codex-sidecar CLAUDE.md

A set of instructions for Claude Code when working in the codex-sidecar code repository. It describes the repository’s rules, commands, package manager, architecture, and expected results.

In plain words
What is it for?
It helps Claude Code install dependencies, type-check, test, build, and run individual tests in the repository.
Why use it?
It gives the coding agent the project-specific information needed to make changes and run checks correctly.

Instructions file

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/kitepon/codex-sidecar/claude-md
Clone the repo
git clone --depth 1 https://github.com/kitepon/codex-sidecar
Per session 2,798 This file is loaded in full into every session.
When invoked 2,798 The same file — it is already loaded in full.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5 $0.02798 $0.02798
Opus 5 $0.01399 $0.01399
Sonnet 5 $0.00560 $0.00560
Haiku 4.5 $0.00280 $0.00280

Measured yesterday against content hash 0dbfc1d6797c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-sidecar CLAUDE.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 yesterday.

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.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

AGENTS.md is the canonical contract for agents working in this repo and applies to Claude as well. Read it before making engineering decisions. This file is the Claude-focused supplement.

Commands

Use corepack pnpm. Bare pnpm is not guaranteed to be on PATH in this environment and the project pins [email protected] via packageManager. Do not switch package managers.

corepack pnpm install
corepack pnpm typecheck   # builds core first, then typechecks every package
corepack pnpm test        # core + mcp tests
corepack pnpm build

Test runner is node --test against compiled dist/*.test.js, not source. Each package's test script does tsc -p tsconfig.json && node --test dist/...test.js. Implications:

  • Running a single core test file directly:
    corepack pnpm --filter codex-sidecar-core build
    node --test packages/core/dist/safety.test.js
    
  • Running a single MCP test:
    corepack pnpm --filter codex-sidecar-mcp build
    node --test packages/mcp/dist/index.test.js
    
  • Filtering by test name uses node's native runner: node --test --test-name-pattern='<regex>' packages/core/dist/<file>.test.js.
  • After editing .ts, you must rebuild before re-running a single test, or the new code is invisible.

packages/cli has no test script — it is a thin delegator to core.

Smoke a read-only App Server turn against this repo (after corepack pnpm build):

node packages/cli/dist/index.js diagnostics --project "$PWD" --preset review
node packages/cli/dist/index.js explore --project "$PWD" 'Reply exactly: OK'

Local Claude Settings

No dotagents checkout or host-global setting is required to build or operate this repository. Optional host-local .claude/settings.json files remain ignored and must not be committed.

Architecture

Two layers, three packages, strict one-way dependency:

caller (human / Claude Code / MCP client / hook)
  ↓
packages/cli ──┐
packages/mcp ──┤──→ packages/core ──→ Codex App Server (stdio)
               │                  └─→ isolated git worktree (codex_work only)

Read the full file on GitHub · 151 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. yesterday First seen · 151 lines · 2,798 tokens per session scan A 0dbfc1d6797c

Subscribe to this mod's changes

codex-sidecar CLAUDE.md is an instructions file published in the GitHub repository kitepon/codex-sidecar (1 stars, last pushed 3d ago), licensed MIT. It adds 2,798 tokens to every session, about $0.0140 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

codex-agent-sdk-go CLAUDE.md

Instructions for hishamkaram/codex-agent-sdk-go, covering codex agent sdk for go, what this is, build & test, architecture and critical rules.

hishamkaram/codex-agent-sdk-go · 1,528 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

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

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 · 5,182 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 · 4,345 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