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/lazercaveman/nuxt-starter/claude-mdgit clone --depth 1 https://github.com/lazercaveman/nuxt-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/lazercaveman/nuxt-starter/claude-md)<a href="https://agentmods.dev/instructions/lazercaveman/nuxt-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/lazercaveman/nuxt-starter/claude-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 5.1 | $0.01484 | $0.01484 |
| Opus 5 | $0.00742 | $0.00742 |
| Sonnet 5 | $0.00297 | $0.00297 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
nuxt-starter CLAUDE.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 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — nuxt-starter
Project
Nuxt 4 Starter Kit — a batteries-included template for real-world Nuxt 4 / Vue 3 applications. MIT-licensed, maintained by Ali Soueidan (@lazercaveman).
Tech Stack
- Framework: Nuxt 4 (Vue 3,
app/directory structure) - Language: TypeScript (strict mode)
- Build: Vite (native Nuxt integration)
- Package Manager: yarn (see version in
package.json) - Node: Version can be found in Package.json (enforced via
engines) - State: Pinia (
@pinia/nuxt) - Styling: Tailwind CSS v4 (
@tailwindcss/vite) + SCSS (Sass) - Linting: Oxlint (
oxlint) — configured in.oxlintrc.jsoncwithtypescriptandvueplugins - Formatting: Oxfmt (
oxfmt) — configured in.oxfmtrc.jsonc - Testing: Vitest +
@vitest/coverage-v8+@vitest/ui - Git Hooks: Husky (pre-push: lint + test)
Directory Layout
├── app/ # Nuxt 4 app directory (components, pages, composables, assets, stores, tests)
│ ├── components/
│ ├── pages/
│ ├── composables/
│ ├── assets/
│ │ └── scss/ # SCSS files (animations, non-Tailwind styles)
│ ├── stores/ # Pinia stores
│ └── tests/ # Vitest unit tests
├── server/ # Nitro server routes & API
│ └── api/
├── public/ # Static assets
├── .oxlintrc.jsonc # Oxlint config — DO NOT create .eslintrc files
├── .oxfmtrc.jsonc # Oxfmt formatter config
├── vitest.config.ts # Vitest configuration
├── nuxt.config.ts # Nuxt configuration
├── tsconfig.json # TypeScript config
└── clean-project.js # One-time cleanup script (removes demo content)
Commands
yarn install # Install dependencies
yarn dev # Start dev server
yarn build # Production build
yarn generate # Static site generation
yarn preview # Preview production build
yarn start # Start production server
yarn type-check # Run vue-tsc type checking
yarn lint # Run oxlint
yarn lint:fix # Run oxlint with auto-fix
yarn format # Format with oxfmt
yarn format:check # Check formatting (used in CI/pre-push)
yarn test # Run Vitest (watch mode)
yarn test:ui # Run Vitest with browser UI
yarn test:coverage # Run Vitest with v8 coverage (used in pre-push)
yarn analyze # Bundle analysis via nuxi analyze
yarn script:cleanup # Remove demo content (one-time, self-deleting)
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 · 117 lines · 1,484 tokens per session scan A 9a6075ab8cd7
nuxt-starter CLAUDE.md is an instructions file published in the GitHub repository lazercaveman/nuxt-starter (92 stars, last pushed 3d ago), licensed MIT. It adds 1,484 tokens to every session, about $0.0074 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
south-admin-react CLAUDE.md
Claude Code instructions for southliu/south-admin-react, covering claude.md, commands, development, code quality and package management.
weapp-vite CLAUDE.md
Claude Code instructions for weapp-vite/weapp-vite, covering claude.md, project overview, vue support, common commands and development.
vuestrata AGENTS.md
AGENTS.md instructions for boussadjra/vuestrata, covering using vite+, the unified toolchain for the web, built-in commands vs scripts, tool versions, review checklist and vuestrata project rules.
vuestrata CLAUDE.md
Claude Code instructions for boussadjra/vuestrata, covering claude.md, the one thing that trips people up, slash commands, verifying and testing reka-backed components.
vuestrata copilot-instructions.md
Copilot instructions for boussadjra/vuestrata, covering copilot instructions, copilot-specific notes and before you finish.
pinyin AGENTS.md
Instructions for yunsii/pinyin, covering agents.md, hard rules, 方案与文本靠 side-effect 注册，漏 import 等于没加, vite.config.ts 的 base: '/pinyin/' 不要随手改 and 拼音术语变量名用全拼.