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 commands/awesome-embedded-learning-studio/cfdesktop/reviewgit clone --depth 1 https://github.com/Awesome-Embedded-Learning-Studio/CFDesktopWrote 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/commands/awesome-embedded-learning-studio/cfdesktop/review)<a href="https://agentmods.dev/commands/awesome-embedded-learning-studio/cfdesktop/review"><img src="https://agentmods.dev/badge/commands/awesome-embedded-learning-studio/cfdesktop/review.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01108 |
| Opus 5 | $0.00000 | $0.00554 |
| Sonnet 5 | $0.00000 | $0.00222 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review — 代码审查
对指定模块进行结构化代码审查,输出中文评审报告。
触发方式
/review <模块/文件路径>— 审查指定模块或文件- 用户说"审查 XXX 子模块"
审查流程
Step 1: 确认审查范围
- 根据用户指定,搜索相关源文件 (
.h,.hpp,.cpp) - 列出完整文件清单(含行数)
- 等待用户确认后再继续
- 如果范围过大(>20 个文件),建议拆分为子模块逐个审查
Step 2: 读取全部代码
- 读取范围内所有
.h,.hpp,.cpp文件 - 读取对应
CMakeLists.txt了解构建上下文 - 查找并读取对应测试文件(
test/目录下)
Step 3: 五维分析
3.1 性能关注点
- 不必要的拷贝(缺少
std::move,大类型按值传递) - 多余的
QString/QByteArray转换 - 过多的堆分配(优先栈分配、
std::array、small buffer optimization) - 虚调度开销(可用静态分派替代的场景)
- Signal/Slot 连接类型(auto vs direct vs queued 的合理性)
- 循环中的重复计算
- 不必要的
Q_OBJECT宏(非 QObject 子类使用)
3.2 模块间依赖检查
参考 .claude/commands/architecture.md 的层级规则:
- base 不得 include ui/desktop
- ui 不得 include desktop
- CMake
target_link_libraries依赖方向正确
3.3 类级耦合分析
| 检查项 | 阈值 | 说明 |
|---|---|---|
| 继承深度 | > 3 | 标记过深的继承链 |
| friend 使用 | 任何 | 需要合理理由,否则标记 |
| Signal 数量 | > 10 | 过多 Signal 可能是设计异味 |
| 类行数 | > 500 | 考虑拆分为多个类 |
| 公共方法数 | > 30 | 检查是否违反接口隔离原则 |
| 依赖类数量 | > 8 | 高耦合信号 |
3.4 C++23 现代性
- 缺少
[[nodiscard]](const getter、工厂函数、返回expected<T>的函数) - 可
constexpr化但未标注的函数和变量 - 裸指针(可用智能指针或引用替代的场景)
- 缺少
override/final(重写虚方法时) - 缺少
noexcept(不抛异常的移动构造/赋值) - 可用
std::span替代指针+长度参数 - 可用
using enum简化枚举使用 - 可用结构化绑定简化返回值处理
3.5 文档完整性
对照 document/DOXYGEN_REQUEST.md 规范:
- 未文档化的公共 API
@param方向标记缺失@return与实际返回类型不匹配- 风格不一致(
/** */和///混用)
Step 4: 输出报告 (中文)
# 代码审查报告: <module_name>
## 审查范围
| 文件 | 类型 | 行数 |
|------|------|------|
| ... | .h/.cpp | N |
模块层次位置: base/ui/desktop — Layer N
## 性能关注点
1. **[严重/中等/建议]** 文件:行号 — 问题描述
## 依赖违规
(层级违规详情,或 "无违规")
## 类级耦合分析
- 继承深度: ...
- friend 使用: ...
- Signal/Slot 合理性: ...
- 类职责评估: ...
- 上帝类检测: ...
## 现代 C++ 改进建议
1. **[类别]** 文件:行号 — 具体建议
## 文档完整性
- 缺失文档的公共 API: ...
- Doxygen 标签问题: ...
## 综合评估
- 健康度评分: X/10
- 主要风险: ...
- 优先改进项:
1. ...
2. ...
3. ...
## 改进指南
(可对接 /optimize 的具体改进项列表)
规则
- 始终读取实际代码,不做假设
- 引用具体文件路径和行号
- 区分严重问题、中等问题和建议
- 报告中的严重问题必须附带修复方案
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 First seen · 124 lines · 0 tokens per session scan A acf0e4c56075
review is a command published in the GitHub repository Awesome-Embedded-Learning-Studio/CFDesktop (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,108 tokens. 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 commands, from other repositories
gui-anything
Build a complete GUI harness for any software application.
validate
Validate a GUI harness against HARNESS.md standards and best practices.
refine
Expand and improve an existing GUI harness with additional coverage.
test
Run tests for a GUI harness and update TEST.md with results.
list
List all GUI-Anything harnesses in the current repository.
gen-gtests
Generate unit Googletests for a diff from trunk.