wyeworks

Claim Falsifier — Research agent for Claude Code

Research community

Adversarial verifier for one analysis note of a review-map run.

How to install Claim Falsifier

Installs to ~/.claude/agents/wyeworks-accountable-review-claim-falsifier.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/wyeworks/accountable-review/HEAD/agents/claim-falsifier.md -o ~/.claude/agents/wyeworks-accountable-review-claim-falsifier.md

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

What Claim Falsifier does

name: claim-falsifier description: Adversarial verifier for one analysis note of a review-map run. Assumes the note contains wrong assumptions, missed consumers and false simplifications, and hunts the repository for evidence that contradicts it. Produces no competing explanation and rewrites nothing. Driven by /accountable-review:review-map at --effort high, one instance per note, before any page is written. tools: Read, Grep, Glob, Bash disallowedTools: Write, Edit model: sonnet

Cla

Alternatives in Research

  • Hooks: — You are a GSD codebase mapper 38.5k ★
  • Improve Agent — Systematic improvement of existing agents through performance analysis, prompt engineering, and cont 31.9k ★
  • Council Sun Tzu — Council member 4.2k ★

Full documentation available on GitHub

View Source Repository

Related Agents

Research Verifier — Research agent for Claude Code

Research Verifier

Independently checks the load-bearing claims in a /research note against their cited sources and returns a ver

Research community
Story Verifier — Research agent for Claude Code

Story Verifier

Independently verifies a built infographic against explicit acceptance criteria, direct artifact evidence, ide

Research community
Loki — Research agent for Claude Code

Loki

Devil's advocate that challenges assumptions, stress-tests designs, finds edge cases, and performs adversarial

Research community
Paper Writer — Research agent for Claude Code

Paper Writer

Scientific writing specialist for research papers — argument structure, claim-evidence chains, narrative arc

Research community
Research Retriever — Research agent for Claude Code

Research Retriever

Retrieve RKC research context without contaminating the parent. Use for ResearchQuestion, Finding, Claim, Evid

Research community
Baksa — Research agent for Claude Code

Baksa

Adversarial PhD reviewer that challenges Jogyo's research claims and verifies evidence

Research community

Related Skills

Cmd Judge — Development skill for Claude Code

Cmd Judge

Adversarial verifier for the PROVE phase: treats a finished-work report as untrusted claims, re-runs every ver

Development community
Bearing — AI skill for Claude Code

Bearing

An intel layer for AI coding agents that assumes its own rules might be wrong — and keeps the evidence. Author

AI community
Claude Code Discipline Skills — AI skill for Claude Code

Claude Code Discipline Skills

Seven Claude Code skills that stop an LLM agent asserting what it has not measured. Each born from a dated pro

AI community