agentmods.dev

RLM: Instructions file for Claude Code

CLAUDE.md

RLM CLAUDE.md is an instructions file for Claude Code from brainqub3/RLM. It costs 1,141 tokens per session, scanned A, original, MIT.

A project guide for a repository that provides a non-interactive Codex command and a Recursive Language Model setup for handling long tasks.

In plain words
What is it for?
Running Codex without interaction, passing prompts or input through the command line, using the long-context RLM mode, and locating results from oolong evaluations.
Why use it?
It tells coding agents how to invoke the repository's headless Codex runner and where to find its long-context workflow and experiment artifacts.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is brainqub3/RLM's own configuration. It tells Claude Code how to work on RLM itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RLM configures →

not rated 393repo 4mo ago A scan 1,141 tokens original MIT
View source ↗ brainqub3/RLM
Reuse

Borrowing it

Nothing to install: this file belongs to brainqub3/RLM. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/brainqub3/RLM/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/brainqub3/RLM

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for RLM CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/brainqub3/rlm/claude-md/github.svg)](https://agentmods.dev/instructions/brainqub3/rlm/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/brainqub3/rlm/claude-md"><img src="https://agentmods.dev/badge/instructions/brainqub3/rlm/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for RLM CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/brainqub3/rlm/claude-md"><img src="https://agentmods.dev/badge/instructions/brainqub3/rlm/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,141 This file is loaded in full into every session.
When invoked 1,141 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01141 $0.01141
Opus 5.5 $0.00456 $0.00456
Sonnet 5.5 $0.00228 $0.00228
Haiku 4.5 $0.00114 $0.00114

Measured 2mo ago against content hash c42b5f7f3d3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

RLM CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project instructions

Headless Codex sub-agent

This repo exposes a root-level headless Codex command for agents that need a non-interactive Codex pass:

./codex-headless "review the current repo and list the highest-risk files"

On Windows shells, use either:

.\codex-headless.ps1 "review the current repo and list the highest-risk files"
.\codex-headless.cmd "review the current repo and list the highest-risk files"

The wrapper runs codex exec from the repo root with gpt-5.5, model_reasoning_effort="xhigh", --sandbox workspace-write, approval_policy="never", and --ephemeral. It preserves normal codex exec behavior, so callers can pass a prompt argument, pipe stdin, add flags such as --json, or use -o <file> for the final message. It requires the Codex CLI on PATH and an existing codex login or CODEX_API_KEY scoped to the invocation.

RLM mode for long-context tasks

This repository includes a faithful "Recursive Language Model" (RLM) setup for Claude Code (after Recursive Language Models, arXiv:2512.24601, Algorithm 1):

  • Skill: rlm in .claude/skills/rlm/
  • Persistent Python REPL: .claude/skills/rlm/scripts/rlm_repl.py — holds the large context as a variable and exposes llm_query / llm_query_map / rlm_query and FINAL / FINAL_VAR.
  • Sub-LM (llm_query): a nested headless Claude Code (claude -p, tools off, default model haiku), called programmatically from REPL code — not a Task subagent. The recursive rlm_query runs claude -p with bash + this skill on.

When the user needs you to work over a context that is too large to paste into chat:

  1. Ask for (or locate) a context file path.
  2. Run the /rlm Skill and follow its procedure.

Keep the main conversation light: the root model never reads the full context — it writes REPL code that sub-queries the context in chunks, then synthesises. Use python (not python3) to invoke the REPL on this machine.

OOLONG eval — where run artifacts go

Read the full file on GitHub · 87 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 87 lines · 1,141 tokens per session scan A c42b5f7f3d3a

Subscribe to this mod's changes

RLM CLAUDE.md is an instructions file published in the GitHub repository brainqub3/RLM (393 stars, last pushed 4mo ago), licensed MIT. It adds 1,141 tokens to every session, about $0.0046 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents
Related

RLM CLAUDE.md compared with instructions from other repositories

RLM CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
RLM CLAUDE.mdbrainqub3/RLMInstructions file3934mo agoMITA1,141Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode