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 jiushiwon/wg-skills --skill frontend-code-doctorgit clone --depth 1 https://github.com/jiushiwon/wg-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/jiushiwon/wg-skills/frontend-code-doctor)<a href="https://agentmods.dev/skills/jiushiwon/wg-skills/frontend-code-doctor"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/frontend-code-doctor/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/jiushiwon/wg-skills/frontend-code-doctor"><img src="https://agentmods.dev/badge/skills/jiushiwon/wg-skills/frontend-code-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.01399 |
| Opus 5.5 | $0.00034 | $0.00560 |
| Sonnet 5.5 | $0.00017 | $0.00280 |
| Haiku 4.5 | $0.00009 | $0.00140 |
Grade A, and why
frontend-code-doctor 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 23d 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.
Frontend Code Doctor - uniapp + Vue3 代码审查
本技能用于审查 uniapp + Vue3 + TypeScript 前端项目，发现代码质量问题、性能问题和潜在 bug。
审查维度
本技能从以下 5 个维度进行审查，默认全部开启：
| 维度 | 优先级 | 检查内容 |
|---|---|---|
| Urgent | P0 | 必须修复的严重问题 |
| TypeScript | P1 | 类型安全、any 用法、类型推断 |
| uniapp 规范 | P1 | 条件编译、平台 API、安全区域 |
| Performance | P1 | 性能问题、内存泄漏 |
| Business | P2 | 业务逻辑、配置管理 |
| React | P1 | Hooks 规则、useEffect 依赖、自定义 hook |
| Security | P1 | XSS、CSRF、敏感信息、输入校验 |
| i18n | P2 | 硬编码中文、翻译 key、RTL 支持 |
| Accessibility | P1 | aria-*、键盘导航、焦点管理 |
开始审查
Step 1: 收集文件
使用 Glob 收集待审查的源文件：
# Vue 文件
Glob "**/*.vue"
# TypeScript 文件
Glob "**/*.ts"
排除以下目录：
node_modules/dist/unpackage/.git/
Step 2: 执行审查
按照以下规则进行检查，将发现的违规标记到对应位置。
Urgent 问题（P0，必须修复）
| 规则 ID | 问题描述 | 检查模式 |
|---|---|---|
| U1 | any 类型丢失类型提示 |
Grep : any |
| U2 | 业务码异常未 throw | 检查 request.ts 错误处理 |
| U3 | 内存泄漏（setTimeout 无清理） | Grep setTimeout.*50 递归模式 |
| U4 | 硬编码测试 URL | 检查 deeflow.ts 中的 URL |
| U5 | 图片下载失败无 fallback | 检查 downloadProtectedFile |
TypeScript 类型安全（P1）
# 检查 any 类型用法
Grep ": any" --output_mode content -n
Performance 问题（P1）
# 检查 Math.random()（打字机效果等）
Grep "Math.random()" --output_mode content
# 检查 Magic Numbers
Grep "9999999" --output_mode content
# 检查 console 日志
Grep "console\.(log|info|warn)" --output_mode content
React Hooks 检查（P1）
# 检查 useEffect 依赖
Grep "useEffect\([^)]*\)" --output_mode content
# 检查 hooks 在循环/条件中调用
Grep "(useState|useEffect|useCallback).*\n.*if" --multiline --output_mode content
Security 安全检查（P1）
# 检查硬编码密钥
Grep "(apiKey|secretKey|token).*=.*['\"][a-zA-Z0-9_-]{20,}" --output_mode content
# 检查 localStorage token
Grep "localStorage\.(setItem|getItem).*token" --output_mode content
i18n 国际化检查（P2）
# 检查中文字符
Grep "[一-龥]" --output_mode content
Accessibility 无障碍检查（P1）
# img without alt
Grep "<img(?![^>]* alt)" --glob "*.vue" --output_mode content
# 检查 input without label
Grep "<input(?![^>]* aria-label)(?![^>]* aria-labelledby)" --glob "*.vue" --output_mode content
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.
- 23d ago Changed · +4 lines 1655e76b55a3
- 2mo ago First seen · 181 lines · 86 tokens per session scan A 6cfdb782f025
frontend-code-doctor is a skill published in the GitHub repository jiushiwon/wg-skills (134 stars, last pushed yesterday), licensed Apache-2.0. It adds 86 tokens to every session and 1,399 once invoked, about $0.0003 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 2026-08-30.
frontend-code-doctor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| frontend-code-doctorjiushiwon/wg-skills | Skill | 134 | yesterday | Apache-2.0 | A | 86 | Claude Code, Codex |
| vue-best-practicesliuyanghejerry/Clausura | Skill | 205 | 1mo ago | MIT | A | 31 | Claude Code, Codex |
| standards-to-toolingpantheon-org/tekhne | Skill | 10 | yesterday | MIT | A | 76 | Claude Code, Codex |
| Component Test Scaffold (Vue.js)s977043/river-review | Skill | 7 | yesterday | MIT | A | 22 | Claude Code |
| fe-framework-coding-standardevolplus/talos | Skill | 8 | yesterday | Apache-2.0 | A | 111 | Claude Code |
| svelte5joshuadavidthomas/agent-skills | Skill | 63 | 3mo ago | MIT | A | 180 | Claude Code, Codex |
| solid-errors-react-contaminationOpenAEC-Foundation/OpenAEC-Workspace-Composer | Skill | 6 | 1mo ago | MIT | A | 113 | Claude Code |