claude-codex-bridge

claude-codex-bridge is a skill for Claude Code from Jayden-X-L/claude-codex-bridge. It costs 68 tokens per session (1,211 once invoked), scanned A, original, MIT.

A bridge for sending work between Claude Code and Codex, two coding assistants, so one can review the other's result. It supports back-and-forth execution, review, and repair feedback.

In plain words
What is it for?
Use it to request a Codex audit of Claude's work, a Claude audit of Codex's work, or an automated repair loop after review.
Why use it?
It provides a defined handoff between the assistants and records whether the review completed or failed. This helps avoid treating an interrupted review as successful.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to request a Codex audit of Claude's work, a Claude audit of Codex's work, or an automated repair loop after review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jayden-x-l/claude-codex-bridge/claude-codex-bridge
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.

Any agent
npx skills add Jayden-X-L/claude-codex-bridge --skill claude-codex-bridge
Clone the repo
git clone --depth 1 https://github.com/Jayden-X-L/claude-codex-bridge

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-codex-bridge

README.md
[![agentmods](https://agentmods.dev/badge/skills/jayden-x-l/claude-codex-bridge/claude-codex-bridge/github.svg)](https://agentmods.dev/skills/jayden-x-l/claude-codex-bridge/claude-codex-bridge)
Your own site
<a href="https://agentmods.dev/skills/jayden-x-l/claude-codex-bridge/claude-codex-bridge"><img src="https://agentmods.dev/badge/skills/jayden-x-l/claude-codex-bridge/claude-codex-bridge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-codex-bridge

Your own site · 80×15
<a href="https://agentmods.dev/skills/jayden-x-l/claude-codex-bridge/claude-codex-bridge"><img src="https://agentmods.dev/badge/skills/jayden-x-l/claude-codex-bridge/claude-codex-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,211 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00068 $0.01211
Opus 5 $0.00034 $0.00606
Sonnet 5 $0.00014 $0.00242
Haiku 4.5 $0.00007 $0.00121

Measured 9d ago against content hash 2dd4e52dcd6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-codex-bridge 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/send-file-to-codex.mjs, scripts/send-to-codex.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/claude-codex-bridge/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.

Claude Codex Bridge

Use this skill for bidirectional Claude-Codex review loops.

  • Claude execution -> Codex audit -> Claude repair feedback.
  • Codex execution -> Claude audit -> Codex repair feedback.

Default to automatic return after audit unless the user explicitly asks for audit-only mode.

Bridge delivery defaults to cli mode through the helper scripts. In cli mode, the target CLI performs the audit and prints the result back into this same conversation; do not use desktop App automation.

CLI runs are tracked under .agent-bridge/runs/<runId>/. Use .agent-bridge/runs/latest.json to inspect the latest run. A completed run has status: success and cli_done.json; a failed run has status: error and bridge_error.json. If a run still says status: started, it is in progress or was interrupted; do not treat that as a successful audit.

CLI preconditions: Codex CLI must be runnable for Codex audits. The bridge tries AGENT_BRIDGE_CODEX_BIN, then codex from PATH, then /Applications/Codex.app/Contents/Resources/codex. claude --version plus claude auth status must work for Claude audits. If the Claude auth preflight fails, tell the user to run Claude Code login/status rather than treating it as an App handoff failure.

If a CLI is missing or auth fails, run:

node "$HOME/.agent-bridge/bridge.mjs" doctor

Use the doctor's suggested fix. Common fixes are:

npm install -g @openai/codex
npm install -g @anthropic-ai/claude-code
claude auth login
claude auth status

If Codex Desktop is installed, the bridge can use /Applications/Codex.app/Contents/Resources/codex without an npm Codex install.

Use --delivery current, --delivery ax, or --delivery new only when the user explicitly asks to operate the desktop App UI. In ax or current mode, treat bridge success as macOS paste/submit automation completion. If the bridge reports a focus error or non-zero exit, do not tell the user the feedback was delivered; report the error and ask them to bring the target app conversation to the front before retrying.

Read the full file on GitHub · 124 lines

Files

What ships with it

2 files 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. 9d ago First seen · 124 lines · 68 tokens per session scan A 2dd4e52dcd6f

Subscribe to this mod's changes

claude-codex-bridge is a skill published in the GitHub repository Jayden-X-L/claude-codex-bridge (15 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 1,211 once invoked, about $0.0003 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

gemini

Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…

nowork-studio/notfair-plugin · 184 tokens

audit

Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.

oliver-kriska/claude-elixir-phoenix · 35 tokens

boundaries

Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.

oliver-kriska/claude-elixir-phoenix · 33 tokens

triage

Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.

oliver-kriska/claude-elixir-phoenix · 32 tokens

critical-code-reviewer

Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.

posit-dev/skills · 67 tokens

han-release

Cut a Han release: update CHANGELOG.md with the changes since the last release, bump and tag every plugin that changed as {plugin-name}--v{version} so a version-constrained dependency can resolve, and publish a GitHub release crediting every merged pull request and closed issue to the people behind it. Use when…

testdouble/han · 172 tokens