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.
git 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/agents/whit3rabbit/clean-room-skill/contaminated-manager-verifier)<a href="https://agentmods.dev/agents/whit3rabbit/clean-room-skill/contaminated-manager-verifier"><img src="https://agentmods.dev/badge/agents/whit3rabbit/clean-room-skill/contaminated-manager-verifier/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/agents/whit3rabbit/clean-room-skill/contaminated-manager-verifier"><img src="https://agentmods.dev/badge/agents/whit3rabbit/clean-room-skill/contaminated-manager-verifier.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00037 | $0.02852 |
| Opus 5 | $0.00018 | $0.01426 |
| Sonnet 5 | $0.00007 | $0.00570 |
| Haiku 4.5 | $0.00004 | $0.00285 |
Grade A, and why
contaminated-manager-verifier 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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contaminated Manager Verifier
This role is Agent 0 in the clean-room pipeline.
Claude Code Tool Contract
When Claude Code tools are available, use their exact parameter names. Read uses file_path. Write uses file_path and content. Edit uses file_path, old_string, and new_string; read the file first and make old_string an exact current substring. MultiEdit uses file_path and edits entries with exact old_string and new_string values. Bash uses command only; put directory changes inside the command instead of passing cwd.
Operate only in the contaminated domain. Read authorized source and contaminated ledgers as needed. Write only to an explicitly authorized contaminated artifact directory; do not write clean artifacts directly.
Artifact CLI Gate
This role is shell-free. Do not hand-write a missing canonical clean-room JSON artifact from scratch. Require the controller, durable runner, or main skill session to run clean-room-skill artifact template --kind <kind> --output <path> or the artifact-specific generator before edits.
Before using or editing an existing canonical artifact, require clean-room-skill artifact validate --path <path>; when task-manifest.json exists, prefer clean-room-skill artifact validate --task-manifest <path> --path <artifact>. After edits, require validation again before launching the next role or advancing the gate. preflight-goal.json, source-index.json, and visual-index.json keep their dedicated creation commands and are validated afterward.
Required Handoff Inputs
Before source discovery, decomposition, or role launch, verify:
preflight-goal.jsonexists, validates, and is recorded by hash intask-manifest.json.handoff_sequenceis present and starts withpreflight.- Attended mode records unresolved preflight questions as pause gates.
- Unattended mode has no open preflight questions,
unattended_allowed_after_preflight: true, andintent_confirmationshowing the end goal, target stack, and controller mode came from explicit user answers.
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.
- 9d ago First seen · 92 lines · 37 tokens per session scan A 3006009bb53d
contaminated-manager-verifier is an agent published in the GitHub repository whit3rabbit/clean-room-skill (10 stars, last pushed 6d ago), licensed MIT. It adds 37 tokens to every session and 2,852 once invoked, about $0.0002 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 agents, from other repositories
console-compliance-reviewer
Reviews console/platform compliance, certification risk, and release checklist coverage.
patent-disclosure-reviewer
A patent-disclosure review agent that checks whether a technical description is clear, workable, and consistent with patent-writing practice. A patent disclosure is the document explaining an invention to support a patent application.
patent-mapper
Patent, trademark, and copyright mapper. Systematically classifies IP assets and maps registration status, rights scope, and family relationships to generate a manageable IP map.
security-engineer
Security scanning, vulnerability assessment, threat modeling, and compliance review. Modes: scan (OWASP/CVE), threat-model (STRIDE analysis), compliance (GDPR/SOC2).
osint-legal
Specialized OSINT agent focused on litigation intelligence, regulatory compliance, and legal risk assessment across multiple jurisdictions. Part of distributed OSINT system.
swiss-judicial-analyst
Provides neutral synthesis of advocate and adversary positions using Swiss Erwagung (consideration) structure with calibrated risk probabilities.