Skip to content

CowboyLogic/ai-dev / skills/client-config-codex

client-config-codex

Flagged

Manage OpenAI Codex CLI configuration files including config.toml, project .codex/config.toml, profiles, model providers, sandbox and approval settings, permission profiles, rules files, MCP servers, hooks, skills, plugins, custom agents, AGENTS.md instructions, and requirements.toml. Use this skill whenever the user wants to view, edit, add, or understand any Codex setting: trusted projects, approval policy, sandbox mode, network access, allow-listing commands, MCP servers, hooks, skills, plugins and marketplaces, model or reasoning effort, custom model providers, authentication, sessions, or AGENTS.md. Trigger on: "configure codex", "codex config.toml", "trust this project in codex", "codex approval policy", "codex sandbox", "add MCP server to codex", "codex hook", "codex rules", "codex profile", "codex plugin", "set codex model", "codex AGENTS.md", or "show my codex config".

FileKindSize
README.mdmarkdown3.0 KB
SKILL.mdskill md8.9 KB
references/agents-plugins.mdmarkdown12.8 KB
references/cli-commands.mdmarkdown21.2 KB
references/config-schema.mdmarkdown43.0 KB
references/hooks.mdmarkdown17.0 KB
references/instructions.mdmarkdown7.5 KB
references/mcp.mdmarkdown12.9 KB
references/permissions.mdmarkdown23.9 KB
references/skills.mdmarkdown6.6 KB
scripts/show-config.pyscript19.1 KB
scripts/update-references.pyscript6.8 KB
sources.jsonconfig3.8 KB
# Codex Configuration Manager

A skill for viewing, editing, and explaining OpenAI Codex CLI configuration.

> [!NOTE]
> **Codex version:** verified against [Codex CLI 0.166.0](https://github.com/openai/codex/releases/tag/rust-v0.166.0)
> (released 2026-10-29; last verified 2026-11-01). The reference files distill the official Codex documentation and
> record where the installed CLI differs from it. Codex changes quickly, so re-verify when it
> ships a new release (see [Refreshing the references](#refreshing-the-references)).

## Overview

Codex configuration is TOML, spread across user, project, profile, and machine layers, and
it changes between releases. An agent answering from memory tends to invent keys or reuse
another client's schema. This skill routes each task to the reference material for the config
area involved and loads only that material.

This skill covers:

- `config.toml` layers and precedence, profiles, and project trust
- Model, reasoning effort, custom model providers, and feature flags
- Memories and app (connector) settings
- Sandbox mode, approval policy, permission profiles, auto-review, and `.rules` files
- MCP servers, hooks, skills, and plugins and marketplaces
- The `[agents]` table and where custom agents live (writing agent files is the job of the
  [agent-creator-codex](../agent-creator-codex/README.md) skill)
- `AGENTS.md` and `AGENTS.override.md` discovery
- Authentication, environment variables, and admin-enforced `requirements.toml`, including the
  Browser Use, Computer Use, and desktop-app network requirements
- CLI subcommands, `-c` overrides, sessions, and slash commands

The skill never reads or prints Codex credentials, and it asks before trusting a project or
loosening the sandbox and approval settings.

## Scripts

Both scripts are in `scripts/` and use only the Python standard library.

| Script | What it does |
|---|---|
| `show-config.py` | Displays every Codex config file that exists, with secrets redacted. Needs Python 3.11+ |
| `update-references.py` | Fetches the upstream documentation listed in `sources.json` into a staging directory so the reference files can be refreshed |

## Refreshing the references

Ask the agent to update the skill, or run `python scripts/update-references.py --all` and
follow the self-update procedure in [SKILL.md](SKILL.md). Every command, flag, and feature
written into a reference should be checked against the installed CLI (`codex --help`,
`codex <subcommand> --help`, `codex features list`) before it is kept, and the version
stamped here and in each reference file should move with the CLI release that was used.

## Official Documentation

| Resource | URL |
|---|---|
| Config basics | <https://developers.openai.com/codex/config-basic> |
| Config reference | <https://developers.openai.com/codex/config-reference> |
| Agent approvals and security | <https://developers.openai.com/codex/agent-approvals-security> |
| Hooks | <https://developers.openai.com/codex/hooks> |
| Codex releases | <https://github.com/openai/codex/releases> |
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall