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 review-clear-blockedgit 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-clear-blocked)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/review-clear-blocked"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/review-clear-blocked/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-clear-blocked"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/review-clear-blocked.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 | $0.00051 | $0.00718 |
| Opus 5 | $0.00026 | $0.00359 |
| Sonnet 5 | $0.00010 | $0.00144 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
review-clear-blocked 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 8d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your objective is to resolve a BLOCKED CocoReview finding.
Before proceeding, verify that .cocoplus/ exists. If not, output: "CocoPlus not initialized in this directory. Run $pod init to begin." Then stop.
Parse arguments: $review clear-blocked --id <finding-id> --rationale <text>. Both are required. If either is missing: output "Usage: $review clear-blocked --id --rationale " Then stop.
Steps
- Read
.cocoplus/lifecycle/review-state.json. If it does not exist or the named finding is not present: output "Finding [id] not found in review-state.json." Then stop. - Verify the finding's
severityisBLOCKED. If it is not: output "Finding [id] is not a BLOCKED finding (severity: [severity]). $review clear-blocked only resolves BLOCKED findings." Then stop. - If already
resolved: true: output "Finding [id] is already resolved." Then stop. - Record the rationale in the audit trail via the same append logic
the PostToolUse hookuses forlifecycle/audit.md(if CocoAudit is enabled): event typeblocked-finding-resolved, artifact the finding ID, developer input the verbatim rationale. - Update the finding in
review-state.json: setresolved: true,resolved_at: <ISO 8601 timestamp>,resolution_rationale: <text>. - Check whether any other
BLOCKINGor unresolvedBLOCKEDfinding remains inreview-state.json.- If none remain: output "Finding [id] resolved. No other BLOCKING or BLOCKED findings remain — $ship is unblocked."
- If others remain: output "Finding [id] resolved. [N] BLOCKING/BLOCKED finding(s) still require resolution before $ship: [list IDs]."
Exit Criteria
review-state.jsonis updated withresolved: true, a timestamp, and the verbatim rationale for the named finding- The rationale is recorded in the audit trail when CocoAudit is enabled
$shipproceeds only when zero unresolvedBLOCKINGorBLOCKEDfindings remain
Anti-Rationalization
| Temptation | Why Wrong |
|---|---|
| Accept an empty or placeholder rationale ("resolved", "fine") | The rationale is the audit record of a human decision — a vacuous rationale defeats the purpose of requiring one |
Resolve a blocking (not BLOCKED) finding through this command |
$review clear-blocked exists specifically for decisions outside the reviewer's authority — regular blocking findings are resolved by fixing the code, not by rationale |
| Skip the audit record when CocoAudit happens to be disabled | Still update review-state.json — the resolution must be tracked even without the compliance audit trail |
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.
- 8d ago First seen · 43 lines · 51 tokens per session scan A 7aca8486f396
review-clear-blocked is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 718 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
cross-review
Verify an implementer's diff with an INDEPENDENT, different-vendor sub-agent (diff plus contract only); turn blocking issues into fix-tasks and loop until clean.
factory-rereview
Re-review a pull request after a push — reconcile the previous review against the new commits, look for new defects the push introduced, then a fresh pass over the whole PR, and finish with a verdict on the PR.
understand-pr
Guided interactive PR review — understand the history and context before forming opinions.
performance-review
Performance-focused code review for identifying bottlenecks and optimization opportunities.
security-review
Security-focused code review checklist for identifying vulnerabilities.
programming-principles
Apply distilled coding principles from 14 classic software books to code review, refactoring, design, and implementation decisions. Do not use for language- or framework-specific tutorials, tool manuals, or tasks already governed by a project's established conventions.