Borrowing it
Nothing to install: this file belongs to fitlab-ai/agent-infra. 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/fitlab-ai/agent-infra/main/.agents/skills/review-pr/SKILL.mdgit clone --depth 1 https://github.com/fitlab-ai/agent-infraWrote 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/fitlab-ai/agent-infra/review-pr)<a href="https://agentmods.dev/skills/fitlab-ai/agent-infra/review-pr"><img src="https://agentmods.dev/badge/skills/fitlab-ai/agent-infra/review-pr/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/fitlab-ai/agent-infra/review-pr"><img src="https://agentmods.dev/badge/skills/fitlab-ai/agent-infra/review-pr.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 | $0.00058 | $0.03246 |
| Opus 5 | $0.00029 | $0.01623 |
| Sonnet 5 | $0.00012 | $0.00649 |
| Haiku 4.5 | $0.00006 | $0.00325 |
Grade A, and why
review-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 4d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
审查 PR
根据目标 PR 的生命周期证据完整度与变更风险，选择 verify（轻量复核）、audit（证据审计）或 reconstruct（重建式审查），并把可执行的检视结论作为正式 PR Review 发布到目标 PR，同时保留可追溯的审查过程证据（pr-review.md / pr-review-r{N}.md）。
行为边界 / 关键规则
持久化报告证据
生成 PR 审查报告时，先读取 .agents/rules/evidence-reporting.md。正常审查记录命令、范围、结构化结果、实际结论和未覆盖部分；正式 Review、finding、阻塞或争议的身份字段和决定性证据必须精确保留。
- 严格遵循方案中固化的证据分级主决策流：宿主解析 → 证据分类 → 新鲜度/对齐 → 风险分级 → 模式选择
pr-review*是独立 artifact family：不接入 analysis/plan/code 阶段依赖链，不修改current_step- PR 上只发布正式 PR Review（head SHA、结论、finding、receipt、Issue artifact 链接），不发第二份完整过程原文到 PR 普通评论
- 完整过程原文与
task.md的可逆镜像只在关联 Issue 上同步；restore-task保持 Issue-only 契约 - 生成会同步到 Issue 的 artifact Markdown 前，先读取
.agents/rules/sync-content-generation.md并遵循其中的生成端约束；Issue 同步保持透明，不解析或改写正文 - 不得为外部 PR 倒填或伪造已发生的
analysis/plan/code生命周期历史 - head SHA 唯一记录于
pr-review*与正式 PR Review；head 漂移必须进入新轮次，不得沿用旧结论 - 审查深度由证据完整度和变更风险决定，不由提交者身份决定
- 执行本技能后，你必须立即更新 task.md（经
task-activitytyped intent） - 绝不自动执行
git add或git commit - 一次性检视路径（无任务/Issue）走
.agents/workspace/reviews/{pr-number}/，标记recoverable: false，不承担可恢复承诺
常见违规借口与反驳
| 借口 | 反驳 |
|---|---|
| 「代码 diff 直接看就行了，不需要重建上下文」 | 仅看 diff 会遗漏需求边界、架构选择与迁移策略；reconstruct 必须先产出最低充分重建记录。 |
| 「PR 没有关联任务，直接写个报告发出去」 | 默认阻塞并要求先关联 Issue/task；只有显式「仅一次性检视」才走不可恢复降级路径。 |
| 「把完整重建过程也发到 PR 普通评论，方便贡献者看」 | 过程原文只同步到 Issue artifact 评论；PR 只保留正式 Review，避免重复远端副本与恢复源混淆。 |
| 「审查完了顺手提交一下」 | 本技能绝不执行 git add/git commit；提交是用户显式发起的独立步骤。 |
第 0 步：状态核对（执行前硬约束）
在加载本技能与相关规则后、做任何任务状态判断或用户可见结论之前，必须先执行状态核对：
agent-infra-internal task-snapshot {task-id} --format text
任务锚定路径在开始前记录当前任务目录与既有 pr-review* 轮次；一次性路径（无任务）记录 PR 编号与目标目录。将命令、PR/head、审查范围、关键结果和未覆盖部分写入本轮产物 pr-review-rN.md 的 ## 状态核对 段；正常成功不粘贴完整目录清单或 task.md 尾部，身份不一致、失败、阻塞或争议时保留决定性原文行。
执行步骤
1. 解析入参与宿主解析
解析目标 PR 编号 {pr-number}（--pr <number>，或 PR URL，或省略时按当前分支反查）。执行：
agent-infra-internal platform-pr-review inspect --pr {pr-number} [--cwd <path>]
agent-infra-internal pr-review-grade resolve-host --pr {pr-number} [--cwd <path>]
What ships with it
4 files 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.
- 4d ago Changed · +4 lines d44cfb7d3944
- 7d ago Changed · +1 lines 3a475db63996
- 11d ago First seen · 187 lines · 58 tokens per session scan A 863a07eb6ca2
review-pr is a skill published in the GitHub repository fitlab-ai/agent-infra (84 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 3,246 once invoked, about $0.0003 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
agentplane-task-closure-recovery
Use when Agentplane task completion, direct finish, branchpr integration, hosted-close, close-tail PRs, PR metadata, dirty task artifacts, or remote branch divergence need diagnosis or recovery.
argot-setup
Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…
detect-task
Internal skill for commands. Detect the active task (any tracker adapter) from the task-state file / git branch name. Do not trigger on user conversation - only when commands need task detection.
dos-verify-done-claims
Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.
loop-bb-pr
A command that prepares a repeating check for a Bitbucket pull request. A pull request is a request to review and merge code changes into a project.
take-task
A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.