codex-debugging

A troubleshooting guide for Codex, an AI coding tool, including its command line, interface, configuration, and tool connections.

In plain words
What is it for?
It helps diagnose configuration parsing, prompts, tool behavior, app-server communication, and runtime bugs.
Why use it?
It gives a focused way to investigate unexpected Codex behavior by checking the relevant source code, settings, and tests.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/steipete/agent-scripts/codex-debugging
Any agent
npx skills add steipete/agent-scripts --skill codex-debugging
Clone the repo
git clone --depth 1 https://github.com/steipete/agent-scripts

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 267 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00267
Opus 5 $0.00012 $0.00133
Sonnet 5 $0.00005 $0.00053
Haiku 4.5 $0.00002 $0.00027

Measured yesterday against content hash 886a702668f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex-debugging scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

3. Check local config in `~/.codex/config.toml` only after understanding the source contract.
skills/codex-debugging/SKILL.md · 36 lines

What it actually says

Codex Debugging

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

Source First

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}

Workflow

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

Notes

  • 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.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 36 lines · 24 tokens per session scan B 886a702668f1

Subscribe to this mod's changes

codex-debugging is a skill published in the GitHub repository steipete/agent-scripts (6,580 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 267 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens