# lm-resizer

> lm-resizer — phuetz-lm-resizer. Use this tool when you need to optimize large language model (LLM) performance by compressing noisy output from tools like tests, diffs, and logs. The lm-resizer filters and reduces unnecessary data, minimizing wasted tokens while allowing for full evidence recovery, making it ideal for use cases involving Claude Code, Codex, and MCP agents. It integrates with Code Explorer and supports git, providing a local-first solution for efficient LLM input processing.

Canonical page: https://skillsregistry.net/skills/phuetz-lm-resizer  
JSON: https://api.skillsregistry.net/v1/skills/phuetz-lm-resizer

## Description

Rust-native context compression for Claude Code, Codex & MCP agents: filters & compresses noisy tool output (tests, diffs, logs, JSON, provider traffic) before it reaches the LLM — fewer wasted tokens, full evidence recoverable. Local-first, Apache-2.0. Pairs with Code Explorer.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/phuetz/lm-resizer)

## 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": "phuetz-lm-resizer"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/phuetz-lm-resizer` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/phuetz-lm-resizer/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