Agent
Part of agon
Read one arXiv paper in depth, write its wiki note, and emit a deep-lit result JSON.
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.
Agent
Part of agon
Read one arXiv paper in depth, write its wiki note, and emit a deep-lit result JSON.
Agent
Part of agon
Check whether the system environment satisfies prerequisites for running the research system.
Agent
Part of agon
Audit the latest experiment round's key conclusions, execution consistency, and scientific validity.
Agent
Part of agon
Implement, deploy, monitor, sync, and debug experiments from the STATE.md Runs table.
Agent
Part of agon
Review an experiment workspace to top-conference standards, then write the final verdict and next phase.
Agent
Part of agon
Analyze experiment results, respond to audits and reviews, update STATE.md, and plan the next experiment round.
Agent
Part of agon
Screen experiment plans before implementation, blocking unnecessary scale and meaningless gates.
Agent
Part of agon
Research a topic landscape, generate and select research ideas, and save them under ideas/.
Agent
Part of agon
Improve an existing idea using reviewer feedback and write the next idea version.
Agent
Part of agon
Review an idea for novelty and quality, write the review, and update its ideas.xml score.
Agent
Part of agon
Write a proposal from an idea, or revise the latest proposal based on a review.
Agent
Part of agon
Review a proposal across multiple dimensions, write the review, and update its proposals.xml score.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: