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 sketch-validategit 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/sketch-validate)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/sketch-validate"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/sketch-validate/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/sketch-validate"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/sketch-validate.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 | $0.00035 | $0.00312 |
| Opus 5 | $0.00017 | $0.00156 |
| Sonnet 5 | $0.00007 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
sketch-validate 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.
This is a copy
94% identical to audit-ci — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Your objective is to perform this V2-native feature behavior using Coco-native capabilities: Read, Write, Edit, Bash when explicitly needed by the host, Snowflake tools when the feature requires data access, and subagents when the feature requires independent review.
Required Contract
- Preserve the artifact paths, schemas, and user-visible outputs documented by the owning feature skill.
- Do not call legacy scripts as the implementation path.
- Prefer deterministic file parsing and structured artifacts over free-form prose when producing machine-readable state.
- If an external side effect would occur, apply the same gate and confirmation semantics as the owning feature.
Exit Criteria
- The owning feature's documented artifact is produced or updated.
- The output schema remains compatible with existing readers.
- No registered runtime script invocation is required.
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.
- 5d ago First seen · 32 lines · 35 tokens per session scan A 86dabb617b78
sketch-validate is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 312 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to audit-ci, differing in 4 lines, and is treated as a copy.
Other skills, from other repositories
implement-universal
Harness-agnostic version of /implement. Drives a single workshop ticket through the SWE→Tester loop in ONE conversation, with the role prompts bundled as agents/software-engineer.md and agents/tester.md instead of being launched as subagents. Resolves the ticket from implementyourself/tasks/, creates an…
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
testing-e2e
End-to-end testing patterns with Playwright — page objects, AI agent testing, visual regression, accessibility testing with axe-core, and CI integration. Use when writing E2E tests, setting up Playwright, implementing visual regression, or testing accessibility.
bare-eval
Run isolated eval and grading calls using CC 2.1.81 --bare mode. Constructs claude -p --bare invocations for skill evaluation, trigger testing, and LLM grading without plugin/hook interference. Use when running eval pipelines, grading skill outputs, benchmarking prompt quality, or testing trigger accuracy in isolation.
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.
synthesize-verification-report
Aggregate all detected errors and gaps into the final verification report, apply strict accept/reject logic, and produce repair hints when rejected.