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/jiushiwon/wg-skills/optimizegit 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/commands/jiushiwon/wg-skills/optimize)<a href="https://agentmods.dev/commands/jiushiwon/wg-skills/optimize"><img src="https://agentmods.dev/badge/commands/jiushiwon/wg-skills/optimize.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 5.1 | $0.00000 | $0.02075 |
| Opus 5 | $0.00000 | $0.01038 |
| Sonnet 5 | $0.00000 | $0.00415 |
| Haiku 4.5 | $0.00000 | $0.00208 |
Grade A, and why
optimize 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 5d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
optimize — 一键智能重构
对现有项目（HTML/Vue/React/uniapp/小程序）智能识别技术栈、提取当前设计、匹配品牌画像、应用统一 Token，全局优化。
用法
optimize [path] [--strategy conservative|gradual|reshape] [--brand <name>] [--report-only] [--dry-run]
参数
| 参数 | 说明 | 默认 |
|---|---|---|
[path] |
项目路径 | cwd |
--strategy |
优化策略 | gradual |
--brand |
目标品牌 | 自动匹配 |
--report-only |
只输出报告不修改 | 否 |
--dry-run |
试运行（输出 diff 不写入） | 否 |
策略
| 策略 | 风险 | 说明 |
|---|---|---|
conservative |
低 | 保留现状，只统一不一致项 |
gradual |
中 | 对齐到匹配品牌 80%（默认） |
reshape |
高 | 完全套用某品牌/场景 Token |
5 步流水线
1. detect-stack
调用 scripts/detect-stack.mjs 识别项目：
- 技术栈（React/Vue/uniapp/...）
- 框架版本
- UI 库
- 项目规模
输出：
{
"stack": "vue-nuxt",
"framework": "Nuxt 3",
"version": "3.13.0",
"ui": "Element Plus",
"scale": "medium",
"files": { "componentCount": 87 }
}
2. extract-tokens
调用 scripts/extract-tokens.mjs 从代码提取事实 Token：
- 颜色（频次统计）
- 字体（家族、字号、字重）
- 间距（padding/margin/gap）
- 圆角
- 阴影
- 动效时长
- 断点
输出包含一致性警告：
- 颜色 > 30 种 → 缺少 Token 化
- 间距 < 70% 在 4pt 网格
- 圆角 > 8 种不一致
- 字体 > 5 种太多
3. match-profile
调用 scripts/match-profile.mjs 匹配调色板 + 字体画像：
- 调色板（10 套）匹配
- 字体（中文/英文/编辑/数据）
- 圆角/间距一致性分析
- 推荐优化策略
输出：
{
"bestMatch": { "name": "冷调极简", "score": 0.78 },
"fontProfile": "chinese-tech",
"drift": [
"约 35% 间距值不在 4pt 网格上",
"圆角有 12 种不同值"
],
"strategy": "gradual"
}
4. apply
按策略 + 技术栈应用变更：
只改视觉相关属性，不改业务代码：
| 改 | 不改 |
|---|---|
| 颜色值（→ CSS 变量） | API 调用 |
| 内联样式（→ 工具类 / 变量） | 数据结构 |
| 魔法数字（→ Token） | 状态管理 |
| 重复样式（→ 公共组件） | 路由配置 |
| 圆角/阴影/动效 | props / event |
| 字号（→ token） | 业务逻辑 |
实施方式
Vue/React/uniapp：
- 在
src/styles/tokens.css写入完整 Token - 在
main.ts/App.vue引入 - 替换硬编码颜色为
var(--color-*) - 替换 px 字号为 token
- 替换 px 间距为 token
- 统一圆角到阶梯
HTML+Tailwind：
- 替换
tailwind.config.js完整 token - 替换自定义 class 为 token
- 移除 arbitrary value（如
text-[#c45c48]→text-primary）
每个修改：
- 提供 before/after diff
- 记录文件路径 + 行号
- 不允许改业务逻辑
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.
- 5d ago First seen · 264 lines · 0 tokens per session scan A 40e264d911ce
optimize is a command published in the GitHub repository jiushiwon/wg-skills (88 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,075 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 2026-08-30.
Other commands, from other repositories
/a11y-audit
Auditoría de accesibilidad WCAG 2.2 completa con escaneo de HTML/componentes. Detecta: alt text faltante, problemas de contraste, navegación por teclado, etiquetas ARIA, gestión de focus, jerarquía de encabezados, etiquetas de formularios. Genera reporte accionable con instrucciones de remediación.
ux-recommend
The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…
review-css-complexity
Scan codebase for overly complex CSS/styling patterns that should be simplified.
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
wcag-audit
Accessibility audit based on WCAG 2.1/2.2 and the axe-core reference.