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 skills add AlexZio00/sovereign-skills --skill clean-roomgit clone --depth 1 https://github.com/AlexZio00/sovereign-skillsWrote 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/skills/alexzio00/sovereign-skills/clean-room)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00000 | $0.03762 |
| Opus 5 | $0.00000 | $0.01881 |
| Sonnet 5 | $0.00000 | $0.00752 |
| Haiku 4.5 | $0.00000 | $0.00376 |
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.
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
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.
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 Changed 8581517cc89e
- 12d ago First seen · 96 lines · 0 tokens per session scan A 7ee5f32e9187
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.
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.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
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.
ap-juror
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
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.
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…