codex-in-claude: Instructions file for Claude Code

AGENTS.md

codex-in-claude AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from briandconnelly/codex-in-claude. It costs 6,484 tokens per session, scanned A, original, MIT.

Repository instructions for codex-in-claude, a Claude Code plugin that calls the OpenAI Codex command-line tool through a Python server. They explain the package boundary, shared library, command-line contract, and development conventions.

In plain words
What is it for?
Use them when modifying, testing, or reviewing the codex-in-claude repository. They guide work on its Python package, command-line behavior, backend adapter, and connection to the shared pontonier library.
Why use it?
They help contributors know where a change belongs and which externally visible settings and interfaces must remain consistent. They reduce accidental behavior changes when working across the bridge and its shared dependency.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is briandconnelly/codex-in-claude's own configuration. It tells Claude Code, Codex and OpenCode how to work on codex-in-claude itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codex-in-claude configures →

Reuse

Borrowing it

Nothing to install: this file belongs to briandconnelly/codex-in-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/briandconnelly/codex-in-claude/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/briandconnelly/codex-in-claude

Made for: Claude Code, Codex, OpenCode.

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 codex-in-claude AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/briandconnelly/codex-in-claude/agents-md/github.svg)](https://agentmods.dev/instructions/briandconnelly/codex-in-claude/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/briandconnelly/codex-in-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/briandconnelly/codex-in-claude/agents-md/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 codex-in-claude AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/briandconnelly/codex-in-claude/agents-md"><img src="https://agentmods.dev/badge/instructions/briandconnelly/codex-in-claude/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,484 This file is loaded in full into every session.
When invoked 6,484 The same file — it is already loaded in full.
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 $0.06484 $0.06484
Opus 5 $0.03242 $0.03242
Sonnet 5 $0.01297 $0.01297
Haiku 4.5 $0.00648 $0.00648

Measured 8d ago against content hash b8af2bb85cfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

codex-in-claude AGENTS.md 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 8d 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.

AGENTS.md · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent working conventions

Conventions for any agent (or human) working in this repository.

What this is

A Claude Code plugin that calls the OpenAI Codex CLI via a FastMCP server. The Python package is codex_in_claude under src/. Generic, CLI-agnostic machinery lives in the shared pontonier library (pontonier.core and the frozen pontonier.backend protocol), which this package consumes as a dependency — the planned extraction of the old in-repo _core/ happened.

  • Rule: this bridge pins its externally visible core knobs explicitly (config.WORKTREE_CONFIG: worktree prefix, baseline-commit identity) rather than inheriting pontonier defaults; changing them is a behavior change, not a refactor.
  • The declarative half of the CLI contract also lives as cli_contract.PONTONIER_CONTRACT (the shared BackendContract shape) with tests pinning its derivation from the legacy constants, and backend.CodexBackend adapts this bridge onto the frozen pontonier AgentBackend protocol (contract_api_version = 1), which every model-bearing run is staged through.

Package boundary

Which repo a change belongs in — this bridge or upstream pontonier. This section is the single home for that decision; other docs link here rather than restating it. pontonier's own README lists what the shared library already exposes — read it there rather than keeping a copy of that list in this repo.

Two questions route an ordinary change:

  1. Does the code have to know it is talking to codex? If yes, it stays here.
  2. Does it extend an abstraction pontonier already exposes, or does another bridge have the same confirmed need? If yes, it goes upstream.

Question 1 wins when both answer yes: Codex-aware code never moves upstream, and a change that needs both halves is the mixed change below. If neither question gives a yes, keep the code here. Absence of the word "codex" is not evidence that a mechanism is shared, and a second caller that does not exist yet is not a requirement.

Read the full file on GitHub · 370 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.

  1. 8d ago First seen · 370 lines · 6,484 tokens per session scan A b8af2bb85cfd

Subscribe to this mod's changes

codex-in-claude AGENTS.md is an instructions file published in the GitHub repository briandconnelly/codex-in-claude (3 stars, last pushed 5d ago), licensed MIT. It adds 6,484 tokens to every session, about $0.0324 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens