clean-room

clean-room is a skill for Claude Code, Codex from AlexZio00/sovereign-skills. It costs 0 tokens per session (3,762 once invoked), scanned A, original, MIT.

A clean-room skill for separating safe work from safety-adjacent material, such as privacy, security, scraping, stealth, or licensing concerns. It uses an isolated fresh context so the worker handling the safe task does not see the original sensitive request.

In plain words
What is it for?
Use it when you need to strip risky parts from a mixed request, perform only the safe portion, or record what was deliberately left out.
Why use it?
It prevents sensitive instructions from affecting the safe portion of a task and keeps removed scope explicit. The workflow is intended for requests where only part of the work needs restriction.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions subagents.

Part of the clean-room plugin — 1 skill shipped together

Good fit Use it when you need to strip risky parts from a mixed request, perform only the safe portion, or record what was deliberately left out.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexzio00/sovereign-skills/clean-room
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.

Any agent
npx skills add AlexZio00/sovereign-skills --skill clean-room
Clone the repo
git clone --depth 1 https://github.com/AlexZio00/sovereign-skills

Made for: Claude Code, Codex.

Or install clean-room, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for clean-room

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexzio00/sovereign-skills/clean-room/github.svg)](https://agentmods.dev/skills/alexzio00/sovereign-skills/clean-room)
Your own site
<a href="https://agentmods.dev/skills/alexzio00/sovereign-skills/clean-room"><img src="https://agentmods.dev/badge/skills/alexzio00/sovereign-skills/clean-room/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.

agentmods 80×15 button for clean-room

Your own site · 80×15
<a href="https://agentmods.dev/skills/alexzio00/sovereign-skills/clean-room"><img src="https://agentmods.dev/badge/skills/alexzio00/sovereign-skills/clean-room.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,762 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Prompt Injection · line 1
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
  • medium Excessive Agency · line 54
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 5.1 $0.00000 $0.03762
Opus 5 $0.00000 $0.01881
Sonnet 5 $0.00000 $0.00752
Haiku 4.5 $0.00000 $0.00376

Measured 5d ago against content hash 8581517cc89e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

clean-room 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.

clean-room/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: clean-room description: "Use when a task mixes safety-adjacent material (stealth, scraping, privacy, IP, licensing, security) with genuinely safe work, or the moment you notice yourself about to hedge, dilute, silently drop, or brace for a refusal on part of a request. Triggers: 'strip the risky part out', 'just the safe part', 'carve this out', 'clean-room this'." tools: Read, Grep, Glob, Write, Agent user_invocable: true

Clean Room

Purpose

Dominant Variable: did the subagent that actually executes the work ever see the original safety-adjacent request? If it did, this skill has failed — isolation is everything. "Never saw it" applies not just at the prompt layer but to what the subagent is instructed not to go looking for too — there is no real filesystem access-control boundary between the main session and its subagent, only a shared filesystem plus an instruction not to consult certain paths. A subagent with shared Read/Grep access to your project files can read a mention of the risky request in a memory or log file just as easily as if it had been told directly; the instruction not to look is the only barrier, not a partition.

Discard if:

  • The whole request is obviously safe (no safety-adjacent element at all) — just handle it directly
  • The whole request is a clear bright-line refusal (nothing safe to carve out) — nothing to carve, just decline
  • The user has already narrowed the request to the safe part explicitly — no carving needed, proceed directly

Read the full file on GitHub · 96 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago Changed 8581517cc89e
  2. 12d ago First seen · 96 lines · 0 tokens per session scan A 7ee5f32e9187

Subscribe to this mod's changes

clean-room is a skill published in the GitHub repository AlexZio00/sovereign-skills (129 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,762 tokens. 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 2026-08-30.

Related

Other skills, from other repositories

nobrainer-review

Use when the owner says nb-review, deep-audit, deep-code-review, or deep-autoreview; explicitly requests an evidence-gated CLOSEOUT, adversarial BUGHUNT or RELEASEGATE; or needs final findings filtered to verified actionable defects. Use nobrainer-build for ordinary implementation and correction work.

nobrainer-tech/nobrainer-tech-skills · 67 tokens

sdd-tasks

Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.

Gentleman-Programming/gentle-ai · 25 tokens

review-work

Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.

code-yeongyu/oh-my-openagent · 63 tokens

ap-juror

Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.

Spielewoy/autoprompt-skill · 24 tokens

ijfw-cross-audit

Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'check with other AIs', 'cross-check this', 'get another perspective', /cross-audit.

FerroxLabs/ijfw · 67 tokens

doubt-driven-development

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…

jcarlosrodicio/opencode-agent-orchestration-kit · 67 tokens