What is cc-codex CLAUDE.md?

Project instructions for combining Claude Code with Codex CLI, including when to delegate complex reasoning, planning, specifications, or analysis.

Use them when deciding whether Codex should help with architecture, trade-offs, detailed plans, technical specifications, or reviews.

They clarify which tasks should be handed to Codex and which simple operations should stay with Claude Code.

cc-codex CLAUDE.md — Instructions file for coding agents by rachittshah: Project instructions for combining Claude Code with Codex CLI…

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 instructions/rachittshah/cc-codex/claude-md

Clone the repo

git clone --depth 1 https://github.com/rachittshah/cc-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/instructions/rachittshah/cc-codex/claude-md.svg)](https://agentmods.dev/instructions/rachittshah/cc-codex/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/rachittshah/cc-codex/claude-md"><img src="https://agentmods.dev/badge/instructions/rachittshah/cc-codex/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 3,552 This file is loaded in full into every session.

When invoked 3,552 The same file — it is already loaded in full.

Security scan D 2 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.

Model	Per session	Once invoked
Fable 5	$0.03552	$0.03552
Opus 5	$0.01776	$0.01776
Sonnet 5	$0.00710	$0.00710
Haiku 4.5	$0.00355	$0.00355

Measured 5d ago against content hash 9610f66e581e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

cc-codex CLAUDE.md scanned grade D with 2 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 5d 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.

Harvests environment variableshighData exfiltration

Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.

printenv OPENAI_API_KEY

Reads agent configuration directoriesmediumAgent snooping

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

**Note**: The high reasoning effort is automatically enabled via `model_reasoning_effort = "high"` in `~/.codex/config.toml`

CLAUDE.md · 547 lines

How it starts

The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code + Codex Integration

Role: Claude Code delegates reasoning, planning, and specification tasks to Codex CLI using gpt-5 model with high reasoning effort

Core Directive

When Claude Code needs to:

Reason through complex problems
Plan multi-step implementations
Create detailed specifications
Analyze architectural decisions

→ Delegate to Codex CLI using gpt-5 model

Note: The high reasoning effort is automatically enabled via model_reasoning_effort = "high" in ~/.codex/config.toml

Usage Pattern

When to Call Codex

Call Codex for:

Deep reasoning - Complex logic, trade-offs, decision trees
Planning - Breaking down features into actionable steps
Specification - Creating detailed technical specs
Analysis - Code architecture, performance, security reviews
Design decisions - Comparing multiple approaches

When NOT to Call Codex

Do NOT call Codex for:

Simple code edits or file operations
Direct execution of known tasks
Quick lookups or simple questions
File reading/writing operations

Required Command Format

Always use this exact format:

codex exec -m gpt-5 --full-auto "YOUR_REASONING_TASK_HERE"

Command Breakdown

codex exec - Non-interactive execution
-m gpt-5 - REQUIRED: Use GPT-5 reasoning model
--full-auto - Automatic execution with workspace write access
"TASK" - Clear, specific reasoning/planning task

Note: High reasoning effort is automatically applied based on your ~/.codex/config.toml setting

Integration Rules

1. Model Requirement

# ✅ CORRECT - Always use gpt-5
codex exec -m gpt-5 --full-auto "reason through this problem"

# ❌ WRONG - Never omit model flag
codex exec --full-auto "reason through this problem"

2. Task Clarity

# ✅ CORRECT - Specific reasoning task
codex exec -m gpt-5 --full-auto "analyze three approaches for implementing user authentication: JWT, session-based, and OAuth2. Compare security, scalability, and complexity."

# ❌ WRONG - Vague request
codex exec -m gpt-5 --full-auto "help with auth"

Read the full file on GitHub · 547 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.

5d ago First seen · 547 lines · 3,552 tokens per session scan D 9610f66e581e

Subscribe to this mod's changes

cc-codex CLAUDE.md is an instructions file published in the GitHub repository rachittshah/cc-codex (11 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 3,552 tokens to every session, about $0.0178 per session on Opus 5. A static security scan graded it D with 2 findings (harvests environment variables, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

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

cc-codex CLAUDE.md