claude-local-docs: Instructions file for Claude Code

CLAUDE.md

claude-local-docs CLAUDE.md is an instructions file for Claude Code from matteodante/claude-local-docs. It costs 4,181 tokens per session, scanned A, original, MIT.

Repository guidance for a local documentation-search plugin for Claude Code that indexes JavaScript and TypeScript library documentation.

In plain words
What is it for?
Working on documentation fetching, indexing, search tools, codebase search, and the TEI Docker services used for embeddings and result ranking.
Why use it?
It explains how the plugin finds, stores, and searches documentation locally, so development can continue with less reliance on cloud services.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is matteodante/claude-local-docs's own configuration. It tells Claude Code how to work on claude-local-docs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-local-docs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to matteodante/claude-local-docs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/matteodante/claude-local-docs/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/matteodante/claude-local-docs

Made for: Claude Code.

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 claude-local-docs CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/matteodante/claude-local-docs/claude-md.svg)](https://agentmods.dev/instructions/matteodante/claude-local-docs/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/matteodante/claude-local-docs/claude-md"><img src="https://agentmods.dev/badge/instructions/matteodante/claude-local-docs/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,181 This file is loaded in full into every session.
When invoked 4,181 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.04181 $0.04181
Opus 5 $0.02090 $0.02090
Sonnet 5 $0.00836 $0.00836
Haiku 4.5 $0.00418 $0.00418

Measured 7d ago against content hash 8890c4018234, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude-local-docs 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 7d 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 · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — claude-local-docs

What this project is

A local-first alternative to Context7 for Claude Code. Provides offline-capable documentation search for JS/TS projects. It reads package.json to detect dependencies, fetches their docs (preferring llms.txt), and indexes them locally with an advanced RAG search pipeline. Embeddings and reranking run via TEI (HuggingFace Text Embeddings Inference) Docker containers — no cloud APIs at query time.

Architecture

The plugin has three parts:

  1. MCP server (src/index.ts) — Exposes 10 tools via stdio transport using server.registerTool(). Handles storage, indexing, search, doc discovery, raw doc fetching, and codebase indexing/search.
  2. /fetch-docs command (commands/fetch-docs.md) — Instructs Claude to fetch docs for each runtime dependency. Uses a multi-step strategy: (1) known URL reference table, (2) WebSearch to find actual llms.txt/llms-full.txt URLs, (3) discover_and_fetch_docs for automatic probing (npm fields + URL patterns), (4) training data fallback. Includes a curated table of verified URLs for 40+ popular libraries.
  3. /index-codebase command (commands/index-codebase.md) — Instructs Claude to index the project's own source code for semantic search via search_code.

TEI backend

ML inference is handled by three TEI instances:

  • Doc Embeddings (:39281) — nomic-ai/nomic-embed-text-v1.5 for library documentation
  • Reranker (:39282) — cross-encoder/ms-marco-MiniLM-L-6-v2 for both doc and code search
  • Code Embeddings (:39283) — Qodo/Qodo-Embed-1-1.5B for source code (68.5 CoIR, 32K context, 1536-dim)

The Node.js MCP server calls these via a shared TeiClient (src/tei-client.ts) with built-in retry, timeout, and batching. URLs are configurable via TEI_EMBED_URL, TEI_RERANK_URL, and TEI_CODE_EMBED_URL env vars (default http://localhost:39281, http://localhost:39282, http://localhost:39283).

./start-tei.sh auto-detects the platform and picks the best backend:

  • NVIDIA GPU → Docker with architecture-optimized image (Blackwell 120, Ada 89, Ampere 86, etc.)
  • Apple Silicon → native Metal build via cargo install (no Docker, GPU-accelerated)
  • No GPU → Errors by default (GPU mandatory). Use --cpu to force CPU Docker (slow, not recommended)

Read the full file on GitHub · 198 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. 7d ago First seen · 198 lines · 4,181 tokens per session scan A 8890c4018234

Subscribe to this mod's changes

claude-local-docs CLAUDE.md is an instructions file published in the GitHub repository matteodante/claude-local-docs (5 stars, last pushed 6mo ago), licensed MIT. It adds 4,181 tokens to every session, about $0.0209 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

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens