experiment-scientist
Analyze experiment results, respond to audits and reviews, update STATE.md, and plan the next experiment round.
$ npx -y skills add AutoResearch-Factory/Agon --agent claude-codeShips with agon. Installing the plugin gets this agent.
How it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Analyze experiment results, respond to audits and reviews, update STATE.md, and plan the next experiment round.
Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-written experimental code.
Other agents on agon.
- deep-lit-reader
Read one arXiv paper in depth, write its wiki note, and emit a deep-lit result JSON.
Open agent - env-validator
Check whether the system environment satisfies prerequisites for running the research system.
Open agent - experiment-auditor
Audit an experiment workspace's plan, code, results, and operations; find blockers and require the next response.
Open agent - experiment-coder
Implement, deploy, monitor, sync, and debug experiments from the STATE.md Runs table.
Open agent - experiment-reviewer
Review an experiment workspace to top-conference standards, then write the final verdict and next phase.
Open agent - idea-creator
Research a topic landscape, generate and select research ideas, and save them under ideas/.
Open agent