A pull-request or merge-request checklist for checking whether a software change follows the team's documented development process. It checks specifications, acceptance criteria, tests, architecture decisions, documentation, and completion rules.

Reviewing GitHub or GitLab changes against an approved specification, linking each acceptance criterion to a passing test, checking unresolved deviations, and posting the result on the change.

It catches missing process evidence before code is merged. This separates process compliance from a code review that looks for bugs and quality problems.

revisar-pr — Skill for Claude Code and Codex by igoruehara: A pull-request or merge-request checklist for checking whether a…

Install

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.

agentmods

npx agentmods add skills/igoruehara/spec-driven/revisar-pr

Any agent

npx skills add igoruehara/spec-driven --skill revisar-pr

Clone the repo

git clone --depth 1 https://github.com/igoruehara/spec-driven

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/igoruehara/spec-driven/revisar-pr.svg)](https://agentmods.dev/skills/igoruehara/spec-driven/revisar-pr)

Your own site

<a href="https://agentmods.dev/skills/igoruehara/spec-driven/revisar-pr"><img src="https://agentmods.dev/badge/skills/igoruehara/spec-driven/revisar-pr.svg" alt="Measured on agentmods" height="20"></a>

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 605 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00107	$0.00605
Opus 5	$0.00053	$0.00302
Sonnet 5	$0.00021	$0.00121
Haiku 4.5	$0.00011	$0.00060

Measured 6d ago against content hash e5eab0efaafe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

revisar-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 6d 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.

template/.claude/skills/revisar-pr/SKILL.md · 33 lines

What it actually says

Skill: Revisar PR/MR (gate de conformidade SDD)

Checa o processo, não os bugs. Para bugs/qualidade, use o /code-review do harness — esta skill verifica se a mudança respeita a esteira SDD antes do merge. As duas se complementam.

Identifique o alvo

O PR/MR (número/branch) e a feature specs/NNNN-<nome>/ correspondente.
Se GitHub/GitLab MCP estiver conectado (conta validada — ver /integracoes), leia o diff e os metadados pelo MCP. Se não houver MCP do git host, ofereça rodar /integracoes para conectar (habilita ler metadados e postar o veredito no PR/MR); se recusar, siga com o diff local (git diff <base>...HEAD).

Checklist de conformidade SDD

Spec existe e está aprovada para o escopo da mudança (tier correto para o tamanho/risco).
Rastreabilidade: todo AC-N tocado tem teste; o diff inclui os testes que cobrem os ACs.
Gates verdes: os comandos de docs/engineering/TESTING.md passam (ou a CI está verde).
Sem SPEC_DEVIATION aberto sem resolução.
ADRs registrados para decisões difíceis de reverter introduzidas no PR.
Docs vivas: glossário/context-map atualizados se a linguagem/fronteira mudou.
Escopo: nada do "Fora de escopo" da spec foi implementado; mudança coesa (um propósito).
STATE.md atualizado, se o próximo passo mudou.

Veredito

Resultado claro: aprovar ou mudanças requeridas (lista do que falta, com link p/ spec/AC).
Se GitHub/GitLab MCP estiver conectado e validado, ofereça postar como comentário no PR/MR (outward-facing — confirme antes; reconfirme conta/workspace, ver /integracoes).
Sugira rodar /code-review (harness) para a camada de bugs/qualidade.

Changes

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.

6d ago First seen · 33 lines · 0 tokens per session scan A e5eab0efaafe

Subscribe to this mod's changes

revisar-pr is a skill published in the GitHub repository igoruehara/spec-driven (213 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 605 once invoked, about $0.0005 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.

Code review

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens