Clean Room
hashgraph-online/awesome-codex-plugins
A skill your agent uses for authorized clean-room, reverse-engineering, source-to-implementation, compatibility rewrite, or migration tasks.
Get an independent decision from a fresh agent that receives a neutral brief and none of the current conversation.
No licenceAuto-check passed
Install Clean Room
$ npx skills add backnotprop/bro --skill clean-room -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install backnotprop/bro clean-room --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/backnotprop/bro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/clean-room .claude/skills/clean-room && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "clean-room" agent skill from https://github.com/backnotprop/bro/tree/main/skills/clean-room into .claude/skills/clean-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clean-room", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/backnotprop/bro/tree/main/skills/clean-roomType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add backnotprop/bro --skill clean-room -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install backnotprop/bro clean-room --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/backnotprop/bro.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/clean-room .agents/skills/clean-room && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "clean-room" agent skill from https://github.com/backnotprop/bro/tree/main/skills/clean-room into .agents/skills/clean-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clean-room", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add backnotprop/bro --skill clean-room -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install backnotprop/bro clean-room --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/backnotprop/bro.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/clean-room .cursor/skills/clean-room && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "clean-room" agent skill from https://github.com/backnotprop/bro/tree/main/skills/clean-room into .cursor/skills/clean-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clean-room", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/backnotprop/bro.git --path skills/clean-room--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add backnotprop/bro --skill clean-room -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install backnotprop/bro clean-room --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/backnotprop/bro.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/clean-room .gemini/skills/clean-room && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "clean-room" agent skill from https://github.com/backnotprop/bro/tree/main/skills/clean-room into .gemini/skills/clean-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clean-room", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install backnotprop/bro clean-roomInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add backnotprop/bro --skill clean-room -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/backnotprop/bro.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/clean-room .github/skills/clean-room && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "clean-room" agent skill from https://github.com/backnotprop/bro/tree/main/skills/clean-room into .github/skills/clean-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clean-room", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add backnotprop/bro --skill clean-room -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install backnotprop/bro clean-room --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/backnotprop/bro.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/clean-room .opencode/skills/clean-room && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "clean-room" agent skill from https://github.com/backnotprop/bro/tree/main/skills/clean-room into .opencode/skills/clean-room/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clean-room", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
clean-room- GitHub stars
- 124
- Token cost
- ~562 tokens
- SKILL.md length
- 309 words
- Files
- 2
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- None found
At a glance
Get an independent decision from a fresh agent that receives a neutral brief and none of the current conversation.
- Works in 5 steps: Frame one decision per run. Separate… → Start a new agent, task, thread, pane,… → Give the agent only the context needed… → …
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Clean Room is an agent skill from backnotprop/bro. Get an independent decision from a fresh agent that receives a neutral brief and none of the current conversation.
Its SKILL.md is about 560 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
Example prompts
- “/clean-room”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Frame one decision per run. Separate “should we” from “how should we.”
- Start a new agent, task, thread, pane, or session with no inherited conversation.
- Give the agent only the context needed to make the decision.
- Tell the agent to think independently, challenge any premise(s), consider other choices, and search for evidence against its conclusion.
- Return the response unchanged, even when it contradicts you or the user.
What it can do on your machine
Read from SKILL.md and the folder at commit 523ed36. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Clean Room loads about 562 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 309 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 309 words (~562 tokens).
“Launch a smart, independent agent to give us an unbiased third-party decision analysis.”
- name
- clean-room
- disable-model-invocation
- true
Files
SKILL.md and 1 other file in skills/clean-room of backnotprop/bro.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 523ed36
Compare with similar skills
Clean Room next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Clean Room this skillbacknotprop/bro | 124 | — | ~562 | Automated safety check: Pass | None | |
| Clean Roomhashgraph-online/awesome-codex-plugins | 1.2k | — | ~9.7k | Automated safety check: Pass | Apache-2.0 | |
| Clean Room Loophashgraph-online/awesome-codex-plugins | 1.2k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Content Freshness Signalsthedaviddias/Front-End-Checklist | 74k | — | ~741 | Automated safety check: Pass | MIT | |
| Payments Receivedsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Android Clean Architectureaffaan-m/ECC | 275k | 4 repos | ~2.2k | Automated safety check: Pass | MIT |
Similar skills
Clean Room Loop
hashgraph-online/awesome-codex-plugins
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.
Content Freshness Signals
thedaviddias/Front-End-Checklist
Audits article pages for freshness signals, covering the Last-Modified header, Article JSON-LD dateModified and a visible last-updated date, and fixes mismatches.
Payments Received
sickn33/agentic-awesome-skills
Payments received log: reference, client and invoice, amount and currency, payment date and method, withholding tax, bank account, received-by and receipt-sent status.
Android Clean Architecture
affaan-m/ECC
Applies Clean Architecture to Android and Kotlin Multiplatform projects: module layout, dependency rules, UseCases, Repositories and data layer patterns.
Research Decision Room
nexu-io/open-design
Turn messy user research notes, interviews, support tickets, surveys, and product context into an evidence-backed decision room: a single HTML artifact with an evidence ledger, theme map, confidence…
More from backnotprop/bro
Ladder
backnotprop/bro
Render one lane of work as a vertical progress ladder in the terminal, done on top and todo below, read top to bottom.
Status
backnotprop/bro
Render the state of the work in flight as an ASCII status board in the terminal, instead of a status paragraph.
Facts
backnotprop/bro
Give a capable engineer a terse, jargon-free briefing on the critical facts and implications of an effort before it is built or after it is completed.
Questions about Clean Room
What does Clean Room do?
Get an independent decision from a fresh agent that receives a neutral brief and none of the current conversation. Clean Room is an agent skill from backnotprop/bro. Get an independent decision from a fresh agent that receives a neutral brief and none of the current conversation.
How do I install Clean Room in Claude Code?
Run `npx skills add backnotprop/bro --skill clean-room -a claude-code`. Or copy the skill folder (skills/clean-room in backnotprop/bro) into .claude/skills/clean-room in your project. Claude Code loads it when a task matches its description.
How do I install Clean Room in Codex?
Run `npx skills add backnotprop/bro --skill clean-room -a codex`. Or copy the skill folder (skills/clean-room in backnotprop/bro) into .agents/skills/clean-room in your project. Codex loads it when a task matches its description.
Can I use Clean Room in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add backnotprop/bro --skill clean-room -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clean-room, .gemini/skills/clean-room, .github/skills/clean-room and .opencode/skills/clean-room in your project.
What does Clean Room need to run?
SKILL.md names no scripts, command-line tools or credentials: Clean Room is instructions for the agent only.
Does Clean Room access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Clean Room safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Clean Room use?
No licence was found for Clean Room or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Clean Room use?
About 562 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Clean Room?
Skills that share tags, products or a category with Clean Room: Clean Room (hashgraph-online/awesome-codex-plugins, 1.2k stars), Clean Room Loop (hashgraph-online/awesome-codex-plugins, 1.2k stars), Content Freshness Signals (thedaviddias/Front-End-Checklist, 74k stars) and Payments Received (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Clean Room?
backnotprop (a GitHub user) maintains it in backnotprop/bro, which has 124 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 24, 2026.
Source: backnotprop/bro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.