codex

A bridge for sending selected work between Claude Code and OpenAI Codex. It supports delegated execution, independent review, and read-only advice.

In plain words
What is it for?
Use it for mechanical edits, bulk file changes, parallel work, independent diff reviews, or read-only second opinions from Codex.
Why use it?
It helps divide repetitive or large batches of work and provides a second review when an independent check is useful. The instructions also define when the bridge should not be used recursively.

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/darkroomengineering/cc-settings/codex
Any agent
npx skills add darkroomengineering/cc-settings --skill codex
Clone the repo
git clone --depth 1 https://github.com/darkroomengineering/cc-settings

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,312 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00072 $0.01312
Opus 5 $0.00036 $0.00656
Sonnet 5 $0.00014 $0.00262
Haiku 4.5 $0.00007 $0.00131

Measured 2d ago against content hash 4306562c54a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex scanned grade A with 0 findings 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 2d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/codex/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Bridge

Standalone Codex

If the active host is already standalone Codex, stop before any bridge command. Never recursively invoke codex-run.ts or launch the Codex CLI from inside Codex. Do the requested task locally with native tools. When the user asks for an independent review, spawn a fresh native reviewer and wait until it finishes; do not spawn codex-verifier.

Everything below is the Claude-only bridge workflow.

Claude-only bridge

Invoke the OpenAI Codex CLI from inside a Claude session. Three subcommands map to three distinct use cases.

All subcommands are called via:

bun "$HOME/.claude/src/scripts/codex-run.ts" <subcommand> [args]

Subcommands

exec -- delegate mechanical or bulk work

bun "$HOME/.claude/src/scripts/codex-run.ts" exec "the full task description"

Runs Codex in a workspace-write sandbox. Use this when a task is:

  • Mechanical (repetitive edits, file scaffolding, boilerplate generation)
  • Bulk (touching many files at once where Claude's serial context would be slow)
  • Parallelizable with Claude's own work (start Codex on one half while Claude handles the other)

Quota routing: Codex is metered by messages per ~5-hour window, not by tokens. Hand it one big complete task, not a sequence of small steps. A single exec call for a whole feature costs the same quota as one exec call for a single file.

After exec returns, ALWAYS review Codex's diff before trusting it:

git diff

Then run the proof gate:

bun run proof

review -- independent cross-model diff review

bun "$HOME/.claude/src/scripts/codex-run.ts" review

Runs in a read-only sandbox. Codex reads the repo itself (git diff, git status) and reports findings by severity (HIGH / MEDIUM / LOW), covering correctness bugs, security issues, and obvious quality problems.

Use this after you have finished a diff and want a second opinion from a different model family. Codex and Claude have different blind spots — cross-model review catches what Opus self-review misses. This is the primary reason to prefer review over asking Claude to review its own output.

Read the full file on GitHub · 124 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 124 lines · 72 tokens per session scan A 4306562c54a4

Subscribe to this mod's changes

codex is a skill published in the GitHub repository darkroomengineering/cc-settings (42 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 1,312 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. 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

dotfiles-bootstrap

Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.

sebastienrousseau/dotfiles · 88 tokens

astro-dso-doc

Generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), AND a ready-to-paste PixInsight project Description field for a deep-sky object (DSO) astrophotography project. Use this skill whenever the user mentions astrophotography, a DSO…

jjmartres/ai-coding-agents · 244 tokens

document-code

Apply Google Style documentation standards to Python, Go, TypeScript, and Terraform code. Use when writing or reviewing code that needs docstrings/comments/JSDoc, when asked to "document this code", "add docstrings", "follow Google Style", or when improving code documentation quality. Supports Python docstrings, Go…

jjmartres/ai-coding-agents · 88 tokens

work-on-ticket

Fetches Jira ticket details, creates an appropriately named branch, and initiates the task planning workflow. Use when the user says "work on [TICKETID]" or similar phrases.

jjmartres/ai-coding-agents · 41 tokens

datadog

Use this skill when you need to search Datadog logs, query metrics, tail logs in real-time, trace distributed requests, investigate errors, compare time periods, find log patterns, check service health, or export observability data.

jjmartres/ai-coding-agents · 51 tokens

document-project

Generate comprehensive, professional project documentation structures including README, ARCHITECTURE, USERGUIDE, DEVELOPERGUIDE, and CONTRIBUTING files. Use when the user requests project documentation creation, asks to "document a project", needs standard documentation files, or wants to set up docs for a new…

jjmartres/ai-coding-agents · 79 tokens