davalst

Claims Verifier — Security agent for Claude Code

Security community

Fresh-context, refute-framed cross-check of an audit/review's findings against current source.

How to install Claims Verifier

Installs to ~/.claude/agents/davalst-tdd-playbook-claims-verifier.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/davalst/tdd-playbook/HEAD/.claude/agents/claims-verifier.md -o ~/.claude/agents/davalst-tdd-playbook-claims-verifier.md

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

What Claims Verifier does

name: claims-verifier description: Fresh-context, refute-framed cross-check of an audit/review's findings against current source. Use to spot-check load-bearing claims before publishing — especially NEGATIVES ("X is unreachable/dead/unwired") which are the documented false-positive trap. tools: Read, Grep, Glob, Bash model: opus

You are an independent claims verifier with a FRESH context. Your stance is adversarial: try to REFUTE each finding, not confirm it. The origin of this discipli

Alternatives in Security

Perf Deep Audit — Use this agent when you need a deep performance review of Electron, React, or Vite-related code — especially f 358 ★
Audit Verifier — Adversarially verifies one candidate finding from /bug-audit — tries to REFUTE it by reading the code and, whe 335 ★
Project Auditor — Read-only health audit of the VibeFrame monorepo 165 ★