llamafarm: Instructions file for Claude Code

CLAUDE.md

llamafarm CLAUDE.md is an instructions file for Claude Code from llama-farm/llamafarm. It costs 542 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for LlamaFarm, a framework for building local AI applications with configuration files, a command-line tool, and user-provided data. A monorepo is one repository containing several related parts, such as the command-line tool, server, search system, and model runtime.

In plain words
What is it for?
Use it when working on LlamaFarm's command-line tool, API server, document search and retrieval system, model runtime, or project examples.
Why use it?
It explains how the parts fit together and provides the expected ways to build, run, and use the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is llama-farm/llamafarm's own configuration. It tells Claude Code how to work on llamafarm 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 llamafarm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to llama-farm/llamafarm. 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/llama-farm/llamafarm/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/llama-farm/llamafarm

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 llamafarm CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/llama-farm/llamafarm/claude-md/github.svg)](https://agentmods.dev/instructions/llama-farm/llamafarm/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/llama-farm/llamafarm/claude-md"><img src="https://agentmods.dev/badge/instructions/llama-farm/llamafarm/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 llamafarm CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/llama-farm/llamafarm/claude-md"><img src="https://agentmods.dev/badge/instructions/llama-farm/llamafarm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 542 This file is loaded in full into every session.
When invoked 542 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 $0.00542 $0.00542
Opus 5 $0.00271 $0.00271
Sonnet 5 $0.00108 $0.00108
Haiku 4.5 $0.00054 $0.00054

Measured 10d ago against content hash cceed3843f93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

llamafarm 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 10d 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LlamaFarm

Modular AI development framework. Build AI apps locally with YAML configs, CLI, and your own data.

Monorepo overview

This repository consists of multiple components

CLI Description: Primary user interface for LlamaFarm. Orchestrates local service lifecycle (starting/stopping server, RAG, and runtime processes), handles project initialization (lf init), provides interactive chat sessions (lf chat), and coordinates model downloads. Tech Stack: Go 1.24+, Cobra Directory: cli/

Server Description: Central API gateway that coordinates all LlamaFarm services. Routes inference requests to the Universal Runtime, dispatches RAG tasks to Celery workers, and serves the Designer UI in production. Tech Stack: Python 3.12+, FastAPI, Celery Directory: server/

RAG Description: Celery-based worker for retrieval-augmented generation. Handles document ingestion, embedding generation, vector storage, and semantic search. Tech Stack: Python 3.11+, LlamaIndex, ChromaDB, Celery Directory: rag/

Universal Runtime Description: Local ML inference server with OpenAI-compatible API. Supports text generation, embeddings, OCR, anomaly detection, and classification across HuggingFace and GGUF models. Tech Stack: Python 3.11+, transformers, torch, llamafarm-llama (LlamaFarm's own llama.cpp bindings) Directory: runtimes/universal/

Designer Description: Browser-based project workbench for building AI applications. Provides config editing, chat testing, dataset management, RAG configuration, and model selection. Tech Stack: TypeScript, React, Vite, TanStack Query Directory: designer/

Build Description: Nx monorepo configuration for cross-project builds and development workflows. Tech Stack: Nx workspace Directory: (root)

See .claude/rules/ for detailed guidelines.

Building and Running

  • Use the nx package to build and run projects within this monorepo.
  • Check the project.json files at the repo root and project directories for available scripts

Read the full file on GitHub · 53 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. 10d ago First seen · 53 lines · 542 tokens per session scan A cceed3843f93

Subscribe to this mod's changes

llamafarm CLAUDE.md is an instructions file published in the GitHub repository llama-farm/llamafarm (838 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 542 tokens to every session, about $0.0027 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 2026-08-30.

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens