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 DongLiStudio/personal-agent-foundation --skill yunxiao-mr-reviewgit clone --depth 1 https://github.com/DongLiStudio/personal-agent-foundationWrote 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/donglistudio/personal-agent-foundation/yunxiao-mr-review)<a href="https://agentmods.dev/skills/donglistudio/personal-agent-foundation/yunxiao-mr-review"><img src="https://agentmods.dev/badge/skills/donglistudio/personal-agent-foundation/yunxiao-mr-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/donglistudio/personal-agent-foundation/yunxiao-mr-review"><img src="https://agentmods.dev/badge/skills/donglistudio/personal-agent-foundation/yunxiao-mr-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 | $0.00136 | $0.02191 |
| Opus 5.5 | $0.00054 | $0.00876 |
| Sonnet 5.5 | $0.00027 | $0.00438 |
| Haiku 4.5 | $0.00014 | $0.00219 |
Grade A, and why
yunxiao-mr-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 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
云效 MR 审查
使用本 Skill 完成跨项目一致的云效 Codeup 合并请求审查闭环。阿里云 CLI、云效插件、组织身份、PAT 生命周期和多身份路由由全局 aliyun-profile 管理;项目 Skill 只提供身份、组织、仓库和业务边界覆盖,不复制通用审查流程。
固定边界
- 先读取目标项目与目标软件仓库的
AGENTS.md、README.md、STATUS.md及当前 Git 状态;项目实时规则优先。 - 从项目规则与
{{AGENT_ROOT}}\GLOBAL\ALIYUN_PROFILES.md解析唯一逻辑 Profile、组织和仓库路由。缺失、冲突或无法核验时停止,不使用全局默认、残留环境变量或其他项目身份回退。 - 项目覆盖层可以固定或收窄身份、仓库与授权边界,但不得省略本 Skill 的证据门禁,也不得在没有用户明确指令时扩大写操作范围。
- PAT 仅通过安全凭据通道进入当前进程环境,不出现在参数、日志、评论或报告中。
- 用户明确要求使用本 Skill 或项目覆盖层审查 MR 时,该请求同时授权三类受控写入:对高可信问题发布精确行内评论;解决经最新代码与讨论证据确认已经修复、失效,或被用户明确接受/暂缓的现有评论;在证据完整、风险相称验证通过且没有问题时提交“通过”评审。
- 请求修改、关闭、合并、重跑流水线、删除分支和部署仍分别需要用户明确授权。
- 有任何仍然有效或无法验证的高可信代码问题、未解决讨论、冲突、必需检查未通过或足以影响结论的证据缺口时,不得提交“通过”评审。已经修复、失效或被用户明确接受/暂缓的评论不得长期保留为形式性阻断项,应先解决并回读,再判断是否通过。
- 不把 MR 已创建、分支已推送、评审已通过或流水线部分通过等同于已合并或已部署。
首审与复审契约
- 首次审查必须在同一轮覆盖当时 MR 的完整差异、全部讨论、冲突、必需检查和风险相称验证,集中提出所有已经确认的高可信问题。不得故意保留问题、只抽查局部,或把同一 patchset 拆成多轮逐步挑错。
- 首审结束时记录审查基线:目标分支 SHA、已审源 SHA/patchset、文件范围、测试与检查结果、已发布评论。优先从云效版本历史、评论和评审记录回读基线;不能可靠确定基线时,明确证据缺口,不假装已经完成增量复审。
- 复审先比较“上次已审源 SHA/patchset → 当前源 SHA/patchset”。审查范围仅包含:原评论对应修复、期间新增或改动的代码,以及验证这些变化所必需的直接影响链。不得重新扫描未变化且已经审过的旧代码,并以新发现的普通问题继续阻断开发。
- 只有两类情况允许复审新增阻断评论:修复或新增差异本身存在问题;修复或新增差异直接触发了与旧代码的可证实交互问题。评论必须说明属于“修复引入”还是“新增代码引入”,并锚定本轮变化的真实致因行。
