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 Snowflake-Labs/cocoplus --skill audit-verifygit clone --depth 1 https://github.com/Snowflake-Labs/cocoplusWrote 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/snowflake-labs/cocoplus/audit-verify)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/audit-verify"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/audit-verify/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/snowflake-labs/cocoplus/audit-verify"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/audit-verify.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 | $0.00018 | $0.00342 |
| Opus 5.5 | $0.00007 | $0.00137 |
| Sonnet 5.5 | $0.00004 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
audit-verify 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 1mo 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.
What it actually says
Your objective is to implement $audit verify [--full].
Before proceeding, verify that .cocoplus/ exists. If not, output: "CocoPlus not initialized in this directory. Run $pod init to begin." Then stop.
Contract
Read .cocoplus/audit/, lifecycle audit records, and contract proof artifacts. Validate append-only ordering, required fields, timestamp presence, actor/source provenance, and hash-chain continuity when hashes are present.
With --full, also re-check CocoContract proof artifacts and report whether archived falsifiability checks remain reproducible from committed inputs.
Output:
- Verified artifact count
- Broken or missing links
- Contract proof status
- Highest-severity finding
- Recommended next command
Exit Criteria
- Missing audit artifacts produce an explicit "no audit artifacts found" result.
- Hash or ordering failures are reported as deterministic audit failures.
- Contract proof drift is distinguished from missing proof.
- The command never repairs audit history silently.
Anti-Rationalization
| Shortcut / Temptation | Why It Fails |
|---|---|
| Treat the skill as complete because the file exists | Skill contracts must describe observable behavior and verification, not just command names. |
| Skip artifact and safety checks for a small command | Small commands still mutate state or guide execution; preserve the same gates. |
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.
- 1mo ago Changed · -1 lines d558d0e72088
- 2mo ago First seen · 43 lines · 18 tokens per session scan A 50a4796066b6
audit-verify is a skill published in the GitHub repository Snowflake-Labs/cocoplus (729 stars, last pushed 6d ago), licensed MIT. It adds 18 tokens to every session and 342 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
audit-verify compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| audit-verifySnowflake-Labs/cocoplus | Skill | 729 | 6d ago | MIT | A | 18 | Claude Code, Codex |
| legal-strategymagnus919/agent-skills | Skill | 176 | yesterday | MIT | A | 50 | Claude Code, Codex |
| privacy-engineeringmagnus919/agent-skills | Skill | 176 | yesterday | MIT | A | 98 | Claude Code, Codex |
| ai-governancemagnus919/agent-skills | Skill | 176 | yesterday | MIT | A | 161 | Claude Code, Codex |
| design-compliance-architecturepjt222/agent-almanac | Skill | 45 | today | MIT | A | 100 | Claude Code |
| design-training-programpjt222/agent-almanac | Skill | 45 | today | MIT | A | 91 | Claude Code |
| assess-ip-landscapepjt222/agent-almanac | Skill | 45 | today | MIT | A | 93 | Claude Code |