How do I install the Rlm skill?

Run npx skillmds@latest add guia-matthieu/rlm in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Rlm?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

guia-matthieu (@guia-matthieu) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Rlm by guia-matthieu — Agent Skill

Name: Rlm
Rating: 4.2 (5 reviews)
Author: guia-matthieu

Rlm

Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map-reduce across files without context rot. Use when: analyzing large repositories; auditing security or auth across many files; finding patterns across 50+ files; processing large log files or data dumps

guia-matthieu Updated Sep 9, 2026

File contents

Recursive Language Model (RLM)

"Context is an external resource, not a local variable."

You are the Root Node. Your job is NOT to read code directly, but to orchestrate sub-agents that read code for you.

The RLM Loop

Phase 1: Index & Filter

Identify relevant files without loading them into context.

# Find candidate files
grep -rl "pattern" src/ --include="*.ts"
find . -name "*.py" -newer last_check

Phase 2: Parallel Map

Split work into atomic units, spawn parallel agents.

Launch 3-5+ agents in parallel for broad tasks
Give each agent ONE specific file or chunk
Each agent returns a structured summary

Example spawn:

Agent 1: "Read src/api/routes.ts. List all endpoints with their auth decorators."
Agent 2: "Read src/api/users.ts. List all endpoints with their auth decorators."
...

Phase 3: Reduce & Synthesize

Collect all agent outputs, find patterns, compile into a coherent answer.

If incomplete, recurse: run a second RLM pass on the specific gaps.

Critical Rules

NEVER read more than 3-5 files into your main context
ALWAYS use parallel agents when file count > 5
Write Python scripts for state tracking across 50+ files — let the script scan and summarize
If parallel agents are unavailable, fall back to iterative Python scripting

Example: "Find all API endpoints, check for Auth"

Wrong (monolithic): Read each file sequentially → context fills up, reasoning degrades.

RLM Way:

grep -l "@Controller" src/**/*.ts → 20 files
Spawn 20 agents, each extracts endpoints + auth status
Collect outputs, compile table, identify missing auth

Output Format

Return a structured summary:

Findings table (file, pattern, status)
Gaps identified (what needs deeper investigation)
Confidence level (how complete the scan was)

Skill Boundaries

Excels for: Codebases >100 files, cross-file pattern search, audit tasks, large file analysis.

Not ideal for: Small projects (<50 files), single file analysis, file modification tasks.

---name: rlmdescription: Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map-reduce across files without context rot. Use when: analyzing large repositories; auditing security or auth across many files; finding patterns across 50+ files; processing large log files or data dumpslicense: MIT--- # Recursive Language Model (RLM) **"Context is an external resource, not a local variable."** You are the **Root Node**. Your job is NOT to read code directly, but to orchestrate sub-agents that read code for you. ## The RLM Loop ### Phase 1: Index & Filter Identify relevant files without loading them into context. ```bash # Find candidate files grep -rl "pattern" src/ --include="*.ts" find . -name "*.py" -newer last_check ``` ### Phase 2: Parallel Map Split work into atomic units, spawn parallel agents. - Launch **3-5+ agents** in parallel for broad tasks - Give each agent **ONE specific file or chunk** - Each agent returns a structured summary Example spawn: ``` Agent 1: "Read src/api/routes.ts. List all endpoints with their auth decorators." Agent 2: "Read src/api/users.ts. List all endpoints with their auth decorators." ... ``` ### Phase 3: Reduce & Synthesize Collect all agent outputs, find patterns, compile into a coherent answer. If incomplete, recurse: run a second RLM pass on the specific gaps. ## Critical Rules 1. **NEVER** read more than 3-5 files into your main context 2. **ALWAYS** use parallel agents when file count > 5 3. **Write Python scripts** for state tracking across 50+ files — let the script scan and summarize 4. If parallel agents are unavailable, fall back to iterative Python scripting ## Example: "Find all API endpoints, check for Auth" **Wrong** (monolithic): Read each file sequentially → context fills up, reasoning degrades. **RLM Way**: 1. `grep -l "@Controller" src/**/*.ts` → 20 files 2. Spawn 20 agents, each extracts endpoints + auth status 3. Collect outputs, compile table, identify missing auth ## Output Format Return a structured summary: - **Findings table** (file, pattern, status) - **Gaps identified** (what needs deeper investigation) - **Confidence level** (how complete the scan was) ## Skill Boundaries **Excels for:** Codebases >100 files, cross-file pattern search, audit tasks, large file analysis. **Not ideal for:** Small projects (<50 files), single file analysis, file modification tasks.

Frequently asked questions

Rlm