- 对未变化旧代码的漏审问题,只有达到严重安全漏洞、数据损坏、不可逆业务错误等必须立即阻断的级别,才允许作为例外补充;必须明确承认这是首审遗漏、说明为何例外阻断,不得包装成普通复审发现。其余旧代码问题进入后续独立治理,不阻断当前复审。
- 如果当前版本仅包含针对既有评论的修复,没有其他新增差异;所有评论已被代码、测试和讨论证据确认解决;冲突、必需检查和风险相称验证均通过;且 SHA 未变化,则必须自动解决适用评论并立即提交“通过”评审,不得等待再次确认或开启新一轮全量审查。
审查流程
- 读取 审查契约,解析逻辑 Profile、组织、仓库和 MR 编号;MR 链接、项目路由与本地 remote 不一致时停止。
- 使用
$aliyun-profile验证目标云效身份,再通过当前 CLI/插件的--help发现精确命令,不依赖历史命令形态。 - 回读 MR 标题、描述、作者、源/目标分支、提交列表、完整文件差异、讨论、评审状态、冲突状态和自动化检查。识别这是首次审查还是复审:首次审查锁定当前完整差异;复审回读上次已审 SHA/patchset,并生成到当前版本的增量差异。逐条把未解决评论映射到最新 patchset 与当前业务决定,分类为“仍有效”“已修复”“已失效”“用户明确接受/暂缓”或“无法验证”;记录获取不到的证据,不能假设为空或通过。
- 在不污染用户工作树的前提下审查代码。优先使用现有干净仓库;需要 checkout 时使用临时 worktree/临时目录,并保留用户未提交改动。
- 运行与改动风险相称的测试、静态检查或构建。因环境缺失未运行时明确区分“未验证”和“失败”。
- 对每个高可信问题,在当前 patchset 中选择真正导致问题的最小变更行,发布一条独立行内评论;评论包含严重度、问题机制、触发条件、用户影响和修复建议。首次审查集中发布全部已确认问题;复审只评论修复或新增差异引入的问题,并标明来源类别。不得重复已解决问题、把多个无关问题堆进一条评论,也不得为了满足行内形式而锚定无关代码。
- 发布评论或解决评论前锁定组织、仓库、MR、最新 patchset 和源 SHA。对“已修复”“已失效”或“用户明确接受/暂缓”的评论直接标记已解决;对“仍有效”或“无法验证”的评论保持未解决。每次写入后按评论 ID 回读内容、文件、行号、patchset 和 resolved 状态。任一写入期间源 SHA 变化,停止剩余动作并从最新版本重新审查。
- 评论处理完成后再次回读全部讨论。首次审查仅当完整差异和全部门禁均已覆盖时通过;复审仅当既有评论、从审查基线到当前版本的增量差异及其直接影响已覆盖时通过。风险相称验证通过、没有仍然有效或无法验证的高可信问题、没有未解决讨论或其他阻断项,且写前复核确认 SHA 未变化时,必须直接提交“通过”评审;随后回读评审人、评审状态、时间和最新 SHA。没有问题但证据不足时保持未通过并向用户说明缺口。
- 最终结论注明审查模式及基线,例如“首审:目标 SHA / 源 SHA”或“复审:上次已审 SHA → 当前 SHA”;先列仍有效的行内发现,按严重度排序并给出文件/行号,同时汇总本轮自动解决的评论及依据。没有发现时明确说明已解决适用评论并通过评审,单列仍不影响本次代码结论的环境边界。未经另行授权不执行合并、关闭、重跑、删分支或部署。
What ships with it
2 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.
- 1mo ago First seen · 51 lines · 136 tokens per session scan A 04dca7ef78c7
yunxiao-mr-review is a skill published in the GitHub repository DongLiStudio/personal-agent-foundation (16 stars, last pushed yesterday), licensed Apache-2.0. It adds 136 tokens to every session and 2,191 once invoked, about $0.0005 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 2026-09-14.
Other skills, from other repositories
code-review-expert
Expert-level code review focusing on quality, security, performance, and maintainability. Use this skill for conducting thorough code reviews, identifying issues, and providing constructive feedback.
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"…
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…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…