agentmods.dev

codex-sidecar AGENTS.md

Repository instructions for Codex agents working on codex-sidecar, a shared execution layer that lets other tools call Codex safely.

In plain words
What is it for?
Use it to guide work on the sidecar’s CLI, MCP tools, integrations, safety behavior, and development workflow.
Why use it?
It gives agents the project’s purpose, repository structure, language rules, and engineering constraints in one place.

Instructions file for CodexOpenCode

1 3d ago A scan 2,149 tokens original MIT
View the source file kitepon/codex-sidecar
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/agents-md
Clone the repo
git clone --depth 1 https://github.com/kitepon/codex-sidecar

Made for: Codex, OpenCode.

Per session 2,149 This file is loaded in full into every session.
When invoked 2,149 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 $0.02149 $0.02149
Opus 5 $0.01074 $0.01074
Sonnet 5 $0.00430 $0.00430
Haiku 4.5 $0.00215 $0.00215

Measured yesterday against content hash b0e9a64a80f3, 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 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 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.

AGENTS.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

このリポジトリで作業する Codex / エージェント向けの入口メモ。

ユーザーとの会話は日本語で行う。

このリポジトリ固有の判断は本ファイルとdocs/README.mdだけで完結させる。 特定hostのglobal instructionや別repositoryを、製品開発の必須正本にしない。

Project Purpose

codex-sidecar は、kitepon.dev の AI 開発基盤群から Codex を sidecar agent として安全に呼び出すための共通実行レイヤー。

単なる codex review CLI ではなく、Throughline / Caveat / Latticeなどの 現役プロジェクトと接続できる「AI 作業OS」の部品として設計する。Claude Code が主で動く環境に、 Codex の別視点、反対意見、レビュー、調査、限定的な修正能力を差し込む。

同時に、汎用ツールとしても成立させる。設計は「generic core」と 「kitepon.dev ecosystem overlay」の二層に分ける。generic core は他の リポジトリでも単体で使える CLI/MCP/安全実行基盤、overlay はユーザーの MCP/OAuth/hook/memory/cost 系プロジェクトに強く刺さる preset / safety profile / context adapter とする。

重要な前提:

  • Claude が主導し、Codex は sidecar / second opinion として呼ばれる。
  • 呼び出し元は人間だけでなく、MCP server、hook、memory tool、cost optimizer になり得る。
  • 結果は人間向け文章だけでなく、他ツールが再利用できる machine-readable JSON として返す。
  • このrepoは単独でinstall、設定、診断、復旧、更新、releaseできる。dotagentsは 公開contractを統合するが、製品内部の状態や運用判断を所有しない。

対象 workflow と MCP tool:

  • CLI workflow review / MCP tool codex_review: diff / branch / patch の読み取り専用レビュー
  • CLI workflow explore / MCP tool codex_explore: コードベース調査とファイル参照つき回答
  • CLI workflow work / MCP tool codex_work: isolated git worktree 上での小さな修正
  • CLI workflow opinion / MCP tool codex_opinion: 設計案への反対意見、見落とし、代替案の提示
  • CLI workflow risk-check / MCP tool codex_risk_check: OAuth / MCP / secrets / Docker / hooks / CI などの重点リスク確認
  • CLI workflow auditor / MCP tool codex_auditor: primary tool-use auditor 用の pass / missingTools 判定
  • CLI workflow generate / MCP tool codex_generate: caller所有schemaによる任意の構造化JSON生成

製品管理用CLIはdiagnostics、factory-diagnostics、factory-errors、 auth-status、auth-recoverと、耐久work用のwork-start / work-result / work-cancel / work-recover / work-auth-recoverを持つ。現在の全入口は docs/USAGE.mdを正とする。

非目的:

  • 画像生成 API 課金の回避
  • Codex App Server を一般 OpenAI API gateway として使うこと
  • active working tree を Codex に自由編集させること
  • approval prompt や危険操作を隠すこと

Repository Shape

  • packages/core/: config loading, safety policy, App Server/session handling, worktree isolation, normalized results
  • packages/cli/: codex-sidecar review|explore|work|opinion|risk-check|auditor
  • packages/mcp/: Claude Code などの MCP client から呼ぶ codex_review / codex_explore / codex_work / codex_opinion / codex_risk_check / codex_auditor
  • docs/: 設計判断、protocol 方針、safety model
  • examples/: consuming repo 側に置く .codex-sidecar.yml の例

Read the full file on GitHub · 147 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 · 147 lines · 2,149 tokens per session scan A b0e9a64a80f3

Subscribe to this mod's changes

codex-sidecar AGENTS.md is an instructions file published in the GitHub repository kitepon/codex-sidecar (1 stars, last pushed 3d ago), licensed MIT. It adds 2,149 tokens to every session, about $0.0107 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.

Code reviewProductivityai-agentsapp-serverautomationclaude-codecodex
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