vibescout CLAUDE.md

vibescout CLAUDE.md is an instructions file for coding agents from sevenseconds/vibescout. It costs 3,221 tokens per session, scanned A, original, MIT.

Repository instructions for VibeScout, an MCP server that turns a codebase into a searchable knowledge base using AI-generated representations of code. It can run locally or use cloud AI providers, and includes a web dashboard.

In plain words
What is it for?
Running tests and linting, indexing or re-indexing folders, searching code with natural-language questions, starting the MCP server or UI, and compacting or resetting its database.
Why use it?
They show how to index projects, search them, start the server or dashboard, and keep the search database maintained.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/sevenseconds/vibescout/claude-md
Clone the repo
git clone --depth 1 https://github.com/sevenseconds/vibescout

Wrote 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.

agentmods badge for vibescout CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sevenseconds/vibescout/claude-md.svg)](https://agentmods.dev/instructions/sevenseconds/vibescout/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sevenseconds/vibescout/claude-md"><img src="https://agentmods.dev/badge/instructions/sevenseconds/vibescout/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,221 This file is loaded in full into every session.
When invoked 3,221 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03221 $0.03221
Opus 5 $0.01611 $0.01611
Sonnet 5 $0.00644 $0.00644
Haiku 4.5 $0.00322 $0.00322

Measured 2d ago against content hash 6d910a8108cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibescout 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.

CLAUDE.md · 364 lines

How it starts

The opening of the file, as written. The whole thing — 364 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.

Project Overview

VibeScout is a high-performance Model Context Protocol (MCP) server for local semantic code search and AI-powered assistance. It transforms codebases into searchable, chat-ready knowledge bases using local or cloud-based AI providers.

Commands

Development

# Run tests
npm test

# Run a specific test file
npx vitest run tests/embeddings.test.js

# Lint code
npm run lint

# Build UI
npm run build:ui

Server Operations

# Start Web UI (dashboard at http://localhost:3000)
vibescout ui

# Start MCP server (stdio mode for Claude Desktop/Cursor)
vibescout --mcp stdio

# Start MCP server (HTTP/SSE mode)
vibescout --mcp sse --port 3000

# Index a folder
vibescout index ./my-project "My Project"

# Force full re-index
vibescout index ./my-project "My Project" --force

# Search from terminal
vibescout search "how does auth work?"

# Compact database (remove stale files)
vibescout compact

# Reset database (clear all data)
vibescout reset

UI Development

cd ui
npm run dev      # Start Vite dev server
npm run build    # Build for production
npm run lint     # Lint UI code

Architecture

Entry Points

  • src/index.js - Main CLI entry point using Commander.js
  • bin/vibescout.js - Executable wrapper
  • src/server.js - MCP server and HTTP API (Hono-based)

Core Systems

Provider Architecture (src/providers/)

  • All providers implement EmbeddingProvider and/or SummarizerProvider interfaces from base.ts
  • Embedding providers generate vectors: generateEmbedding(text) or generateEmbeddingsBatch(texts)
  • Summarizer providers handle LLM operations: summarize(), generateBestQuestion(), generateResponse()
  • Providers include: Local (Transformers.js), Ollama, OpenAI, Gemini, Cloudflare, Z.AI, Bedrock
  • src/embeddings.ts - Manages provider instances with adaptive concurrency throttling

Read the full file on GitHub · 364 lines

Changes

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.

  1. 2d ago First seen · 364 lines · 3,221 tokens per session scan A 6d910a8108cc

Subscribe to this mod's changes

vibescout CLAUDE.md is an instructions file published in the GitHub repository sevenseconds/vibescout (0 stars, last pushed 7mo ago), licensed MIT. It adds 3,221 tokens to every session, about $0.0161 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.

Related

Other instructions, from other repositories