andyed

Rigor Audit — Security agent for Claude Code

Security community

Review research artifacts for scientific rigor before they're committed or pushed.

How to install Rigor Audit

Installs to ~/.claude/agents/andyed-science-agent-rigor-audit.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/andyed/science-agent/HEAD/agents/rigor-audit.md -o ~/.claude/agents/andyed-science-agent-rigor-audit.md

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

What Rigor Audit does

name: rigor-audit description: Review research artifacts for scientific rigor before they're committed or pushed. Catches framing errors (nulls as detection limits, p-values without effect+CI, undefined metrics), unsupported claims, and presentation problems. Sibling to citation-audit (which checks citation structure) and the planned claim-audit (semantic claim correctness). tools:

  • Read
  • Glob
  • Grep
  • Bash
  • WebSearch
  • WebFetch

Science Audit Agent

You are a skeptical

Alternatives in Security

  • Token Auditor — Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces d 79.4k ★
  • Malware Analyst — You are an elite malware analyst focused on defensive security research 31.9k ★
  • JS Error Handler Auditor — Use this agent when you need to audit a JavaScript codebase for unhandled errors in top-level async operations 6.1k ★

Full documentation available on GitHub

View Source Repository

Related Agents

Synthesis Reviewer — Security agent for Claude Code

Synthesis Reviewer

Audit draft reports for internal contradictions, unsupported claims, missing context, and citation integrity.

Security community
Verification Auditor — Security agent for Claude Code

Verification Auditor

Verification auditor that checks every agent's claims against the actual codebase. Runs twice — once after imp

Security community
Style Reviewer — Security agent for Claude Code

Style Reviewer

Audit draft reports for clarity, accessibility, and plain-language style without changing meaning or weakening

Security community
Adversary — Security agent for Claude Code

Adversary

Pre-implementation red-team analysis. Challenges plans BEFORE code is written — edge cases, security holes, sc

Security community
Fix-Diff Reviewer — Security agent for Claude Code

Fix-Diff Reviewer

You are the fix-diff reviewer for an audit round that has just committed its fixes. You are NOT a specialist a

Security community
Gan Reviewer Independent — Security agent for Claude Code

Gan Reviewer Independent

Independent code reviewer that judges a sprint's committed diff cold, with fresh context and no sight of the s

Security community

Related Skills

Global Blocks — AI skill for Claude Code

Global Blocks

Claims that survive crossing a boundary — addressable, versioned, hash-chained blocks for AI agents; portals n

AI community
Paper Critic — Development skill for Claude Code

Paper Critic

Scientifically critique a paragraph, section, or claim in the current scientific manuscript for rigor and clai

Development community
Academic Paper Accuracy And Citation Audit — Security skill for Claude Code

Academic Paper Accuracy And Citation Audit

Use when: (1) performing a multi-pass LaTeX paper audit covering data consistency, cross-references, scientifi

Security community