Borrowing it
Nothing to install: this file belongs to kyto64/codex-pr-review-toolkit-minimal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kyto64/codex-pr-review-toolkit-minimal/main/AGENTS.mdgit clone --depth 1 https://github.com/kyto64/codex-pr-review-toolkit-minimalWrote 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.
[](https://agentmods.dev/instructions/kyto64/codex-pr-review-toolkit-minimal/agents-md)<a href="https://agentmods.dev/instructions/kyto64/codex-pr-review-toolkit-minimal/agents-md"><img src="https://agentmods.dev/badge/instructions/kyto64/codex-pr-review-toolkit-minimal/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.
<a href="https://agentmods.dev/instructions/kyto64/codex-pr-review-toolkit-minimal/agents-md"><img src="https://agentmods.dev/badge/instructions/kyto64/codex-pr-review-toolkit-minimal/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00754 | $0.00754 |
| Opus 5 | $0.00377 | $0.00377 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
codex-pr-review-toolkit-minimal 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
Repository
This is a minimal PR review skill pack for Codex CLI. There is no install script, no autonomous runner, no hooks, and no MCP auto-configuration.
Layout
| Path | Role |
|---|---|
plugins/pr-review-toolkit/skills/*/SKILL.md |
Source of truth for review instructions |
plugins/pr-review-toolkit/.codex-plugin/plugin.json |
Public plugin manifest (interface metadata) |
.agents/plugins/marketplace.json |
Local marketplace; source.path is ./plugins/pr-review-toolkit |
.codex/agents/*.toml |
Generated subagent definitions (6 perspectives only) |
scripts/generate_subagents.py |
Regenerate .codex/agents/ and .codex/config.toml from SKILL.md |
scripts/validate_plugin.py |
Validate plugin packaging |
Do not add install.sh, .mcp.json, hook runners, or codex-autonomous / codex-account artifacts.
Internationalization
- Primary language: English (
README.md,plugins/pr-review-toolkit/skills/*/SKILL.md, etc.) - Japanese translations:
docs/ja/(mirrors README, skills, samples, and attribution docs) - Edit English source files first; update
docs/ja/when maintaining translations
Subagents (issue #14)
Decision (2026-06): Adopt optional parallel subagent mode for pr-review, with sequential single-session review as the fallback.
- Custom agents live in
.codex/agents/(generated fromplugins/pr-review-toolkit/skills/*/SKILL.md) - Regenerate after skill edits:
python3 scripts/generate_subagents.py pr-revieworchestrates spawns explicitly; Codex only spawns subagents when asked- Perspective selection (#13) limits parallel spawns to control token cost
- Subagents inherit parent sandbox policy; do not set
sandbox_modeto bypass
Skills
| Skill | When to use |
|---|---|
pr-review |
Unified PR review with P0–P3 findings |
code-reviewer |
Correctness, security, maintainability |
silent-failure-hunter |
Error handling and silent failures |
pr-test-analyzer |
Test coverage quality |
comment-analyzer |
Comment accuracy |
type-design-analyzer |
Type invariants and encapsulation |
code-simplifier |
Complexity review (no behavior change) |
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.
- 9d ago First seen · 68 lines · 754 tokens per session scan A 2fdaaba92da2
codex-pr-review-toolkit-minimal AGENTS.md is an instructions file published in the GitHub repository kyto64/codex-pr-review-toolkit-minimal (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 754 tokens to every session, about $0.0038 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.
Other instructions, from other repositories
repobrain copilot-instructions.md
Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.
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.
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.
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).
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).
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.