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 wot-ui/wot-starter --skill starter-cleanergit clone --depth 1 https://github.com/wot-ui/wot-starterWrote 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/wot-ui/wot-starter/starter-cleaner)<a href="https://agentmods.dev/skills/wot-ui/wot-starter/starter-cleaner"><img src="https://agentmods.dev/badge/skills/wot-ui/wot-starter/starter-cleaner/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/wot-ui/wot-starter/starter-cleaner"><img src="https://agentmods.dev/badge/skills/wot-ui/wot-starter/starter-cleaner.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 | $0.00082 | $0.00658 |
| Opus 5 | $0.00041 | $0.00329 |
| Sonnet 5 | $0.00016 | $0.00132 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
starter-cleaner 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- starter-cleaner — 100% identical, 0 lines differ
What it actually says
Starter Cleaner
使用随技能提供的确定性脚本清理 wot-starter v2，保留基础页面、Wot UI、uni-echarts 和 echarts 能力。
执行流程
-
在项目根目录运行
git status --short，确认并告知用户未提交改动会被保留，但待清理目录中的改动会随目录一起删除。 -
如果用户尚未明确要求执行清理，先说明这是破坏性操作并取得确认。
-
先预览清理计划：
node .agents/skills/starter-cleaner/scripts/clean.js --dry-run -
确认目标是
wot-starterv2 后执行。脚本会删除旧的src/pages.json，然后受控运行pnpm dev:h5，等新的最小src/pages.json生成后退出 dev server：node .agents/skills/starter-cleaner/scripts/clean.js -
执行
pnpm install --lockfile-only更新锁文件，再运行pnpm type-check和pnpm lint。如果依赖不可用，至少检查git diff --check和清理后的 diff，并将未运行的验证明确告知用户。
清理范围
脚本执行以下操作，且支持重复运行：
- 删除
docs/、src/subPages/、src/subEcharts/、src/subAsyncEcharts/。 - 删除旧的
src/pages.json，再通过pnpm dev:h5触发vite-plugin-uni-pages重新生成最小页面配置。 - 删除
pnpm-workspace.yaml，将项目从文档 workspace 恢复为单包项目。 - 从
vite.config.ts的UniHelperPages配置中移除上述三个示例分包入口。 - 从
package.json中移除docs:*与lint:docs脚本。 - 保留
uni-echarts、echarts依赖和相关 Vite 配置，方便业务继续使用图表。
安全约束
- 不直接拼接或扩展删除路径；仅使用脚本内的固定清单。
- 不在非
wot-starterv2 项目中运行。仅在用户明确确认目标项目后使用--force跳过项目身份检查。 - 不用
--force绕过未提交改动提示；该参数只用于项目身份检查。
What ships with it
2 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.
- 8d ago First seen · 44 lines · 82 tokens per session scan A 3df6bb07074f
starter-cleaner is a skill published in the GitHub repository wot-ui/wot-starter (386 stars, last pushed 11d ago), licensed MIT. It adds 82 tokens to every session and 658 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 2026-08-31.
Other skills, from other repositories
tinyvue-develop-spec
Development rules for a TinyVue component library that supports Vue 2 and Vue 3, desktop browsers, and mobile-first layouts. They separate templates, reusable logic, styles, design rules, localization, and tests.
build-app-page
Construct a new app page from scratch using this repo's component system. Use when the user says "build a new page for X", "create a settings page", "add a dashboard for Y", "scaffold an app screen", or otherwise wants a Next.js page assembled from the project's elements/components/patterns. Produces a route under…
export-component-to-other-repo
Port a component from nextjs-css-agent-components into a different repo without losing the design-system precision. Use when the user says "copy this component to ", "lift Button into ", "bring the Thin layout over", or otherwise wants a faithful transplant of one or more components from this codebase. Carries over…
next-upgrade
Upgrade Next.js to the latest version following official migration guides and codemods.
admin-net-frontend
Use when building Vue 3 admin dashboard frontends with dynamic routing, permission-based menus, and CRUD page generation. Admin.NET Frontend: Vue 3 + Vite + TypeScript admin UI for Admin.NET backend.
nuxt-data-audit
An audit guide for checking how Nuxt projects load data and whether their data-fetching patterns follow the project's performance rules.