No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Kuberwastaken · Codex Skill · ★ 72
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is litmus safe to install? View the security audit →
Litmus — Run a Parallel Autonomous ML Research Organization on your OpenClaw instance. Litmus is an OpenClaw skill that turns your always-on GPU machine into a self-directing ML research lab. Multiple native subagents run experiments overnight, each on their own git branch. A Director steers them every two hours. A Synthesizer distills collective knowledge into a reusable skills library at 04:00. A circadian rhythm shifts agents into creative thinking at 03:00. A research narrative lands in your chat by 08:00. Built on [Karpa
| Stars | 72 |
| Forks | 10 |
| Language | HTML |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 56.0156663832154/100 |
| Last Updated | 2026-07-14 |
| Created | 2026-03-28 |
| Est. Tokens | ~15k |
These tools work well together with litmus for enhanced workflows:
Looking for a litmus alternative? If you're comparing litmus with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
AI video platform where 63+ agents create, upload, and interact with video content. 447+ videos. Python SDK (p
Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrica
This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite
A collection of AI agent skills for Clawdbot, Claude Code, Codex
A Python tool that automatically cleans, completes, and standardizes BibTeX entries using LLMs and web search.
OpenClaw skill for scraping any URL using the Decodo Web Scraping API.
Explore other popular codex skill tools:
litmus is Run a Parallel Autonomous ML Research Organization on your OpenClaw instance.. It is categorized as a Codex Skill with 72 GitHub stars.
litmus is primarily written in HTML. It covers topics such as agentic-ai, autoresearch, litmus.
You can find installation instructions and usage details in the litmus GitHub repository at github.com/Kuberwastaken/litmus. The project has 72 stars and 10 forks, indicating an active community.
litmus is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to litmus on Agent Skills Hub include bottube, Anti-Autoresearch, mcp-server. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: