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 reviewgit 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/review)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/review"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/review/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/review"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/review.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 | $0.00050 | $0.01251 |
| Opus 5 | $0.00025 | $0.00626 |
| Sonnet 5 | $0.00010 | $0.00250 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
review 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are executing the Review phase (5/6) of CocoBrew.
Before proceeding, verify that .cocoplus/ exists.
If not: output "CocoPlus not initialized in this directory. Run $pod init to begin." Then stop.
Read .cocoplus/lifecycle/meta.json. Verify phases_completed contains "test".
If not: output "The Test phase must be completed before review. Run $test first." Then stop.
Aggregate Findings
Collect from these sources:
1. Code Quality Findings
Look for files matching .cocoplus/quality-findings-*.md. Read all and extract critical and high severity findings.
2. CocoCupper Findings
Read .cocoplus/grove/cupper-findings.md. Extract the most recent 5 findings.
3. Spec Compliance Check
Read .cocoplus/lifecycle/spec.md (Success Criteria, Deliverables) and .cocoplus/lifecycle/test.md.
For each success criterion: was it tested? Did it pass?
For each deliverable: does the file/table/artifact exist?
4. Test Summary
Read .cocoplus/lifecycle/test.md. Extract pass/fail summary.
5. Decision Coverage Check
Extract key decisions from plan.md (and discuss.md if it exists): evaluation target, data source, accuracy threshold, model to use, warehouse assignment, production safety requirements.
For each extracted decision, scan implementation artifacts — SQL functions, evaluation configurations, flow.json stage definitions, prompt files — for evidence that the decision is honored in the implementation.
A decision is honored if the artifact reflects the stated value or approach. A decision is a Coverage Gap if it is present in plan/discuss but absent or contradicted in the implementation.
Coverage Gaps are severity-equivalent to must-fix. $ship is blocked until all Coverage Gaps are resolved or explicitly acknowledged with a documented rationale written into review.md.
Write Review Document
Write .cocoplus/lifecycle/review.md:
# Review Report
**Date:** [ISO 8601 timestamp]
**Phase:** Review (5/6)
**Phase ID:** review-YYYYMMDD-001
## Quality Findings
[Critical and high severity findings from Code Quality Advisor]
If none: "No critical quality findings."
## Intelligence Insights
[CocoCupper findings — top 5]
If none: "No CocoCupper analysis available."
## Spec Compliance
| Criterion | Tested | Result |
|-----------|--------|--------|
[Table of success criteria vs test results]
## Deliverable Checklist
| Deliverable | Present | Notes |
|-------------|---------|-------|
[Table of deliverables vs existence check]
## Test Summary
Passed: [N] / [Total]
## Decision Coverage
| Decision | Source | Honored | Notes |
|----------|--------|---------|-------|
[Table of plan/discuss decisions vs implementation evidence]
Coverage Gaps (if any): [list — each blocks $ship until resolved or acknowledged with rationale]
## Decision Points
[List any items requiring developer decision before shipping]
## Approval Status
PENDING DEVELOPER APPROVAL
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 · 131 lines · 50 tokens per session scan A f7a113328d8f
review is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 5d ago), licensed MIT. It adds 50 tokens to every session and 1,251 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
ork-verify
Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove, check readiness, run the relevant tests, or distinguish a claimed result from an observed one. Do not use to write missing tests or fix failures.
pn-best-of-n
Run 2–3 competing implementations of the same spec in isolated worktrees, eliminate failures via objective gates, then judge survivors with a separate premium-tier pass. Use for ambiguous algorithm/API/refactor choices with strong tests — not auth/security paths.
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
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…
mantis-plan
Formulates a targeted defensive security reviewing plan based on the active threat model and historical learnings. Use when starting a security review campaign to map the codebase boundaries and generate a roadmap (workspace/plan.json). Don't use for executing code reviews, writing test scripts, or patching code.
qa-review
QA review for code changes — test coverage analysis, edge case identification, test plan generation, regression detection, test health tracking over time.