Skip to content
Skills Library
AI & agents · Tool integration

codex

/codex

Claude-to-Codex bridge to delegate bulk mechanical work, get an independent cross-model diff review, or ask a read-only question. Triggers only when the user names Codex, as in "use codex", "have codex review", "cross-check with codex", "ask codex".

Repository
cc-settings ↗
Licence
MIT
Last repository change
23.10.2026

Assessment and security

100/ 100Class: good
Format25 / 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
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 23.10.2026, 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

Claude-to-Codex bridge to delegate bulk mechanical work, get an independent cross-model diff review, or ask a read-only question. Triggers only when the user names Codex, as in "use codex", "have codex review", "cross-check with codex", "ask codex".

Triggers from the description

use codexhave codex reviewcross-check with codexask codex

Arguments

/codex [exec|review|ask] [task]
Original author description

Claude-to-Codex bridge to delegate bulk mechanical work, get an independent cross-model diff review, or ask a read-only question. Triggers only when the user names Codex, as in "use codex", "have codex review", "cross-check with codex", "ask codex".

How it works

  1. Standalone Codex
  2. Claude-only bridge
  3. Subcommands
  4. Quota and cost guidance
  5. Availability states
Original SKILL.md headings · 125 lines, 883 words
SKILL.md preview
---
name: codex
argument-hint: "[exec|review|ask] [task]"
description: Claude-to-Codex bridge to delegate bulk mechanical work, get an independent cross-model diff review, or ask a read-only question. Triggers only when the user names Codex, as in "use codex", "have codex review", "cross-check with codex", "ask codex".
context: main
---

# 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; the script refuses when it detects a Codex session. Do the requested task
locally with native tools. When the user asks for an independent review, spawn
`claude-verifier` (a Claude model through the read-only `claude-run.ts` bridge)
or a fresh native `reviewer`; 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:

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

---

## Subcommands

### exec -- delegate mechanical or bulk work

```bash
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.

**Write the task as an outcome, not a recipe.** The script wraps every `exec` task in a completion contract (run the repo's local checks, fix what the change broke, do not stop after a first implementation, leave changes uncommitted, report what was verified). Codex returns that report as JSON, and the script prints `ready: yes|no` after checking it against the working tree; read that line before reviewing the diff. Pass `--expected <minutes>` to have a silent worker killed and reported as stalled at 3x that. GPT-6 Astra stops early when done is undefined and over-follows step lists, so the task itself must say:

- the end state that means done (which behavior holds, which files or surfaces are covered);
- where to stop exploring, if the task is open-ended;
- any decision Codex must bring back instead of making (leave everything else to its judgment).

Do not add "ask before X" language for reversible in-scope work; the sandbox already bounds the blast radius, and Astra reads such language as a reason to stop.

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

```bash
git diff
```

Then run the proof gate:

```bash
bun run proof
```

### review -- independent cross-model diff review

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

Runs in a `read-only` sandbox. The prompt names the diff under review and the review contract (behavior and risk only, findings by HIGH / MEDIUM / LOW with file, line range, and fix). Codex decides how to inspect the repository.

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.

**Scope presets** — mirrors Codex's own `/review` presets (base-branch / uncommitted / commit / custom). Default with no flags is the uncommitted working-tree diff. Flags are mutually exclusive:

```bash
# Default: review the current uncommitted diff (git diff + git diff --cached)
bun "$HOME/.claude/src/scripts/codex-run.ts" review

# Only the staged diff
bun "$HOME/.claude/src/scripts/codex-run.ts" review --staged

# Diff against a base branch (merge-base...HEAD)
bun "$HOME/.claude/src/scripts/codex-run.ts" review --base main

# A single commit
bun "$HOME/.claude/src/scripts/codex-run.ts" review --commit abc1234
```

Codex's fourth preset ("custom instructions") is covered by `ask` above rather than a review flag.

**Model routing**: no model is pinned. Every subcommand runs on Codex's own configured default, so a newer Codex CLI brings newer models. Pin one per call with `--model <id>` before the task text, or per session with `CODEX_EXEC_MODEL`, `CODEX_REVIEW_MODEL`, `CODEX_ASK_MODEL`.

