Codex Debugging

SkillAI & models

Lets your agent debug the Codex CLI by reading its source code and tracing bugs through its modules.

Then ask your AI: use the Codex Debugging skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.

No other account needed.

Add it as a step in a pipeline you build on Ahel, or connect Ahel to Claude, ChatGPT, Cursor, Claude Code or Codex and ask your AI to use it.

About this skill

Codex debugging: codex-rs core/tui/exec/cli/app-server/config.

What this skill tells your AI

The instructions your AI receives, as published by steipete/agent-scripts in skills/codex-debugging/SKILL.md and read by Ahel’s review.

Use when investigating Codex CLI/app behavior, config parsing, tool behavior, prompts, MCP/app wiring, or runtime bugs.

Prefer local source before web/docs:

cd ~/Projects/codex
sed -n '1,220p' codex-rs/AGENTS.md

Then search targeted areas:

rg "<symbol|setting|error|feature>" codex-rs/{core,tui,exec,cli,app-server,app-server-protocol,config}

Identify whether the behavior is CLI, TUI, app server, protocol, config, or exec/tooling.
Read the owning module and adjacent tests before proposing changes.
Check local config in ~/.codex/config.toml only after understanding the source contract.
Prefer small repros or focused tests over broad speculation.

For OpenAI API/product docs, use the official-docs path only when source is insufficient.
For local browser automation in CLI, use $browser-use; the bundled Browser plugin is Codex app-only.

Advanced