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.
npx agentmods add instructions/whit3rabbit/clean-room-skill/agents-mdgit clone --depth 1 https://github.com/whit3rabbit/clean-room-skillWrote 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/whit3rabbit/clean-room-skill/agents-md)<a href="https://agentmods.dev/instructions/whit3rabbit/clean-room-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/whit3rabbit/clean-room-skill/agents-md.svg" alt="Measured on agentmods" 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 | $0.04731 | $0.04731 |
| Opus 5 | $0.02365 | $0.02365 |
| Sonnet 5 | $0.00946 | $0.00946 |
| Haiku 4.5 | $0.00473 | $0.00473 |
Grade A, and why
clean-room-skill 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 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.
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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Room Repo Guide
Repo Quick Facts
- npm package:
clean-room-skill. - CLI entrypoint:
bin/install.js. - Executable inner-loop runner:
clean-room-skill run. - Full local verifier:
bin/verify.sh. - Node requirement:
>=22. - CI runs Node 24 with Python 3.12 on macOS.
- This repo installs clean-room skills, role agents, hooks, schemas, examples, and optional verification templates for multiple agent runtimes.
- Installer runtime flags: Codex, Claude Code, Antigravity, Gemini CLI, OpenCode, Kilo, Cursor, GitHub Copilot, Windsurf, Augment, Trae, Qwen Code, Hermes Agent, and CodeBuddy.
- Hook registration is verified for Codex, Claude Code, and OpenCode. Other runtime layouts are best-effort installs unless code and tests prove otherwise.
- Dynamic workflows (
workflows/*.js->.claude/workflows/) are Claude Code only and local-scope only, installed alongside their/clean-room:<name>front-door command wrapper. No other runtime ships aWorkflow()engine; global installs stay hooks-only, so a triggerless global workflow is never shipped. - The workflow creates clean behavioral spec packages and clean implementation outputs. It does not generate replacement code directly from source.
- Full docs: README.md, docs/ARCHITECTURE.md, and docs/REFERENCE.md.
Repo Map
bin/: installer CLI and local verification script.lib/: installer helpers, TUI, hook config helpers, runtime layout logic, preflight helpers, doctor checks, and inner-loop runner.skills/: skill entrypoints, schemas, references, source and visual index scripts, and example spec packages.agents/: Claude role-agent prompts.examples/codex/: Codex role-agent templates.hooks/: Python guardrail hooks.templates/docker/: optional Agent 3 verification images and example verification command policies.tests/: Node tests, JSON Schema fixtures, schema parity fixtures, and validation helper..github/workflows/: CI and npm publish workflows..agents/plugins/marketplace.json: Codex repo marketplace..agents/skills/synrepo/: repo-bundled synrepo skill metadata..codex/: repo-local Codex config and hook config used for this workspace..claude-plugin/marketplace.json: Claude Code marketplace.plugin.json,.codex-plugin/plugin.json, and.claude-plugin/plugin.json: runtime-specific plugin manifests.
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 · 219 lines · 4,731 tokens per session scan A ca3e43636fd7
clean-room-skill AGENTS.md is an instructions file published in the GitHub repository whit3rabbit/clean-room-skill (10 stars, last pushed 2d ago), licensed MIT. It adds 4,731 tokens to every session, about $0.0237 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
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).
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.
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 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.