fast-litellm: Instructions file for Claude Code

CLAUDE.md

fast-litellm CLAUDE.md is an instructions file for Claude Code from neul-labs/fast-litellm. It costs 1,987 tokens per session, scanned C, original, MIT.

Project instructions for Fast LiteLLM, a Rust-based speed layer for LiteLLM that keeps the same Python interface. They explain setup, development builds, release builds, and Python package creation.

In plain words
What is it for?
Use them when setting up the project, creating a development environment with uv, building locally, making release packages, or targeting a specific Python version.
Why use it?
They give contributors the commands and project context needed to build a Python extension that combines Rust code with Python.

Instructions file for Claude Code

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

This is neul-labs/fast-litellm's own configuration. It tells Claude Code how to work on fast-litellm 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 fast-litellm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to neul-labs/fast-litellm. 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/neul-labs/fast-litellm/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/neul-labs/fast-litellm

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 fast-litellm CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/neul-labs/fast-litellm/claude-md/github.svg)](https://agentmods.dev/instructions/neul-labs/fast-litellm/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/neul-labs/fast-litellm/claude-md"><img src="https://agentmods.dev/badge/instructions/neul-labs/fast-litellm/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.

agentmods 80×15 button for fast-litellm CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/neul-labs/fast-litellm/claude-md"><img src="https://agentmods.dev/badge/instructions/neul-labs/fast-litellm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,987 This file is loaded in full into every session.
When invoked 1,987 The same file — it is already loaded in full.
Security scan C 2 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 $0.01987 $0.01987
Opus 5 $0.00993 $0.00993
Sonnet 5 $0.00397 $0.00397
Haiku 4.5 $0.00199 $0.00199

Measured 9d ago against content hash cedf0cd27da3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

fast-litellm CLAUDE.md scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -LsSf https://astral.sh/uv/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -LsSf https://astral.sh/uv/install.sh | sh
CLAUDE.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 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

Fast LiteLLM is a high-performance Rust acceleration layer for LiteLLM that provides drop-in replacements for performance-critical components. It uses PyO3 to create Python extensions from Rust code, achieving 2-20x performance improvements while maintaining full compatibility with the existing Python API.

Build Commands

Initial Setup

# Install uv (fast Python package manager)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Create virtual environment and install dependencies
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install maturin and development dependencies
uv add --dev maturin

# Development build (creates editable install)
uv run maturin develop

# Or use the automated setup script
./scripts/setup_dev.sh

Building

# Development build (fast, with debug symbols)
uv run maturin develop

# Release build (optimized)
uv run maturin build --release

# Build wheel for distribution
uv run maturin build --release --out dist

# Build for specific Python version
uv run maturin build --interpreter python3.11

Testing

# Run all tests
uv run pytest tests/

# Run specific test file
uv run pytest tests/test_accelerator.py

# Run single test
uv run pytest tests/test_basic.py::test_import_package

# Run tests with coverage
uv run pytest tests/ --cov=fast_litellm --cov-report=html

# Run tests excluding slow benchmarks
uv run pytest tests/ -m "not slow"

# Run only integration tests
uv run pytest tests/ -m integration

# Run Rust tests
cargo test

# Run Rust tests with specific module
cargo test --lib core

Code Quality

# Python formatting
uv run black fast_litellm/ tests/

# Python import sorting
uv run isort fast_litellm/ tests/

# Python linting
uv run flake8 fast_litellm/
uv run mypy fast_litellm/
uv run ruff check fast_litellm/

# Rust formatting
cargo fmt

# Rust linting
cargo clippy -- -D warnings

# Run all quality checks
uv run black --check . && uv run isort --check-only . && uv run flake8 . && uv run mypy fast_litellm/ && cargo fmt -- --check && cargo clippy

Read the full file on GitHub · 250 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. 9d ago First seen · 250 lines · 1,987 tokens per session scan C cedf0cd27da3

Subscribe to this mod's changes

fast-litellm CLAUDE.md is an instructions file published in the GitHub repository neul-labs/fast-litellm (47 stars, last pushed 2d ago), licensed MIT. It adds 1,987 tokens to every session, about $0.0099 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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

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

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

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

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