codex-review AGENTS.md

Project instructions for Codex Review, a command-driven tool for planning work, approving plans, implementing them, and reviewing the results.

In plain words
What is it for?
Maintaining review workflows, handling multiple planning rounds, implementing approved plans, and keeping findings and outcomes inspectable.
Why use it?
They define how workflows advance and ensure implementation reviews use the approved plan as their reference.

Instructions file for CodexOpenCode

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/boyand/codex-review/agents-md
Clone the repo
git clone --depth 1 https://github.com/boyand/codex-review

Made for: Codex, OpenCode.

Per session 1,034 This file is loaded in full into every session.
When invoked 1,034 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01034 $0.01034
Opus 5 $0.00517 $0.00517
Sonnet 5 $0.00207 $0.00207
Haiku 4.5 $0.00103 $0.00103

Measured 3d ago against content hash 0a877186a80e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex-review AGENTS.md 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 3d 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.

- The wrapper rebuilds the Go engine to `.bin/codex-review-go`, walks a small parent-process chain to find the current Claude session file under `~/.claude/sessions/`, injects hidden `--session-pid` and `--session-id` ru
AGENTS.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Review — Required Behavior and Architecture

This plugin is command-driven and session-scoped.

Required product behavior

These are the non-negotiable behaviors the plugin must preserve:

  • Commands must resolve the correct workflow automatically from the current Claude Code session.
  • The normal user path must not require --workflow <id>.
  • Multi-round plan and impl must work with explicit user choices to move forward, repeat, or finish.
  • Running /codex-review:impl from plan/approval counts as an explicit user choice to move forward and should auto-advance to implement.
  • The canonical plan under review is .claude/codex-review/workflows/<id>/artifacts/plan.md.
  • Implementation review must compare against that canonical approved plan, not a mutable native Claude plan file.
  • Findings/outcomes must remain inspectable through summary and the workflow artifacts.
  • The normal flow is command-driven. Hidden hook progression is not part of the default architecture.

High-level architecture

Workflows live under: .claude/codex-review/workflows/<workflow-id>/

Key files:

  • workflow.json — workflow state for phase, round, owner session, status, and plan source
  • decisions.tsv — normalized findings/outcome ledger used by summary
  • artifacts/plan.md — sticky canonical plan snapshot
  • artifacts/plan-review-rN.md and artifacts/plan-findings-rN.md
  • artifacts/implement-review-rN.md and artifacts/implement-findings-rN.md

Runtime model:

  • The tracked wrapper entrypoint is "${CLAUDE_PLUGIN_ROOT}/.bin/codex-review".
  • The wrapper rebuilds the Go engine to .bin/codex-review-go, walks a small parent-process chain to find the current Claude session file under ~/.claude/sessions/, injects hidden --session-pid and --session-id runtime flags when available, and executes the binary from the workflow root when available.
  • The Go engine resolves the current Claude session and then resolves that session's workflow.
  • If explicit runtime hints fail to resolve, the engine fails closed. It does not guess another workflow or fall back to another Claude session's plan.
  • plan seeds the workflow from the current session's native Claude plan only when the canonical artifacts/plan.md does not already exist, or when --plan explicitly replaces it.
  • Review rounds are forward-only:
    • __repeat increments the round and runs another review
    • __approve advances plan -> implement or completes the workflow
  • Prior round artifacts are preserved.

Read the full file on GitHub · 88 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. 3d ago First seen · 88 lines · 1,034 tokens per session scan B 0a877186a80e

Subscribe to this mod's changes

codex-review AGENTS.md is an instructions file published in the GitHub repository boyand/codex-review (16 stars, last pushed 17d ago), licensed MIT. It adds 1,034 tokens to every session, about $0.0052 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 2026-08-30.

Related

Other instructions, from other repositories

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

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

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

next.js 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