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/simon-he95/markstream-vue/agents-mdgit clone --depth 1 https://github.com/Simon-He95/markstream-vueWrote 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/simon-he95/markstream-vue/agents-md)<a href="https://agentmods.dev/instructions/simon-he95/markstream-vue/agents-md"><img src="https://agentmods.dev/badge/instructions/simon-he95/markstream-vue/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 | $0.00644 | $0.00644 |
| Opus 5 | $0.00322 | $0.00322 |
| Sonnet 5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
markstream-vue 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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/is the Vue 3 library source.src/components/*/contains SFC components (PascalCase folders,*.vuefiles) andindex.tsbarrel exports.src/utils/,src/types/,src/composables/contain shared helpers, types, and composables.- Library entry points and styles are exported via
src/exports.tsandsrc/index.css.
test/contains Vitest specs (e.g.test/index.test.ts,test/plugins/*.test.ts).playground/andplayground-nuxt/are local demo apps for manual testing.docs/is the VitePress documentation site.scripts/contains maintenance utilities (DTS build, peer-deps checks, doc sync scripts).
Build, Test, and Development Commands
Use pnpm (see package.json#packageManager). Key commands:
pnpm dev/pnpm play: run the Vite playground.pnpm build: build the library bundles and generate.d.ts.pnpm test/pnpm test:ui: run tests (CLI/UI).pnpm typecheck: runvue-tsc --noEmit.pnpm lint/pnpm lint:fix: ESLint checks/fixes.pnpm docs:dev/pnpm docs:build: run/build VitePress.
Coding Style & Naming Conventions
- TypeScript-first, Vue 3 SFCs.
- Indentation: 2 spaces, LF endings (see
.editorconfig). - Components:
PascalCasefolder + file names (e.g.src/components/CodeBlockNode/CodeBlockNode.vue). - Helpers:
camelCasefunctions; follow existing file naming insrc/utils/. - Linting uses
@antfu/eslint-configviaeslint.config.mjs.
Testing Guidelines
- Framework: Vitest (
pnpm test). - Prefer small, focused unit tests for parsers/components; name files
*.test.tsundertest/. - Update snapshots with
pnpm test:update.
Commit & Pull Request Guidelines
- Commit messages follow Conventional Commits (e.g.
feat:,fix:,docs:,chore:). - Link issues using GitHub keywords when applicable (e.g.
close: #123). - PRs should include: clear description/rationale, linked issues, and screenshots/GIFs for UI-visible changes.
- Before requesting review: run
pnpm lint,pnpm typecheck, andpnpm test, then sanity-check the playground.
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 · 43 lines · 644 tokens per session scan A 23d51d29f1fb
markstream-vue AGENTS.md is an instructions file published in the GitHub repository Simon-He95/markstream-vue (2,972 stars, last pushed 4d ago), licensed MIT. It adds 644 tokens to every session, about $0.0032 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 2026-08-30.
Other instructions, from other repositories
markout CLAUDE.md
Instructions for maxmilian/markout, covering claude.md, build, test, run, full test suite (swift testing), a single suite or test and build and launch the app.
MarkCardStudio AGENTS.md
AGENTS.md instructions for pangxiaobin/MarkCardStudio, covering repository guide for coding agents, product scope, stack and commands, architecture and important invariants.
eve AGENTS.md
AGENTS.md instructions for vercel/eve, covering agents.md, about eve, repository layout, git workflow and commands.
svelte-markdown CLAUDE.md
Claude Code instructions for humanspeak/svelte-markdown, covering claude.md, project overview, key technologies, project structure and development commands.
chatgpt-vue3-light-mvp AGENTS.md
Instructions for pdsuwwz/chatgpt-vue3-light-mvp, a project described as: 💭 一个可二次开发 Chat Bot 单轮对话 Web 端 MVP 原型模板, 基于 Vue 3, Vite8, TypeScript, Naive UI, Pinia(v3), UnoCSS 等主流技术构建, 🧤简单集成大模型 API, 采用单轮 AI 问答对话模式, 每次提问独立响应, 无需上下文, 支持 SSE 打字机效果流式输出, 集成 markdown-it Mermaid/KaTex/LaTex 公式高亮预览, 星火, 智谱, 硅基流动, Deepseek…
vue-bpmn-designer AGENTS.md
Instructions for tsai996/vue-bpmn-designer, covering vue-bpmn-designer collaboration rules, 1. project scope and stack, 2. commands, 3. directory responsibilities and 4. vue, state, and component rules.