Borrowing it
Nothing to install: this file belongs to gianverdum/ai-dev-skillset. 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/gianverdum/ai-dev-skillset/main/.agents/skills/quality-revisao-aderencia/SKILL.mdgit clone --depth 1 https://github.com/gianverdum/ai-dev-skillsetWrote 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/gianverdum/ai-dev-skillset/quality-revisao-aderencia)<a href="https://agentmods.dev/skills/gianverdum/ai-dev-skillset/quality-revisao-aderencia"><img src="https://agentmods.dev/badge/skills/gianverdum/ai-dev-skillset/quality-revisao-aderencia/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/gianverdum/ai-dev-skillset/quality-revisao-aderencia"><img src="https://agentmods.dev/badge/skills/gianverdum/ai-dev-skillset/quality-revisao-aderencia.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 | $0.00249 | $0.07707 |
| Opus 5.5 | $0.00100 | $0.03083 |
| Sonnet 5.5 | $0.00050 | $0.01541 |
| Haiku 4.5 | $0.00025 | $0.00771 |
Grade A, and why
quality-revisao-aderencia 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 1mo 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Revisao de Aderencia a Skills e Rules
Use esta skill como ultima etapa antes de declarar uma tarefa concluida e, em mudancas grandes, tambem ao terminar cada etapa significativa (modulo novo, camada nova, refator estrutural). O objetivo e fechar o ciclo TDD/quality e impedir desvios silenciosos.
Quando rodar
Regra absoluta de gatilho — antes de qualquer frase de conclusao:
Antes de escrever no resumo final QUALQUER uma destas frases (ou equivalente em outro idioma), VOCE PRECISA ter rodado a checklist objetiva desta skill:
- "concluido" / "completo" / "completa" / "pronto" / "feito" / "terminei" / "finalizado" / "encerrado"
- "the refactoring is complete" / "refactor is done" / "implementation complete" / "all done"
- "refatoracao concluida" / "feature pronta" / "task pronta" / "tudo certo"
- Qualquer declaracao categorica de fim de tarefa (mesmo implicita: "rodei tudo, passou", "all checks pass", etc.)
Se a checklist objetiva (secao "Pontos a verificar") tem 2 ou mais itens vermelhos, voce esta PROIBIDO de usar qualquer dessas frases. Use o formato WIP transparente em vez (secao "Formato no reporte final QUANDO refatoracao esta em WIP").
Declarar conclusao com itens vermelhos sem WIP = DESVIO grave de honestidade, anula o credito do trabalho feito.
Outros gatilhos:
- Ao terminar uma implementacao, fix ou refator, antes do resumo final ao usuario.
- Ao concluir um modulo novo, antes de seguir para o proximo.
- Ao concluir uma camada (domain/application/interface) novamente, antes de seguir.
- Sempre que uma extensao criar modulo novo: aplique a checklist completa SEPARADAMENTE ao modulo novo (suite e2e propria, README proprio, cobertura propria, literal unions, etc.), mesmo que o modulo existente ja tenha cobertura completa.
- Quando o usuario pedir explicitamente revisao de aderencia.
Sintoma da skill nao rodada (auto-deteccao):
Se voce esta prestes a escrever uma frase de conclusao e NAO consegue listar mentalmente o status (❌/✅) dos 9 itens da checklist objetiva nem dos anti-padroes desta secao, voce nao rodou a skill. Pare, leia esta skill, rode item-a-item, depois decida entre "concluido" ou "WIP transparente".
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.
- 1mo ago Changed · +249 tokens per session 9659632c7520
- 2mo ago First seen · 290 lines · 0 tokens per session scan A 9706eba3c5b9
quality-revisao-aderencia is a skill published in the GitHub repository gianverdum/ai-dev-skillset (6 stars, last pushed 1mo ago), licensed MIT. It adds 249 tokens to every session and 7,707 once invoked, about $0.0010 per session on Opus 5.5. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…