# rlm

> rlm — saschaontour-rlm. Use this tool when you need to efficiently query and edit large codebases with minimal context waste. The rlm context broker solves problems of token waste and context rot by providing progressive disclosure and AST-aware retrieval, enabling surgical editing and semantic search. Ideal for use with AI coding agents, particularly when working with git version control systems.

Canonical page: https://skillsregistry.net/skills/saschaontour-rlm  
JSON: https://api.skillsregistry.net/v1/skills/saschaontour-rlm

## Description

Context broker for AI coding agents (CLI + MCP). Queries codebases via progressive disclosure instead of feeding entire files into context — reducing token waste and context rot. AST-aware retrieval, surgical editing with syntax guard, semantic search. Inspired by Recursive Language Models research (MIT/Stanford, 2025). Built in Rust.

## Trust

- **Trust score (0–1):** 0.49
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** search
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/SaschaOnTour/rlm)

## 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": "saschaontour-rlm"
    }
  }
}
```

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