A setup helper for connecting Claude Code and Codex CLI so they can call each other as MCP partners. MCP is a standard way for AI tools to communicate with external services or other agents.

Letting Claude call Codex, letting Codex call Claude, or optionally adding Codex as a Claude Code teammate.

It removes the manual configuration needed to register the bridge and check that the connection works.

setup — Skill for Claude Code and Codex by rbutera: A setup helper for connecting Claude Code and Codex…

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/rbutera/harness-bridge/setup

Any agent

npx skills add rbutera/harness-bridge --skill setup

Clone the repo

git clone --depth 1 https://github.com/rbutera/harness-bridge

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rbutera/harness-bridge/setup.svg)](https://agentmods.dev/skills/rbutera/harness-bridge/setup)

Your own site

<a href="https://agentmods.dev/skills/rbutera/harness-bridge/setup"><img src="https://agentmods.dev/badge/skills/rbutera/harness-bridge/setup.svg" alt="Measured on agentmods" height="20"></a>

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 696 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.

Model	Per session	Once invoked
Fable 5	$0.00019	$0.00696
Opus 5	$0.00010	$0.00348
Sonnet 5	$0.00004	$0.00139
Haiku 4.5	$0.00002	$0.00070

Measured 4d ago against content hash e3102c4ba1eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

setup 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

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

1. First check if `~/.codex/config.toml` exists. If not, create the directory and file.

.claude/skills/setup/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up claude-codex-bridge so Claude Code and Codex CLI can call each other as MCP partners.

The user may pass an argument: both (default), claude, or codex.

Setup Claude Code -> Codex (let Claude call Codex)

Run this command to register the codex MCP server:

claude mcp add codex -s user -- npx claude-codex-bridge serve codex

After running, verify it was added by checking:

claude mcp list

Confirm that codex appears in the list.

Setup Codex -> Claude (let Codex call Claude)

First check if ~/.codex/config.toml exists. If not, create the directory and file.
Read the existing file content. Then append or add the following TOML block (only if [mcp_servers.claude] is not already present):

[mcp_servers.claude]
command = "npx"
args = ["claude-codex-bridge", "serve", "claude"]
tool_timeout_sec = 600

Be careful not to duplicate the section if it already exists. If it exists, ask the user if they want to update it.

Install Codex Teammate Agent (optional)

The codex-teammate agent lets you spawn Codex as a Claude Code subagent/teammate. It knows how to use all 6 codex bridge tools automatically.

Run:

npx claude-codex-bridge install agent --global

Or for project-local:

npx claude-codex-bridge install agent --local

Verify the agent is available by starting a new Claude Code session. The agent will appear as codex-teammate subagent type in the Task tool.

Install /codex Skill for Claude Code (optional)

npx claude-codex-bridge install skill claude --global

Install /claude Skill for Codex (optional)

npx claude-codex-bridge install skill codex --global

After Setup

Tell the user:

For Claude Code: restart Claude Code or start a new session for the MCP server to be available
For Codex: restart Codex for the MCP server to be available
Available tools: codex_query, codex_review_code, codex_review_plan, codex_explain_code, codex_plan_perf, codex_implement (from Claude), and claude_query, claude_review_code, claude_review_plan, claude_explain_code, claude_plan_perf, claude_implement (from Codex)
Codex Teammate Agent: If installed, you can spawn Codex as a teammate with Task(subagent_type: "codex-teammate", prompt: "your task here")

Read the full file on GitHub · 81 lines

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.

4d ago First seen · 81 lines · 19 tokens per session scan B e3102c4ba1eb

Subscribe to this mod's changes

setup is a skill published in the GitHub repository rbutera/harness-bridge (1 stars, last pushed 8d ago), licensed MIT. It adds 19 tokens to every session and 696 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 2026-08-31.

Building agents ai claude-code codex coding-agents mcp model-context-protocol

trusty-squire

Use when a coding agent needs to sign up for a website or SaaS, provision an OAuth client or API key, pay a checkout, or otherwise act on a real website on the user's behalf — and the secret or card must NOT land in chat, source code, or a .env file. Trusty Squire is an MCP server that drives a real browser through…

Trusty-Squire/trusty-squire · 208 tokens

idesense

Guide for using JetBrains IdeSense tools for code navigation and analysis (plus the retained rename/move refactorings). TRIGGER: When ANY of these MCP tools are available in the current session: idefindusages, idefinddefinition, idefindclass, idefindfile, idesearchtext, idediagnostics, ideexplainsymbol…

vcth4nh/idesense · 172 tokens

internal-rag

Mandatory persistent project memory for substantial coding tasks. Use at task start, recovery, milestones, failures, before risky operations, before compaction, and before finishing. v1.0.1 adds type filtering, type-priority scoring, query expansion, grouped context output, and promote workflow.

PeterPirog/mcp-light-memory · 62 tokens

setup