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 agentmods add skills/joaonic/agentkit/review-open-prnpx skills add Joaonic/agentkit --skill review-open-prgit clone --depth 1 https://github.com/Joaonic/agentkitWrote 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/joaonic/agentkit/review-open-pr)<a href="https://agentmods.dev/skills/joaonic/agentkit/review-open-pr"><img src="https://agentmods.dev/badge/skills/joaonic/agentkit/review-open-pr.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.04850 |
| Opus 5 | $0.00021 | $0.02425 |
| Sonnet 5 | $0.00008 | $0.00970 |
| Haiku 4.5 | $0.00004 | $0.00485 |
Grade A, and why
review-open-pr 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 3d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-open-pr
Analisa um MR aberto de ponta a ponta: pipeline OK, ligação obrigatória a pelo menos uma issue (fechar ao merge quando aplicável), e confirmação de que o que a issue promete está implementado no código, validado com diff completo. Usa glab no projeto GitLab padrão; o agente cruza texto das issues com todo o diff.
Política: todo MR deve referenciar pelo menos uma issue no corpo (Closes #n, Fixes #n, Refs #n) coerente com o escopo. Se não houver issue vinculada de forma inequívoca, o resultado é bloqueante até corrigir (corpo do MR ou fluxo).
Kanban (GitLab): ao iniciar esta revisão, garantir que a(s) issue(s) ligada(s) ao MR têm label Code Review (e não In Progress como estágio único). Após merge bem-sucedido e CI verde: retirar Code Review e aplicar Testing ou Done conforme a política da equipa; usar os nomes exactos em .cursor/skills/implement-plan/SKILL.md (Labels Kanban).
Correções: qualquer mudança de código, testes ou docs após a análise deve ser feita na branch de origem do MR (source_branch), preferencialmente num git worktree dedicado. Proibido corrigir em main ou noutra feature branch que não atualize o mesmo MR.
Zero tolerância — warnings, stubs, TODOs
Warnings são bloqueantes
Todo warning é bloqueante e deve ser corrigido antes de aprovar:
- Compiler warnings (Java
-Xlint, TypeScriptstrict, etc.) - Lint warnings (ESLint, Checkstyle, SpotBugs, PMD, etc.)
- Deprecation warnings — usar a API actual, não a deprecated
- Test warnings — testes instáveis, assertions fracas,
@Disabledsem justificativa - Build warnings — dependency convergence, plugin warnings, resource filtering
Se o warning já existia antes do MR (pré-existente na target_branch), registar como finding de severidade Medium mas não bloquear o MR actual — o MR não pode introduzir warnings novos. Se o MR toca o ficheiro que já tinha o warning, deve corrigi-lo (boy-scout rule).
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.
- 3d ago First seen · 347 lines · 42 tokens per session scan A f62b0022c2f4
review-open-pr is a skill published in the GitHub repository Joaonic/agentkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 4,850 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…