```bash
bun "$HOME/.claude/src/scripts/codex-run.ts" review --model <id> --base main
bun "$HOME/.claude/src/scripts/codex-run.ts" exec --model <id> "..."
```

### ask -- read-only second opinion

```bash
bun "$HOME/.claude/src/scripts/codex-run.ts" ask "your question here"
```

Runs in a `read-only` sandbox. Use for quick factual questions, architecture opinions, or anything where you want a fast external perspective without making any changes.

---

## Quota and cost guidance

- `review` and `ask` are read-only and cheap — use them freely as a cross-check; `exec` follows the quota routing above.
- If the bridge is unavailable (the script is missing, Codex is not installed or not logged in, or it is rate-limited), do the delegated task yourself, Claude-only, without asking which fallback to use. Say once that Codex was unavailable. Do not block the session.
- Routing policy comes from the `quota-steer` and `codex-verify` hooks (see "Claude and Codex routing" in `~/.claude/CLAUDE.md`); when either injects a reminder, prefer `exec`/`review` here over spawning Claude subagents.

---

## Availability states

The script handles all availability states gracefully. On failure it prints guidance to stderr and exits 1. Possible states:

- `not-installed` -- install Codex CLI and run `codex login`
- `unauthenticated` -- run `codex login`
- `no-access` -- plan entitlement issue; try `codex logout && codex login`
- `rate-limited` -- usage window exhausted; retry after the ~5-hour reset
- `unknown` -- one-off error; safe to retry
Files in this package (2)
  • SKILL.md 6 KB
  • agents/openai.yaml 1 KB

Versions

RepositoryScoreLicence
This page · darkroomengineering/cc-settings100MIT
davila7/claude-code-templates100MIT
tigercosmos/japanese-podcast-learner100MIT
puck-muling/peer-agent100MIT
ispc/ispc100BSD-3-Clause
dzhng/skills100MIT
majiayu000/spellbook100MIT
onlypfachi/chief100MIT
dzhng/skills100MIT

Database snapshot: 13.11.2026 · package version 11b890381cb0 (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

  • 100ask-codex
    Use when a Claude Code agent needs to delegate a question, subtask, or review to a local Codex instance.
  • 100ask-codex
    Consult OpenAI Codex (headless `codex exec`) for an independent review of a design doc, spec, plan, PRD, decision, diff, or piece of code, then reconcile its findings with your own view. Use ONLY when the user explicitly names codex (e.g. "ask codex", "what would codex say",…
  • 100ask-codex
    Get a second opinion or independent review from Codex (OpenAI) via the local Codex CLI. Use when the user wants Codex to review a design memo, PR, diff, or decision, or to cross-check an approach from another model. Also trigger on "Codexに聞いて", "Codexと相談", "Codexにレビュー", "Codexの意見", "別のモデルで確認".
  • 100review
    Delegate a read-only code review to a Codex subagent (GPT 6.1 Sol by default) that inspects code and reports findings without editing anything. Use when the user wants Codex — or "GPT-5.5" — to review, look over, audit, or give a second opinion on a diff, branch, pull request,…
  • 100review
    Cross-model orchestration between Claude Code and a local Codex CLI. Claude orchestrates, plans, and reviews; Codex implements and provides an independent second opinion. Use when you want two different model families to cross-check work rather than one model reviewing itself.
  • 100ask
    Ask another agent: message any running Claude Code session or Codex thread, or hand work to a fresh Claude or Codex worker, in any direction (Claude to Claude, Claude to Codex, Codex to Claude, Codex to Codex), on this machine or another over ssh. Use when the user says…

Feedback and reports

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