CoderLM — Recursive LLM File Explorer

Trust Score 71/100

Run a recursive, file-discovering agent to handle large codebases or multi-file tasks by decomposing work into sub-agents and truncating high-volume outputs.

triggers:large repomany filesdivide-and-conquerrecursive agentcontext truncation

GitHub SKILL.md

What it does

CoderLM turns a coding assistant into a recursive file-discovery LLM (RLM). When a task involves many files or the total content exceeds a comfortable context size, CoderLM discovers relevant files with shell tools, peeks strategically, and spawns sub-agents to divide-and-conquer the task. Outputs from high-volume commands are automatically truncated to avoid flooding the agent's context window.

When to use it

Use CoderLM when you need the agent to work across large repositories (>10 files), run broad codebase audits (TODOs, type errors, refactors), or perform tasks that benefit from controlled recursion and isolated sub-tasks (linting, large-scale search-and-replace, multi-file fixes).

What's included

Scripts: none detected in the repo snapshot (has_scripts=false)
References: none detected (has_references=false)
Instructions: Usage and examples show a CLI style: coderlm <agent> --prompt <file> [--max-depth N] [--allowedTools TOOLS] with concrete examples for codex, claude, and gemini CLI. The skill describes how it parses tasks, discovers files, and delegates to sub-agents while applying context guards.

Compatible agents

Designed for coding-capable agents and CLIs (Codex/Copilot-style agents, Claude Code, Gemini CLI). It integrates with agents that can run shell tools and spawn sub-agents.

Audit Summary

CoderLM is a CLI tool for recursive LLM-powered file exploration of large codebases, decomposing work into sub-agents with automatic output truncation. The SKILL.md is minimal — just usage and examples — with no actionable procedural steps for an agent to follow. No scripts were bundled, so no execution testing was possible. The concept is valuable but the skill itself reads more like a tool README than a structured agent skill.

Watch Out

Requires coderlm CLI to be installed separately — not bundled
No step-by-step agent instructions, just CLI usage docs

Notes

Thin skill — effectively a pointer to an external CLI tool. Would benefit from structured procedures (e.g. 'when to use', 'how to interpret output', 'fallback strategies'). Architecture doesn't follow skill spec conventions (no scripts/, references/, output contracts).

Information

Repository: coderlm
Stars: 20

Trust Score

Overall71

Security99

Code Quality46

Architecture37

Usefulness64

Related Skills

FastAPI Project Templates

Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.

GraphQL Inspector — Validate

Validate GraphQL operations against a schema with configurable depth, complexity, alias and directive limits to catch errors before runtime.

Chinese Software Copyright Application

Generate complete Chinese software copyright application materials (application form, code documentation, user manual, design docs) and export them to PDF from

JJ Hunk

Programmatic hunk selection for Jujutsu (jj): list, split, commit, or squash specific hunks to enable partial commits and fine-grained history editing without a

Codex Collab

Bridge Claude and Codex to run tasks, perform code reviews, and run background jobs for research or implementation workflows.

Cursor Hello World Tutorial

A concise 10-minute hands-on tutorial demonstrating Cursor's Tab completion, Chat, Inline Edit, and Composer features for getting started quickly.

Code Spec Backfill

Identify missing function-level contracts and backfill docstrings and type annotations; report ambiguous gaps with misuse scenarios. Incremental, state-driven w

LAP CLI

CLI for compiling, searching, and managing API specifications into a compact agent-native format and generating/installing skills from specs.

Back to Skills