munhq/distil

Measure what context compression actually costs an LLM agent: where a session's tokens go, and whether a rewrite pays for the prompt cache it invalidates. Rust crate, MCP server and benchmark harness.

Latest release v0.3.4 · 28 Aug 2026

1 file for Claude Code: distil CLAUDE.md — 1,447 tokens loaded in every session.

1Stars on the repository
1Files it configures its agents with
1,447Tokens loaded in every session
1Agent configured

Instructions

These files are munhq/distil's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.