What is ragfs CLAUDE.md?

Repository instructions for ragfs, a Rust workspace that provides a FUSE filesystem for semantic search. They cover Claude Code guidance, build and run commands, tests, formatting, linting, and the nine-crate processing pipeline.

Building ragfs in development or release mode, testing all or one crate, checking formatting, running Clippy, and indexing or querying files with its command-line interface.

They give an agent the project-specific commands and structure it needs to work consistently, reducing guesswork when building, testing, or debugging the code.

How Venere-Labs/ragfs configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Venere-Labs/ragfs. 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/Venere-Labs/ragfs/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Venere-Labs/ragfs

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/venere-labs/ragfs/claude-md/github.svg)](https://agentmods.dev/instructions/venere-labs/ragfs/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/venere-labs/ragfs/claude-md"><img src="https://agentmods.dev/badge/instructions/venere-labs/ragfs/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/venere-labs/ragfs/claude-md"><img src="https://agentmods.dev/badge/instructions/venere-labs/ragfs/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,175 This file is loaded in full into every session.

When invoked 1,175 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.

Model	Per session	Once invoked
Fable 5.1	$0.01175	$0.01175
Opus 5.5	$0.00470	$0.00470
Sonnet 5.5	$0.00235	$0.00235
Haiku 4.5	$0.00118	$0.00118

Measured 1mo ago against content hash 31c3abaf10de, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ragfs 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 1mo 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 · 117 lines

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

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build Commands

cargo build                          # Development build
cargo build --release                # Release build
cargo build -p <crate-name>          # Build specific crate

Testing

cargo test --all                     # Run all tests
cargo test -p <crate-name>           # Run tests for specific crate
cargo test -- --nocapture            # Run tests with output

Linting & Formatting

cargo fmt --all                      # Format code
cargo fmt --all -- --check           # Check formatting
cargo clippy --all-targets -- -D warnings  # Run clippy

Running

cargo run -- -v index /path/to/dir   # Index with verbose logging
cargo run -- query /path "search"    # Query the index
RUST_LOG=debug cargo run -- ...      # Debug logging

Architecture

RAGFS is a FUSE filesystem for semantic search using vector embeddings. It's organized as a Rust workspace with 10 crates plus a Python MCP server, following a pipeline pattern:

File → Extraction → Chunking → Embedding → Storage → Search

Crate hierarchy:

ragfs - CLI binary (entry: crates/ragfs/src/main.rs)
ragfs-core - Foundation traits and types (traits.rs, types.rs)
ragfs-extract - Content extraction via ExtractorRegistry
ragfs-chunker - Document chunking via ChunkerRegistry
ragfs-embed - Local embeddings using Candle (gte-small, 384-dim)
ragfs-store - Vector storage with LanceDB
ragfs-index - Pipeline orchestration and file watching
ragfs-query - Query execution
ragfs-fuse - FUSE filesystem with agent operations, safety layer, and semantic features
ragfs-python - PyO3 bindings; Haystack / LangChain / LlamaIndex adapters live under crates/ragfs-python/python/ragfs/
ragfs-mcp - Python MCP server (crates/ragfs-mcp, not a Cargo member)

ragfs-fuse modules:

filesystem.rs - Main FUSE handler, inode management, virtual directory routing
ops.rs - OpsManager for file operations with JSON feedback (.ops/)
safety.rs - SafetyManager for soft delete, audit logging, undo (.safety/)
semantic.rs - SemanticManager for AI-powered file operations (.semantic/)

Read the full file on GitHub · 117 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.

1mo ago Changed · +2 lines · +74 tokens per session 31c3abaf10de
2mo ago First seen · 115 lines · 1,101 tokens per session scan A f8322aebedc9

Subscribe to this mod's changes

ragfs CLAUDE.md is an instructions file published in the GitHub repository Venere-Labs/ragfs (14 stars, last pushed 28d ago), licensed Apache-2.0. It adds 1,175 tokens to every session, about $0.0047 per session on Opus 5.5. 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.

RAG and vectors Rust claude embeddings fuse semantic-search

ragfs CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ragfs CLAUDE.mdVenere-Labs/ragfs	Instructions file	14	28d ago	Apache-2.0	A	1,175	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ragfs: Instructions file for Claude Code