clean-room

v0.8.0

Spec-first clean-room workflow for authorized source analysis without replacement code.

Codex9 Skills

By whit3rabbitLicense: MIT1.1k GitHub starsUpdated 2 days ago

Directory evidence

Runtimes: Codex
Parsed components: 9 skill or MCP entries
Source updated: Sep 22, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install clean-room for Codex

Installs for the current user

codex plugin marketplace add hashgraph-online/awesome-codex-plugins
codex plugin marketplace upgrade awesome-codex-plugins
codex plugin add clean-room@awesome-codex-plugins

Paste and run these commands in a terminal with Codex. They add and refresh the awesome-codex-plugins catalog, then install this plugin.

Compatibility: the page URL and API slug “clean-room” remain stable.

Codex: clean-room@agent-plugin-marketplace → clean-room@awesome-codex-plugins

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/hashgraph-online/awesome-codex-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/whit3rabbit/clean-room-skill/.

Plugin files

plugins/whit3rabbit/clean-room-skill/

├── .codex-plugin/plugin.json
├── skills/attended/SKILL.md
├── skills/clean-room/SKILL.md
├── skills/clean-room-loop/SKILL.md
├── skills/init/SKILL.md
├── skills/preflight/SKILL.md
├── skills/refocus/SKILL.md
├── skills/resume-cr/SKILL.md
├── skills/start-over/SKILL.md
└── skills/unattended/SKILL.md

Included Skills9

attendedskills/attended/SKILL.md

Starts the Clean Room startup wizard in attended controller mode for authorized source-to-implementation work with human review pauses at clean-room gates.

clean-roomskills/clean-room/SKILL.md

Use for authorized clean-room, reverse-engineering, source-to-implementation, compatibility rewrite, or migration tasks. Produces clean behavioral specs, implementation plans, clean code changes, verification reports, QC reports, open questions, and test plans without moving source expression into the clean implementation.

clean-room-loopskills/clean-room-loop/SKILL.md

Front door for running the clean-room unattended loop as a Claude Code dynamic WORKFLOW using in-session subagents, so it never spends `claude -p` API tokens. Use when the user wants to run a clean-room / reverse-engineering / source-to-clean-implementation task hands-off but without paying per-token for `clean-room-skill run`, or says "clean-room as a workflow", "unattended clean-room without API cost", "/clean-room-loop". Runs a short discussion (authorization, end goal, target stack, policies, source roots, output roots, iterations) then launches the `clean-room-loop` workflow with the answers. NOT the enforced OS-level wall - that is `clean-room-skill run --agent-runtime claude`.

initskills/init/SKILL.md

Records Clean Room initialization preferences, separated artifact locations, model policy, schema profile, and clean-safe rule defaults before a clean-room run starts or resumes.

preflightskills/preflight/SKILL.md

Creates or reviews the required Clean Room preflight goal contract before source discovery, decomposition, attended execution, or unattended execution.

refocusskills/refocus/SKILL.md

Audits an existing Clean Room run and steers it back to missed gates without expanding declared scope.

resume-crskills/resume-cr/SKILL.md

Continues an existing Clean Room run from durable artifacts without relying on prior chat history.

start-overskills/start-over/SKILL.md

Archives or quarantines current Clean Room artifacts and restarts from the scope gate with a fresh task id.

unattendedskills/unattended/SKILL.md

Starts the Clean Room startup wizard in bounded unattended controller mode for authorized source-to-implementation work with finite loop limits and safety stops.

Plugin manifests1

plugins/whit3rabbit/clean-room-skill/.codex-plugin/plugin.json

{
  "name": "clean-room",
  "version": "0.8.0",
  "description": "Spec-first clean-room workflow for authorized source analysis without replacement code.",
  "author": {
    "name": "whit3rabbit"
  },
  "homepage": "https://github.com/whit3rabbit/clean-room-skill",
  "repository": "https://github.com/whit3rabbit/clean-room-skill",
  "license": "MIT",
  "keywords": [
    "clean-room",
    "specification",
    "migration",
    "reverse-engineering",
    "compliance"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Clean Room",
    "shortDescription": "Produce clean-room behavioral specs",
    "longDescription": "Guides spec-first clean-room workflows that separate contaminated source analysis from clean behavioral specifications, skeleton manifests, QC reports, and test plans. Writes clean specification artifacts only. Does not generate replacement implementation code.",
    "developerName": "whit3rabbit",
    "category": "Development",
    "capabilities": [
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "Create a clean-room spec package for this authorized source scope.",
      "Review these clean-room spec artifacts for leakage, coverage gaps, and schema conformance.",
      "Organize these behavioral specs into a clean skeleton manifest."
    ],
    "brandColor": "#0F766E",
    "composerIcon": "./assets/icon.svg"
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[clean-room on Agent Plugins Marketplace](https://pluginsmp.com/plugins/clean-room)