Coderlm

Turns codex/gemini/claude into a recursive agent with bundled bash output truncation guard

Tested · Didn't pass

Test report

Verdict
Tested · Didn't pass
Tested
Jul 20, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 30, 2026 · 0aa2b6d

This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 20, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

The skill is only a doc wrapper around a separate `coderlm` binary that ships via npm/pypi and is not installed by copying the skill, and its recursive runs also need a coding-agent CLI plus API keys, so the headline divide-and-conquer benefit could not be measured here. The one bundled feature I could run live, the bashrlm.sh guard, does truncate a 1892-char flood down to a 200-char head+tail preview as advertised. But its documented redirect-aware bypass is broken on macOS: `cat big > out.txt` wrote only 266 of 1892 chars with a TRUNCATED marker leaked into the saved file, because the check relies on Linux-only /proc/self/fd/1. Useful concept, but real setup friction and a data-corrupting bug on this platform.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 4/10
  • Docs & honesty 3/5

What Coderlm does

Wraps a coding-agent CLI (codex, gemini, or claude) in a recursive divide-and-conquer harness for tasks that span many files, and ships bashrlm context guards that auto-truncate high-output shell commands. Triggers when a task involves >10 files, exceeds a comfortable context window, or benefits from decomposition into sub-agents.

How to install Coderlm

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Coderlm

  • /coderlm Turns codex/gemini/claude into a recursive agent with bundled bash output truncation guard

It also activates on plain-language prompts like these:

  • This refactor spans over 15 files, break it into sub-agent tasks
  • Run this codex task recursively and truncate the noisy bash output
  • Divide and conquer this large migration across multiple agents

Frequently asked questions

Is the Coderlm skill free?
Yes. The skill itself is free from CyrusNuevoDia/coderlm. SkillProof publishes the install command and an independent test verdict at no cost.
Does Coderlm work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 20, 2026. Verdict: Tested · Didn't pass. The skill is only a doc wrapper around a separate `coderlm` binary that ships via npm/pypi and is not installed by copying the skill, and its recursive runs also need a coding-agent CLI plus API keys, so the headline divide-and-conquer benefit could not be measured here. The one bundled feature I could run live, the bashrlm.sh guard, does truncate a 1892-char flood down to a 200-char head+tail preview as advertised. But its documented redirect-aware bypass is broken on macOS: `cat big > out.txt` wrote only 266 of 1892 chars with a TRUNCATED marker leaked into the saved file, because the check relies on Linux-only /proc/self/fd/1. Useful concept, but real setup friction and a data-corrupting bug on this platform.
How do I install Coderlm?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Coderlm with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.