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/programmeranthony/expert-coding-harness/code-review-expertnpx skills add ProgrammerAnthony/Expert-Coding-Harness --skill code-review-expertgit clone --depth 1 https://github.com/ProgrammerAnthony/Expert-Coding-HarnessWhat 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 | $0.00079 | $0.01852 |
| Opus 5 | $0.00039 | $0.00926 |
| Sonnet 5 | $0.00016 | $0.00370 |
| Haiku 4.5 | $0.00008 | $0.00185 |
Grade A, and why
code-review-expert 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
代码审查专家
铁律：默认只输出审查报告，不实现任何修改。未经用户明确确认，不得编写或修改任何代码。
Inputs / Outputs / Gates / Handoffs（统一契约）
- Inputs（最小输入）：审查范围（默认：当前
git diff；或用户指定 commit/目录）；运行/测试命令（如有）；风险偏好（例如“安全优先/交付优先”）。 - Outputs（产物形态）：结构化审查报告（结构参考
references/review-report-template.md）。 - Gates（继续前必须满足）：
- 默认只输出报告；用户明确选择“修复”选项前禁止修改代码（保持与本文件 HARD-GATE 一致）。
- 所有问题必须给证据（文件/行号/调用路径）；不确定要明确标注。
- 通用门控清单可复制使用：
references/quality-gates-checklist.md。
- Handoffs（推荐下游）：
writing-plans（实施计划编写）：先写可执行修复计划subagent-driven-development（子代理驱动开发）：按计划逐任务执行
严重度分级
| 级别 | 名称 | 说明 | 处置 |
|---|---|---|---|
| P0 | 致命 | 安全漏洞、数据丢失风险、逻辑错误 | 必须阻止合并 |
| P1 | 严重 | 重大 SOLID 违反、性能回退、业务逻辑缺陷 | 合并前应修复 |
| P2 | 中等 | 代码异味、可维护性问题、轻微 SOLID 违反 | 本 PR 修复或创建后续 Issue |
| P3 | 建议 | 风格、命名、优化建议 | 可选改进 |
工作流
第一步：预检与上下文收集
执行以下命令建立审查范围：
git status -sb
git diff --stat
git diff
边界情况处理：
- 无变更：告知用户，询问是否审查暂存区或指定提交范围
- 大型 diff（>500行）：先按文件汇总，再按模块/功能区域分批审查
- 混合关注点：按功能特性分组，而非按文件顺序
若需要，用 rg 查找相关模块、用法和接口契约，识别入口点、权限边界和关键路径（认证、数据写入、网络调用）。
第二步：SOLID 与架构审查
加载 references/solid-checklist.md 进行系统检查。
重点关注：
- SRP：类/函数是否承担多个职责
- OCP：是否通过修改而非扩展来增加功能
- LSP：子类是否破坏父类契约
- ISP：接口是否过于臃肿
- DIP：是否直接依赖具体实现而非抽象
提出重构建议时，必须说明为何能改善内聚性/耦合度，并给出最小化、安全的拆分方案。非简单重构时，提出渐进式计划而非大规模重写。
第三步：可删除代码与迭代计划
加载 references/refactor-plan.md。
识别：无用代码、冗余逻辑、功能开关保护的死代码。 分类为：立即安全删除 vs 延后处理（附计划与检查节点）。
第四步：安全与可靠性扫描
加载 references/security-checklist.md。
覆盖：
- 注入：SQL 注入、命令注入、LDAP 注入、模板注入
- 认证与授权：Token 校验缺失、越权访问、会话固定
- 文件操作：路径穿越、任意文件读写、上传校验不足
- SSRF：不受限的外部 URL 请求
- 加密：弱算法、硬编码密钥、不安全随机数
- 敏感信息：日志泄露、错误信息暴露、配置文件明文
- 竞态条件与反序列化：并发漏洞、不可信数据反序列化
第五步：代码质量扫描
加载 references/quality-checklist.md。
覆盖：错误处理完备性、性能热点、边界条件、可测试性。
第六步：输出报告
输出格式固定如下：
## 代码审查报告
### 总览
[变更范围概述，受影响的核心模块与影响面评估]
### 发现问题
#### P0 致命问题
- **[文件:行号]** 问题描述
- 原因：[为什么这是问题]
- 修复建议：[具体如何修复，可含代码示例]
#### P1 严重问题
[同上格式]
#### P2 中等问题
[同上格式]
#### P3 建议
[同上格式]
### 可删除/重构计划
[来自 refactor-plan 的识别结果]
### 安全摘要
[安全扫描结论，无问题则明确说明已覆盖的检查项]
### 亮点
[代码中做得好的部分，平衡批评]
What ships with it
7 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.
- 2d ago First seen · 166 lines · 79 tokens per session scan A 7acccaa36824
code-review-expert is a skill published in the GitHub repository ProgrammerAnthony/Expert-Coding-Harness (235 stars, last pushed 3mo ago), licensed MIT. It adds 79 tokens to every session and 1,852 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…