SarthakDz

OpenMythos Skill — Development skill for Claude Code

Development community

OpenMythos Claude Skill: a lightweight add-on that makes Claude act like a senior engineer who deeply understands Kye Gomez’s PyTorch RDT repo.

How to install OpenMythos Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open SarthakDz/OpenMythos-Skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What OpenMythos Skill does

OpenMythos Claude Skill: a lightweight add-on that makes Claude act like a senior engineer who deeply understands Kye Gomez’s PyTorch RDT repo. It knows architecture, invariants, patterns, and debugging workflows—helping you reason, extend, and troubleshoot without modifying or redistributing the code.

Alternatives in Development

OpenMythos — A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the availabl 14.8k ★
Discuss — Act as a planning interviewer 2.9k ★
MiniCode Architecture — 简体中文 This document describes the lightweight architecture decisions behind mini-code 388 ★

README

OpenMythos-Skill: A Claude Skill for Kye Gomez's OpenMythos Repo

A [Claude skill](https://docs.claude.com) that gives Claude careful, repo-specific knowledge of **OpenMythos** — Kye Gomez's open-source PyTorch reconstruction of a hypothesized Recurrent-Depth Transformer architecture. When this skill is loaded, Claude acts like a senior engineer who has read every line of `open_mythos/main.py`: it knows the architectural invariants, the conventions, the debugging playbook, and the papers the repo cites.

This is a **third-party harness for working with OpenMythos**. It does not modify the OpenMythos codebase, does not redistribute its source, and is not affiliated with either the OpenMythos project or Anthropic.

Credit where it's due

All the substance this skill knows comes from **Kye Gomez**'s work on OpenMythos:

Repo: https://github.com/kyegomez/OpenMythos
Twitter/X: @kyegomezb

If you're going to use this skill, go star and read [the upstream repo](https://github.com/kyegomez/OpenMythos) first. The README there is genuinely one of the better explainers of looped-transformer theory I've read — LTI stability via `A = exp(-exp(...))`, loop-index embedding, ACT halting, Parcae scaling laws, the memorization-reasoning tradeoff, all laid out clearly with citations. This skill is a harness around that content; the content itself is Kye's.

What the skill actually does

When loaded, the skill triggers whenever Claude sees signals that the user is working on OpenMythos: filenames like `open_mythos/main.py`, imports like `from open_mythos.main import OpenMythos, MythosConfig`, symbol names (`MythosConfig`, `RecurrentBlock`, `LTIInjection`, `ACTHalting`, `MoEFFN`, `MLAttention`, `GQAttention`), variant helpers (`mythos_1b` through `mythos_1t`), and debugging symptoms specific to looped training (step-reproducible loss spikes, residual explosion, overthinking dri