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 instructions/wot-ui/wot-starter/agents-mdgit 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/instructions/wot-ui/wot-starter/agents-md)<a href="https://agentmods.dev/instructions/wot-ui/wot-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/wot-ui/wot-starter/agents-md.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 | $0.00651 | $0.00651 |
| Opus 5 | $0.00326 | $0.00326 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
wot-starter AGENTS.md 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.
What it actually says
Project Guidelines
Scope
Wot Starter 是基于 uni-app、Vue 3 和 Wot UI 的跨平台起手项目。优先做最小改动,保持现有页面、路由、组件和构建行为稳定。
Architecture
- 页面代码位于
src/pages和src/subPages。 - 通用组件位于
src/components;状态位于src/store;请求封装位于src/api。 pages.config.ts与@uni-helper/vite-plugin-uni-pages负责页面生成;生成文件不要手工维护重复来源。.agents/skills/保存给 Agent 使用的技能说明。
Build And Test
- 安装依赖:
pnpm install - 代码检查:
pnpm lint - 类型检查:
pnpm type-check - H5 构建:
pnpm build:h5
OpenSpec Workflow
涉及新功能、用户可见行为变化、API 或数据契约变化、新页面/路由、公共组件/主题调整、跨端兼容处理或跨模块重构时,必须先使用 OpenSpec 建立变更:
- 阅读
openspec/specs/中相关规范。 - 使用
.agents/skills/openspec-propose创建并评审变更提案。 - 使用
.agents/skills/openspec-apply-change实现代码。 - 使用
.agents/skills/openspec-verify-change核对规格、任务、实现和测试。 - 确认无误后使用
.agents/skills/openspec-archive-change归档。
纯拼写、格式化、明显的单点修复和不改变行为的依赖维护可以不创建变更,但仍需说明验证结果。
OpenSpec 的项目上下文和 artifact 规则位于 openspec/config.yaml;工作流以 CLI 返回的路径和状态为准,不手工假设 artifact 位置。
项目已锁定 @fission-ai/[email protected]。运行 pnpm install 后可使用 pnpm exec openspec;共享 OpenSpec Skills 调用的是裸命令 openspec,因此 Codex/Claude Code 环境还需要将同一版本安装到 PATH:
npm install -g @fission-ai/[email protected]
openspec --version
Conventions
- Vue 组件使用
<script setup lang="ts">和 Composition API,保持严格类型。 - 网络流程必须考虑加载、成功、空数据、失败和恢复/重试状态。
- 不得把凭据写入仓库;不得默认使用只在浏览器可用的 API 破坏小程序端。
- 修改 Wot UI、主题、API 或模板相关代码时,优先读取
.agents/skills/中对应的SKILL.md。 - 未经明确要求,不要顺手重构无关模块。
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 · 49 lines · 651 tokens per session scan A 00572b52ba20
wot-starter AGENTS.md is an instructions file published in the GitHub repository wot-ui/wot-starter (385 stars, last pushed 6d ago), licensed MIT. It adds 651 tokens to every session, about $0.0033 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 instructions, from other repositories
tiny-vue AGENTS.md
AGENTS.md instructions for opentiny/tiny-vue, covering agents.md, 项目概述, 关键目录结构, 环境要求 and 核心命令.
vite-vue3-browser-extension-v3 copilot-instructions.md
Instructions for mubaidr/vite-vue3-browser-extension-v3, covering copilot ai agent instructions, project overview, key workflows, architecture & patterns and integration points.
uniapp-vue3-template CLAUDE.md
Claude Code instructions for oyjt/uniapp-vue3-template, covering claude.md, 技术栈, 目录结构, 常用命令 and 架构要点.
mica-admin AGENTS.md
Instructions for lets-mica/mica-admin, covering agents.md, 项目概述, 工作准则(必读), 构建命令 and 后端 (mica-admin-server).
quail-ui CLAUDE.md
Instructions for quailyquaily/quail-ui, covering claude.md, build commands, architecture overview, entry points and component organization.
quail-ui AGENTS.md
Instructions for quailyquaily/quail-ui, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.