# distil

> distil — munhq-distil. Use this tool when you need to measure the cost of context compression for LLM agents, identifying where session tokens are allocated and whether rewrites are efficient. It solves problems related to optimizing prompt cache usage and token allocation, providing insights through a Rust crate, MCP server, and benchmark harness. Ideal for use cases where LLM agents require efficient context management, such as large-scale language modeling tasks.

Canonical page: https://skillsregistry.net/skills/munhq-distil  
JSON: https://api.skillsregistry.net/v1/skills/munhq-distil

## Description

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.

## Trust

- **Trust score (0–1):** 0.48
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/munhq/distil)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "munhq-distil"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/munhq-distil` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/munhq-distil/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt