mufeedvh/code2prompt

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

What it solves

It eliminates the tedious manual process of copying and formatting multiple files from a codebase when providing context to Large Language Models (LLMs). It solves the problem of "context engineering" by automating the ingestion and structuring of local codebases into a single, LLM-ready prompt.

How it works

Built in Rust for high performance, the tool traverses directories and reads files while respecting .gitignore rules. It uses Handlebars templates to format the gathered code and metadata into a structured prompt. It offers multiple interfaces: a CLI for quick use, a TUI for interactive configuration, a Python SDK for integration into agents or RAG pipelines, and an MCP server for agentic applications to access local codebases efficiently.

Who it’s for

It is designed for developers who manually provide code context to AI chat interfaces (like ChatGPT), developers building AI agents, and engineers implementing RAG (Retrieval-Augmented Generation) pipelines that require codebase ingestion.

Highlights

  • Smart Filtering: Supports glob patterns and automatically respects .gitignore settings.
  • Git Integration: Can include Git diffs, logs, and branch comparisons in the generated prompt.
  • Token Estimation: Provides parallel per-file token counts to estimate the prompt size.
  • Flexible Output: Supports outputting to stdout, saving to a file, or copying directly to the clipboard.
  • Multi-language Support: Includes specialized reading for formats like CSV, Notebooks, and JSONL.

Related

  • Project
    NeoLabHQ/context-engineering-kit

    A plug‑in marketplace for LLM‑based coding assistants (Claude Code, Gemini, Antigravity, etc.) that supplies token‑efficient, context‑engineering patterns—reflection loops, sub‑agent judges, specification‑first development, code‑review agents, and Git helpers—to make AI‑generated code more reliable and easier to integrate into CI pipelines.

  • Project
    cyberchitta/llm-context.py

    A context curation tool that enables AI coding agents to automatically identify, pack, and manage the specific files and code excerpts needed for a task to avoid token limits and missing information.

  • Project
    microsoft/agentrc

    A context engineering tool for AI coding agents that automatically generates, measures, and maintains the instruction files and configurations needed for agents to understand a codebase.

  • Dispatch
    Anthropic Effective Context Engineering for AI Agents

    Anthropic introduces context engineering as a strategy for curating the optimal set of tokens to maximize LLM performance and overcome attention scarcity and context rot.

  • Project
    chr15m/runprompt

    A command-line tool to execute .prompt files, allowing users to treat LLM prompts as versionable artifacts and automate AI workflows via the shell.