Overview
autoresearch-agent is an open-source productivity skill for Claude Code and compatible agents, published by alirezarezvani. Its author describes it as: “Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failure…”. The project has 25k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add alirezarezvani/claude-skills`.
What autoresearch-agent does
> You sleep. The agent experiments. You wake up to results.
What’s inside
The SKILL.md for autoresearch-agent is organised into these sections:
- Slash Commands
- When This Skill Activates
- Setup
- First Time — Create the Experiment
- What Setup Creates
- Domains
- If program.md Already Exists
- Agent Protocol
- Before Starting
- Each Iteration
- What the Script Handles (you don't)
- Starting an Experiment
Installation
Add autoresearch-agent to your agent with:
/plugin marketplace add alirezarezvani/claude-skillsReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — ships a claude code plugin marketplace
- Codex — declared in the repository topics
- Cursor — declared in the repository topics
- Gemini CLI — declared in the repository topics
License
autoresearch-agent is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in alirezarezvani/claude-skills, an established project with 24,617 GitHub stars
- Works with Claude Code, Codex, Cursor, Gemini CLI
- Actively maintained — repository updated in the last 90 days
Author
Topics
Alternatives to autoresearch-agent
Similar skills from other repositories:
Frequently asked questions
- What does autoresearch-agent do?
- Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
- How do I install autoresearch-agent?
- Run /plugin marketplace add alirezarezvani/claude-skills in your agent, then reload your skills. Review the source at https://github.com/alirezarezvani/claude-skills before installing.
- Is autoresearch-agent free to use?
- Yes. autoresearch-agent is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does autoresearch-agent work with?
- autoresearch-agent lists Claude Code, Codex, Cursor, and Gemini CLI — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does autoresearch-agent come from?
- autoresearch-agent ships inside alirezarezvani/claude-skills, a repository that contains 41 catalogued skills in total. The repository's 24,617 GitHub stars apply to that whole collection, not to this skill on its own.
