Finding Validator — Development agent for Claude Code
Adversarial validation agent that attempts to disprove blocking findings from code review.
How to install Finding Validator
Installs to ~/.claude/agents/haacked-review-code-finding-validator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/haacked/review-code/HEAD/agents/finding-validator.md -o ~/.claude/agents/haacked-review-code-finding-validator.md Restart Claude Code, or start a new session, for it to be picked up.
What Finding Validator does
name: finding-validator description: "Adversarial validation agent that attempts to disprove blocking findings from code review. Receives a finding and the code, then tries to construct the strongest argument that the finding is wrong, theoretical, or not a real issue." model: opus color: magenta metadata: execution-tier: deep
You are a skeptical senior engineer whose job is to **disprove** a code review finding. Your default posture is that the finding is wrong until proven otherwise
Alternatives in Development
- Civitai Perf Review — Reviews a feature segment in the main Civitai Next.js app (src/) for production performance — N+1 queries, uni 7.2k ★
- Dast Devils Advocate — Adversarial validator for DAST findings 812 ★
- Finding Checker — Blind adversarial checker — given ONLY a finding artifact and its evidence (never the author's reasoning), tri 348 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Discover Critic
Blind adversarial critic for a candidate product direction — decomposes it into ranked falsifiable assumptions
Refute Verifier
Clean-context skeptic that tries to REFUTE each draft finding or claim it is given — verdicts CONFIRMED / REFU
Overfitting Detector
Adversarial reviewer that tries to disprove a strategy's backtest. Use after any backtest or when a result loo
Dr Verifier
Deep-review verify pass. Takes a batch of deduplicated candidate findings and adversarially tries to disprove
Adversarial Breaker
Actively tries to break the app — wrong inputs, unexpected sequences, auth bypasses, race conditions, state co
Answer Critic
Adversarially attacks one mock-interview answer - tries to prove it wrong, vague, or unsupported. Spawned by /
Related Skills
Steelman
Construct the strongest version of a position before disagreeing
Code Audit
Adversarial code review tree. Wraps /cc-tree:tree with the code-audit preset preselected — finds security / pe
Exploitation Validator
A prompt-based pipeline for finding, validating, and proving vulnerabilities using LLM sub-agents.
