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 Zhangs-11/zs-skills --skill peer-pr-reviewgit clone --depth 1 https://github.com/Zhangs-11/zs-skillsWrote 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/zhangs-11/zs-skills/peer-pr-review)<a href="https://agentmods.dev/skills/zhangs-11/zs-skills/peer-pr-review"><img src="https://agentmods.dev/badge/skills/zhangs-11/zs-skills/peer-pr-review/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/zhangs-11/zs-skills/peer-pr-review"><img src="https://agentmods.dev/badge/skills/zhangs-11/zs-skills/peer-pr-review.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 | $0.00050 | $0.09130 |
| Opus 5 | $0.00025 | $0.04565 |
| Sonnet 5 | $0.00010 | $0.01826 |
| Haiku 4.5 | $0.00005 | $0.00913 |
Grade A, and why
peer-pr-review 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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
代码改动第一性审查
目标不是替改动者证明方案正确,也不是为了显得严格而强行找问题。先把自己放在“需求交给我实现”的位置,独立形成一份开发方案,再让这份方案和改动者方案互相补漏、互相证伪。无论审查同事还是自己的代码,都要在有限时间内回答七件事:这块功能负责什么、实际出了什么问题、根因是什么、如果由我开发会怎样解决、改动者怎样解决、两套方案谁遗漏了什么、最终代码是否合理。
默认把读者视为第一次接触该项目的新手。报告主体只保留会影响理解、提交、合并决定或后续验证方式的信息;不要用一串术语和方法名代替解释。具体 Case 走读不设机械字数上限,以读者能沿真实输入、判断、状态变化和下游结果完整听懂为准,但不要重复粘贴同一份图、表和代码。
输入与边界
最低输入是一个可定位的审查对象,例如:
- CodeUp PR 链接;
- 当前仓库的 staged、unstaged 和 untracked 改动;
- 指定 worktree 路径或本地分支;
- 明确的 commit、patch 或比较范围。
需求背景通常应提供,但若当前对话、关联工作项、提交说明或代码能可靠恢复,就先自行整理;无法恢复时仍可做实现质量审查,但要明确“需求符合性未验证”。可选输入包括 OA 需求/缺陷 ID、project ID、Chat ID、环境、复现步骤、日志、改动者判断的根因和修复方案。
缺少可选输入时继续做能完成的静态审查,不把可自行检查的问题反问用户。只有审查对象无法访问、仓库或 worktree 无法定位、比较基线存在多个合理选择,或某个缺失选择会实质改变审查范围时才请求补充。
本 Skill 默认只读:
- 不修改代码、配置、数据库或文档;
- 不在 CodeUp 上评论、通过、关闭或合并 PR;
- 不 commit、push 或部署;
- 数据库只允许 SELECT;日志和配置只读取与当前假设有关的最小范围;
- 不在报告中回显 Token、Cookie、凭据、完整 Prompt 或未脱敏业务数据。
事实获取顺序
按成本从低到高取证,证据足够支撑结论就停止,不为低风险改动制造不成比例的调查。
1. 固定审查对象
先识别审查模式并在报告顶部写明“审查对象、基线、终点和包含范围”:
- CodeUp PR:解析仓库、源分支、目标分支、当前 patch set 和 commit。优先通过已登录页面、只读 OpenAPI 或对应 Git 远端锁定不可变 diff;先只记录范围和需求入口,把 patch hunk、改动者方案、讨论结论和测试结论留到独立方案冻结后再读。
- 当前未提交改动:默认审查
HEAD → 当前工作区。分别读取git diff --cached、git diff和git ls-files --others --exclude-standard;相关 untracked 文件必须读取,不能因普通git diff看不到就漏审。生成物、二进制或明确无关文件可以排除,但要在范围中说明。 - worktree 或本地分支:先用
git worktree list、git status、当前分支、HEAD 和远端信息确认实际路径。默认以用户指定目标分支为基线;未指定时只在仓库默认分支明确时使用其最新远端引用,并以 merge-base 为起点,审查merge-base → HEAD,再叠加该 worktree 的 staged、unstaged 和相关 untracked 改动。基线不唯一时不要擅自选择。 - commit 或 patch:按用户明确给出的不可变范围审查,并记录两端 commit 或 patch 来源。
若 PR 与本地改动同时存在,默认把 PR 作为主审查对象;检查本地分支是否还有未进入 PR 的提交或工作区改动,并单独标为“PR 外本地改动”,不要混入 PR 结论。用户明确要求审查发布前全部内容时,再合并两部分范围。
涉及远端基线或 PR 时,先检查 git status、分支和 worktree,再 git fetch,使用最新远端引用判断;只审查当前工作区相对 HEAD 的未提交内容时不必为了形式强制 fetch。全程不得切换分支、改 index、stash、commit 或清理文件。
记录审查开始时的 HEAD、状态和 diff 范围;交付前重新检查。若用户或其他会话在审查中改变了 HEAD、index 或工作区,重新读取受影响 diff,或者明确报告审查基于哪个快照。无法取得真实 diff 时,不根据标题或描述假装完成代码审查。锁定 diff 不等于提前研究改法;同事 Review 和自审都应尽量避免用目标版本的实现反推“自己本来会怎样设计”。
What ships with it
9 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 · -107 lines · -104 tokens per session 14fd4b34ca75
- 7d ago Changed · +33 lines ece37709f037
- 11d ago First seen · 485 lines · 154 tokens per session scan A c4bf913b49f7
peer-pr-review is a skill published in the GitHub repository Zhangs-11/zs-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 50 tokens to every session and 9,130 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 2026-08-31.
Other skills, from other repositories
code-review-zh
A Git-based code review workflow that compares changes from a chosen commit, branch, tag, or merge point. It checks both whether the code follows the repository's written standards and whether it implements the requested specification.
address-github-comments
Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…