multi-file, long-running, architecture-heavy, or require deep analysis.

## Interaction modes

### MCP mode
Use `mcp__codex-native__codex` and `mcp__codex-native__codex-reply` for interactive multi-turn work.

### Headless mode
Use `codex exec` for one-off scripted tasks.

### Background mode
Use background execution for long tasks and summarize results after completion.

## Session handling

- `threadId` should be preserved for follow-up calls.
- Session bookkeeping in `scripts/codex-interactive.py` is process-local and in-memory.

## Model selection

- Simple: `gpt-5.4` + low reasoning
- Medium: `gpt-5.4` + medium reasoning
- Complex: `gpt-5.4` + high reasoning
- Critical/security: `gpt-5.4` + xhigh reasoning

## Prompt guidance

When crafting prompts for Codex, follow the GPT-5.4 prompt patterns in `references/codex-prompt-guidance.md`. Key patterns:
- Use **output contracts** to constrain what and how much the model outputs.
- Use **tool persistence rules** so Codex doesn't stop early.
- Use **completeness contracts** for multi-step or batch tasks.
- Use **verification loops** before finalizing results.
- For coding tasks, apply **autonomy & persistence** — Codex should carry changes through implementation, not stop at analysis.

## Best practices

1. Keep prompts specific — follow prompt guidance patterns.
2. Validate outputs before applying.
3. Ask before enabling MCP servers or writing config files.
4. Enable only MCPs needed for the current task.
5. Use dependency checking for multi-step workflows.
6. Apply action safety frames for irreversible operations.

## References

- `references/codex-cli-reference.md` — CLI commands, flags, config
- `references/codex-prompt-guidance.md` — GPT-5.4 prompt patterns and best practices
- `examples/delegation-patterns.md` — delegation examples
- `skills/codex-ecosystem/SKILL.md` — bootstrap and MCP setup
Files in this package (4)
  • SKILL.md 2 KB
  • examples/delegation-patterns.md 6 KB
  • references/codex-cli-reference.md 11 KB
  • references/codex-prompt-guidance.md 11 KB

Versions

The database has no other skills named Codex Integration.

Database snapshot: 13.11.2026 · package version c5cd1856c10e (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 95codex-cli
    Reference for using OpenAI Codex CLI to handle complex coding tasks. Use when Research-Claw needs to delegate multi-file projects, iterative debugging, or complex code generation to a specialized AI coding tool. Trigger words: codex, coding CLI, delegate coding, complex project.
  • 100codex
    Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fixing. Requires the codex CLI and a git repository.
  • 95community-codex
    Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fixing. Requires the codex CLI and a git repository.
  • 90codex
    Use when asked to use Codex, GPT, OpenAI, or the Codex CLI to delegate; write-enabled unless mode:plan. Not for messaging a Codex session.
  • 90codex-cli-specialist
    OpenAI Codex CLI and cross-platform skill authoring. Use when setting up Codex CLI, converting or syncing skills between Claude Code and Codex, configuring agents/openai.yaml, or validating cross-platform skill compatibility.
  • 100codex
    Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fixing. Requires the codex CLI and a git repository.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.