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 thaifurforo/ai-toolkit --skill harness-code-reviewgit clone --depth 1 https://github.com/thaifurforo/ai-toolkitWrote 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/thaifurforo/ai-toolkit/harness-code-review)<a href="https://agentmods.dev/skills/thaifurforo/ai-toolkit/harness-code-review"><img src="https://agentmods.dev/badge/skills/thaifurforo/ai-toolkit/harness-code-review.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 5.1 | $0.00071 | $0.01065 |
| Opus 5 | $0.00036 | $0.00532 |
| Sonnet 5 | $0.00014 | $0.00213 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
harness-code-review scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
6. **Evidências** — saída dos testes, screenshots, respostas do curl How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness: Code Review (Etapa 05)
Persona: Engenheiro sênior especialista em qualidade.
Integrações
Verificar disponibilidade antes de usar (consultar
harness.config.yaml). Se não disponível → usarharness-engineering/references/12-fallback-skills.md.
requesting-code-review(se disponível) — prepara a descrição do PR e dispara a revisão; fallback:12-fallback-skills.md § requesting-code-reviewreceiving-code-review(se disponível) — processa feedback e rastreia resolução; fallback:12-fallback-skills.md § receiving-code-reviewtlc-spec-driven(se disponível) — equivalente averify work
Execute os sensores computacionais primeiro. Se lint, type check ou testes estruturais ainda estiverem falhando, corrija-os antes de executar este review inferencial.
Escala de Severidade
| Símbolo | Nível | Ação |
|---|---|---|
| 🔴 | Blocker | Deve corrigir antes do merge |
| 🟠 | Major | Deve corrigir antes do merge |
| 🟡 | Minor | Corrigir ou documentar a decisão |
| 🟢 | Praise | Reconhecer o que foi bem feito (≥1 obrigatório) |
6 Dimensões de Review
- Corretude — todos os CAs atendidos? Comportamento correto nos edge cases?
- Segurança — input validation, secrets expostos, auth, SQL injection?
- Tratamento de erros — edge cases cobertos, mensagens informativas?
- Testabilidade — testes cobrem todos os CAs? Casos de falha testados?
- Manutenibilidade — legível, sem duplicação, segue padrões do projeto?
- Performance — N+1 queries, memory leaks, chamadas bloqueantes?
Copilot PR Review (se project_tracking.tool: github)
Quando um PR está aberto e a ferramenta configurada é GitHub, o GitHub Copilot pode postar comentários de revisão nas diff lines. Se aplicável, processá-los antes da Etapa 05 estar completa:
- Buscar comentários de revisão na ordem de preferência:
- gh CLI:
gh pr view <número> --commentsough api repos/{owner}/{repo}/pulls/{number}/comments - MCP:
github-mcp-server-pull_request_readcommethod: get_review_comments - API REST:
GET /repos/{owner}/{repo}/pulls/{number}/commentscomGITHUB_TOKEN
- gh CLI:
- Para cada comentário do Copilot: classificar severidade → corrigir Blockers/Majors → documentar decisões Minor
- Verificar threads resolvidos (
isResolved: true) - Iterar até não haver Blocker/Major aberto
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 81 lines · 71 tokens per session scan A 0db397615c2a
harness-code-review is a skill published in the GitHub repository thaifurforo/ai-toolkit (5 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 1,065 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…