agon
01Plugin Claude Code
Idea discovery, proposal refinement, experiment execution, and deep literature orchestration.
44 7d ago A
tokens not measured
original MIT
Agent
Read one arXiv paper in depth, write its wiki note, and emit a deep-lit result JSON.
44 7d ago A 26 tokens
original MIT
Agent
Check whether the system environment satisfies prerequisites for running the research system.
44 7d ago A 16 tokens
original MIT
Agent
Audit the latest experiment round's key conclusions, execution consistency, and scientific validity.
44 7d ago A 21 tokens
original MIT
Agent
Implement, deploy, monitor, sync, and debug experiments from the STATE.md Runs table.
44 7d ago A 22 tokens
original MIT
Agent
Review an experiment workspace to top-conference standards, then write the final verdict and next phase.
44 7d ago A 23 tokens
original MIT
Agent
Analyze experiment results, respond to audits and reviews, update STATE.md, and plan the next experiment round.
44 7d ago A 26 tokens
original MIT
Agent
Screen experiment plans before implementation, blocking unnecessary scale and meaningless gates.
44 7d ago A 18 tokens
original MIT
idea-creator
09Agent
Research a topic landscape, generate and select research ideas, and save them under ideas/.
44 7d ago A 21 tokens
original MIT
idea-refiner
10Agent
Improve an existing idea using reviewer feedback and write the next idea version.
44 7d ago A 18 tokens
original MIT
Agent
Review an idea for novelty and quality, write the review, and update its ideas.xml score.
44 7d ago A 23 tokens
original MIT
Agent
Write a proposal from an idea, or revise the latest proposal based on a review.
44 7d ago A 21 tokens
original MIT
Agent
Review a proposal across multiple dimensions, write the review, and update its proposals.xml score.
44 7d ago A 22 tokens
original MIT
Command
Run the scoped deep literature loop until relevant papers are saturated.
44 7d ago A 17 tokens
original MIT
Command
Orchestrate the experiment scientist/screener/coder/auditor/reviewer loop for a workspace.
44 7d ago A 25 tokens
original MIT
idea-tick
16Command
Create or continue ideas from a topic and run create/review/refine/deep-lit to dual-gate saturation.
44 7d ago A 27 tokens
original MIT
Command
Run proposal refine/review/deep-lit loops in parallel until proposals are ready.
44 7d ago A 20 tokens
original MIT
PostToolUse
18Hook
Runs after a tool call finishes, executing settings-change-notify.py via python3. From AutoResearch-Factory/Agon.
44 7d ago A
tokens not measured
original MIT
SessionEnd
19Hook
Runs when a session ends, executing settings-change-notify.py via python3 with --cleanup. From AutoResearch-Factory/Agon.
44 7d ago A
tokens not measured
copy · 64% MIT
aris
20Skill Claude CodeCodex
Research-mindset catalog distilled from ARIS skills, for subagent Read on demand.
44 7d ago A 20 tokens
original MIT
arxiv-tools
21Skill Claude CodeCodex
This skill should be used when the user asks to "search for papers", "get paper info", "download LaTeX source", "generate BibTeX citation", "find citing papers", or provides an arXiv ID or arXiv URL.
44 7d ago A 56 tokens
original MIT
Skill Claude CodeCodex
Use when checking novelty of a research idea or proposal. Extract core claims, do multi-source arxiv / Scholar / S2 search, grade each claim HIGH/MEDIUM/LOW. 基本就是 ARIS novelty-check skill, 但去掉了 cross-model verification 和 report schema.
44 7d ago A 63 tokens
original MIT
Skill Claude CodeCodex
Use when you need project-specific compute/server notes to pick a server or confirm a running task, if the project has filled its server manual or monitoring hooks.
44 7d ago A 34 tokens
original MIT
sibyl
24Skill Claude CodeCodex
Research-persona catalog distilled from Sibyl prompts, for subagent Read on demand. 与 ARIS 互补 — ARIS 按阶段组织, Sibyl 按人格视角组织.
44 7d ago A 43 tokens
original MIT