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/fmaclen/svelte-vibe-code/claude-mdgit clone --depth 1 https://github.com/fmaclen/svelte-vibe-codeWhat 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 | $0.00809 | $0.00809 |
| Opus 5 | $0.00404 | $0.00404 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
svelte-vibe-code 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Common Development Commands
Development Workflow
# Install dependencies
npm install
# Start Convex backend (keep running in terminal 1)
npm run convex
# Run development server (terminal 2)
npm run dev
# Run tests (requires Convex running)
npm test
# Quality checks
npm run quality # Runs format, lint, and type checks
npm run format # Auto-format code with Prettier
npm run lint # Check code style with ESLint and Prettier
npm run check # Type check with svelte-check
Testing
# Run E2E tests with Playwright (Convex must be running)
npm test
# Tests will automatically set IS_DEV_OR_TEST=true for database clearing
Architecture Overview
Stack
- Frontend: SvelteKit (client-only, no SSR) + Svelte 5 with runes
- UI Components: shadcn-svelte 1.x (Tailwind v4 + Bits UI) - fully installed in
src/lib/components/ui/ - Backend: Convex (real-time database with TypeScript functions)
- Auth: Custom implementation using Convex sessions (demo-ready, not production-ready)
- Testing: Playwright E2E tests
Key Directories
convex/- Backend functions and database schemaschema.ts- Database tables: users, sessions, messagesauth.ts- Authentication mutations/queries (signUp, signIn, signInAnonymously, signOut, currentUser)messages.ts- Real-time messaging functionsdev.ts- Development helpers (clearAllData - only works with IS_DEV_OR_TEST=true)
src/lib/auth.svelte.ts- Client-side auth state management using Svelte 5 runessrc/lib/components/ui/- Complete shadcn-svelte component librarysrc/routes/- SvelteKit pages
Important Patterns
Authentication Flow
- Auth state is managed in
src/lib/auth.svelte.tsusing Svelte 5 runes ($state,$derived,$effect) - Auth context is set up in
src/routes/+layout.svelte - Pages use
AuthGuardcomponent for protection - Sessions stored in localStorage with token-based authentication
- Passwords are hashed client-side with PBKDF2, then server-side with bcrypt
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.
- 2d ago First seen · 103 lines · 809 tokens per session scan A b503cf65b7c9
svelte-vibe-code CLAUDE.md is an instructions file published in the GitHub repository fmaclen/svelte-vibe-code (3 stars, last pushed 1y ago), licensed MIT. It adds 809 tokens to every session, about $0.0040 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
daisyui packages.docs.instructions.md
Instructions for saadeghi/daisyui, a project described as: 🌼 🌼 🌼 🌼 🌼 The most popular, free and open-source Tailwind CSS component library.
formkit CLAUDE.md
Instructions for formkit/formkit, covering formkit, architecture, packages, core (framework-agnostic) and vue integration.
vue-tui AGENTS.md
Instructions for vuejs-ai/vue-tui, covering common pitfalls & best practices, project context records (pcr), using vite+, the unified toolchain for the web and review checklist.
skills AGENTS.md
AGENTS.md instructions for vuejs-ai/skills, covering vue skills development guide, branch strategy, development workflow, skill scopes and common pitfalls & best practices.
svelte-markdown CLAUDE.md
Instructions for humanspeak/svelte-markdown, covering claude.md, project overview, key technologies, project structure and development commands.
mulmoterminal CLAUDE.md
Instructions for receptron/mulmoterminal, covering claude.md — mulmoterminal, stack & package manager, run after changes, import a component at module scope, never inside a test and no emojis.