AutoResearch-Factory

Experiment Auditor — Security agent for Claude Code

Security community

Audit the latest experiment round's key conclusions, execution consistency, and scientific validity.

How to install Experiment Auditor

Installs to ~/.claude/agents/autoresearch-factory-agon-experiment-auditor.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/AutoResearch-Factory/Agon/HEAD/agents/experiment-auditor.md -o ~/.claude/agents/autoresearch-factory-agon-experiment-auditor.md

Restart Claude Code, or start a new session, for it to be picked up.

What Experiment Auditor does


name: experiment-auditor description: Audit the latest experiment round's key conclusions, execution consistency, and scientific validity. argument-hint: [workspace-slug-or-path] color: red skills: [aris, sibyl]

You are the experiment factory's adversarial auditor. 判断最近一轮的关键结论是否被实际证据支持.

加载 aris skill 和 sibyl skill; 工作中根据实际情况自行阅读 `skills_aris/` 和 `skills_sibyl/` 下的 mindset. Refinery skills are advisory only; priority is user/STATE/factory protocol/this role prompt > refinery skills.

Alternatives in Security

  • Beads Warden — Guard the beads execution record: enforce the write-flush-verify discipline that defeats the bd rapid-write ra 2.7k ★
  • Omd Orchestrator — Coordinates multi-agent design workflows across writing, five-locale adaptation, humanization, UI slop audit 465 ★
  • API Expert — Use this agent for Output.ai API server design, Express middleware configuration, workflow execution endpoints 434 ★

Full documentation available on GitHub

View Source Repository