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 agentmods add skills/ryanzhao1011/workframe/code-reviewnpx skills add ryanzhao1011/workframe --skill code-reviewgit clone --depth 1 https://github.com/ryanzhao1011/workframeWhat 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 | $0.00040 | $0.02385 |
| Opus 5 | $0.00020 | $0.01192 |
| Sonnet 5 | $0.00008 | $0.00477 |
| Haiku 4.5 | $0.00004 | $0.00238 |
Grade A, and why
code-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 2d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
代码审查技能
产物去向
审查结论默认只在响应中呈现。用户要求存档时按 skill: document-norms §1 落
projects/modules/<basic>/<sub>/requirements/<req_slug>/<sub_req_slug>/reviews/；
发现的缺陷若需跟踪，走 projects/issues/ + board task 草稿（不直接写 board）。
适用场景
- @dev 交付代码变更后
- @qa 做回归验证的前置检查
- 安全/质量疑点时的深度审查
四步流程
第 1 步：变更范围识别
读取代码变更（diff 或指定文件），识别：
| 维度 | 内容 |
|---|---|
| 改动文件 | 新增/修改/删除的文件清单 |
| 改动范围 | 每个文件的具体改动行数和函数 |
| 影响模块 | 直接调用改动代码的其他模块 |
| 依赖变化 | 新增/移除的依赖关系 |
第 2 步：多维度审查
2.1 需求符合度（Requirement Conformance）
前提：先拿到规范资产（PRD 正文 / AC / spec / 词表 / 接口约定），逐条比对，不能只看 AC —— AC 是抽样，正文才是全量口径。
| 审查点 | 检查内容 |
|---|---|
| 规则落地 | 规范正文写明的每条规则，代码是否实现且口径一致 |
| 缺漏 | 规范写了、代码没做（含只做了一半、静默降级、开关/埋点等非功能要求） |
| 超纲 | 代码做了、规范没写（自行发挥的逻辑，需回溯确认） |
| 规范空白 | 规范本身没定，代码"忠实实现了不完整的规则" —— 不算实现错误，退回需求侧补口径 |
| 已符合项 | 明确列出实现正确的部分，供修其他问题时防误伤 |
「规范空白」与「缺漏」必须分开报：前者要 PM/需求方先拍板，研发改了也是白改；后者研发直接修。
2.2 正确性（Correctness）
| 审查点 | 检查内容 |
|---|---|
| 逻辑正确 | 代码实现是否符合需求/AC |
| 边界处理 | 空值、零值、极值、负数等边界条件 |
| 错误处理 | 异常捕获、错误返回、失败恢复 |
| 并发安全 | 竞态条件、死锁、共享状态 |
| 类型安全 | 类型断言、null 检查 |
2.3 安全性（Security）
| 审查点 | 检查内容 |
|---|---|
| 注入风险 | SQL 注入、命令注入、XSS |
| 权限校验 | 未登录访问、越权访问 |
| 敏感信息 | 密码/密钥泄露、日志打印敏感数据 |
| 输入校验 | 未校验的用户输入、文件上传 |
| 依赖安全 | 已知漏洞的依赖库 |
2.4 可维护性（Maintainability）
| 审查点 | 检查内容 |
|---|---|
| 命名清晰 | 变量、函数、类名能自解释 |
| 结构清晰 | 单一职责、合理抽象、避免过深嵌套 |
| 注释充分 | 复杂逻辑有解释，公开接口有文档 |
| 代码复用 | 避免重复代码，合理提取公共函数 |
| 测试覆盖 | 关键逻辑有测试 |
2.5 性能（Performance）
| 审查点 | 检查内容 |
|---|---|
| 算法复杂度 | O(n²) 或更差的循环 |
| 数据库查询 | N+1 查询、缺失索引、全表扫描 |
| 网络请求 | 串行请求应并行、缺失缓存 |
| 内存使用 | 大对象加载、内存泄漏 |
| IO 操作 | 同步阻塞 IO、文件句柄泄漏 |
第 3 步：Finding 分级与归因
每个 Finding 打两个正交标签：风险级别（多急）+ 依据来源（凭什么）。
风险级别：
| 级别 | 含义 | 处理要求 |
|---|---|---|
| Critical | 必须修复 | 阻塞合并/发布，P0 问题 |
| Warning | 建议修复 | 下次迭代或同一 PR 修复 |
| Info | 建议改进 | 记录待办，不阻塞 |
依据来源（决定谁来处理、能不能拒绝）：
| 来源 | 含义 | 处理方 |
|---|---|---|
| 违反规范 | 规范 / spec / PRD 明文写了，实现没做到 | 实现方直接修，无需再讨论口径 |
| 规范空白 | 规范本身没定，实现只是「忠实实现了不完整的规则」 | 需求方先补口径，实现方此时改了也可能白改 |
| 审查者判断 | 无规范依据，属审查者的经验或偏好（架构选型、分层、工程实践） | 建议性质，实现方可拒绝；单独分区，不与前两类混排 |
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.
- 2d ago First seen · 185 lines · 40 tokens per session scan A c5cef397ceca
code-review is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 15d ago), licensed MIT. It adds 40 tokens to every session and 2,385 once invoked, about $0.0002 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
check-understanding
Phase quiz for AI Engineering from Scratch. Trigger with "quiz me", "test phase", "check my understanding", "do I know phase 3", or /check-understanding .
find-your-level
Interactive quiz that maps your AI/ML knowledge to a starting point in the 260-lesson, 20-phase AI Engineering from Scratch curriculum. Trigger phrases: "where should I start", "find my level", "what do I know", "which phase", "assess my knowledge", "placement test", "skip ahead".
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.