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 curtisgalloway/public-skills --skill cleanroom-implementergit clone --depth 1 https://github.com/curtisgalloway/public-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/curtisgalloway/public-skills/cleanroom-implementer)<a href="https://agentmods.dev/skills/curtisgalloway/public-skills/cleanroom-implementer"><img src="https://agentmods.dev/badge/skills/curtisgalloway/public-skills/cleanroom-implementer/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/curtisgalloway/public-skills/cleanroom-implementer"><img src="https://agentmods.dev/badge/skills/curtisgalloway/public-skills/cleanroom-implementer.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 | $0.00088 | $0.03592 |
| Opus 5 | $0.00044 | $0.01796 |
| Sonnet 5 | $0.00018 | $0.00718 |
| Haiku 4.5 | $0.00009 | $0.00359 |
Grade A, and why
cleanroom-implementer scanned grade A with 2 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 7d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.gemini/config/hooks.json` to cover every project). The event is **`PreToolUse`**, matcher Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`git clone`/`curl` to known targets; it cannot catch everything a shell can do) — the sandbox and The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
18 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.
- assets/agents-md-block.md 2.4 KB
- assets/antigravity-hooks.json 1.1 KB
- assets/antigravity-permissions.json 2.8 KB
- assets/cleanroom-policy.json 1.6 KB
- assets/driver-implementer.md 4.1 KB
- scripts/cleanroom_hook.py 13 KB runs code
- scripts/session_audit.py 18 KB runs code
- tests/fixtures/antigravity_artifacts/implementation-plan.md 1.2 KB
- tests/fixtures/antigravity_artifacts/walkthrough.md 689 B
- tests/fixtures/antigravity_clean_session.jsonl 1.5 KB
- tests/fixtures/antigravity_dirty_session.jsonl 1.2 KB
- tests/fixtures/clean_session.jsonl 961 B
- tests/fixtures/custom_policy_session.jsonl 305 B
- tests/fixtures/custom-policy.json 501 B
- tests/fixtures/dirty_session.jsonl 733 B
- tests/README.md 4.7 KB
- tests/test_cleanroom_hook.py 15 KB runs code
- tests/test_session_audit.py 7.5 KB runs code
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.
- 7d ago Changed 9249e940e614
- 10d ago First seen · 226 lines · 88 tokens per session scan A 494446c53394
cleanroom-implementer is a skill published in the GitHub repository curtisgalloway/public-skills (2 stars, last pushed yesterday), with no licence file. It adds 88 tokens to every session and 3,592 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
arch-review
Read-only architecture review of RTL vs uArch spec with area/timing/power tradeoffs. Use for post-RTL architecture sign-off or suspected spec mismatch.
kicad-pcb-review
Use this skill when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.
cdc-tool-profiles
Internal reference: cdc tool profiles (agent-loaded; do not invoke).
rtl-review
Audit RTL code for lint violations, synthesis hazards, coding-style compliance, and readability. Use when the user says "review this Verilog", "check my RTL", "lint this module", "is this code synthesizable", or shares an HDL file and asks for feedback before simulation or tape-in.
kicad-pcb-review
KiCad PCB review and manufacturing readiness agent skill for Cursor.
code-review-policy
Internal reference: code review policy (agent-loaded; do not invoke).