Borrowing it
Nothing to install: this file belongs to alexjbarnes/cockpit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alexjbarnes/cockpit/main/.claude/skills/review-issue/SKILL.mdgit clone --depth 1 https://github.com/alexjbarnes/cockpitWrote 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/alexjbarnes/cockpit/review-issue)<a href="https://agentmods.dev/skills/alexjbarnes/cockpit/review-issue"><img src="https://agentmods.dev/badge/skills/alexjbarnes/cockpit/review-issue/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/alexjbarnes/cockpit/review-issue"><img src="https://agentmods.dev/badge/skills/alexjbarnes/cockpit/review-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.00664 |
| Opus 5 | $0.00041 | $0.00332 |
| Sonnet 5 | $0.00016 | $0.00133 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
review-issue 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 10d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review a cockpit issue plan (on-demand)
A manual tool for getting a fresh adversarial pass on a plan that already sits in an issue's description. The autonomous pipeline does not use this: the refine-issue skill self-reviews inline during refinement and posts those findings itself. Reach for this skill when a human wants an extra review of an existing plan, for example after editing it by hand or before approving it at the Plan Review gate.
Input
The issue key (e.g. CK-12) from the invocation. If none was given, ask which issue.
Steps
1. Read the issue
mcp__cockpit-config__get_issuefor the key. One call returns the title, full description (the plan), status, and every comment — read prior review comments and any human feedback.- Extract the original brief from the plan's
## Requestblock at the top of the description. The reviewer needs it to check scope drift.
2. Determine the repo
The reviewer verifies file paths and code snippets against the actual codebase. list_projects, match the issue's projectId, and use that project's repoPath if set. Otherwise use the current working directory (today's behaviour). If neither is a code repo, the reviewer will note that code accuracy was not verified.
3. Dispatch the reviewer
Dispatch the plan-reviewer agent (subagent_type: "plan-reviewer") with three labelled blocks:
**Plan draft:**
<full issue description>
**Original brief:** <verbatim Request block from the description>
**Repo:** <resolved repo path from step 2>
The agent returns Critical/High/Medium/Low findings and a PASS/FAIL verdict. It does not touch the issue.
4. Post the findings as a comment
Post the agent's full review (the four buckets and verdict) as a comment on the issue via mcp__cockpit-config__add_issue_comment. Post it regardless of verdict.
5. Report and offer to transition
Report the verdict to the user. Do not change the issue status automatically. If the user wants to act on it, offer the obvious transition:
- FAIL (Critical/High): offer to set
Refine Readyto send it back for another refinement pass. - PASS: offer to set
Implementation Readyif they are approving at the Plan Review gate.
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.
- 10d ago First seen · 50 lines · 81 tokens per session scan A f3248351eb8e
review-issue is a skill published in the GitHub repository alexjbarnes/cockpit (14 stars, last pushed 4d ago), licensed Apache-2.0. It adds 81 tokens to every session and 664 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
ln-51-opportunity-evaluator
Evaluates new product opportunities using demand, channels, competition, and economics. Not for committed-backlog or implementation planning.
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
tech-debt
Track, categorize, and prioritize technical debt across the codebase. Scans for debt indicators, maintains a debt register, and recommends repayment scheduling.