White Hat — Development agent for Claude Code
Objective fact-finder who finds code first, theories second.
How to install White Hat
Installs to ~/.claude/agents/bjcoombs-ai-native-toolkit-white-hat.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/bjcoombs/ai-native-toolkit/HEAD/agents/white-hat.md -o ~/.claude/agents/bjcoombs-ai-native-toolkit-white-hat.md Restart Claude Code, or start a new session, for it to be picked up.
What White Hat does
name: white-hat description: Objective fact-finder who finds code first, theories second. Verifies claims with evidence. model: inherit color: cyan
Apply White Hat methodology - objective facts, evidence, and verified claims.
When operating within a team meeting, your professional lens shapes what you investigate; this method shapes how. When operating standalone, you are both the lens and the method.
Not My Job
- Critical judgement (Black Hat)
- Emotional reactions (Red Hat)
- Cr
Alternatives in Development
- Review Fact Checker — Verify every factual claim in a review draft against vault sources 4.6k ★
- Executioner — Optional Sanhedrin fallback verifier 632 ★
- Brand Logo Finder — Finds brand logos using Brandfetch 395 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Source Checker
Independent fact-checker for a report's references. Verifies that each reference is reachable, that its biblio
Fact Finder
Answers one factual question from the code, the docs, memory, or the web, with file and line evidence, so an i
Note Researcher
Take notes worker — researches one atomic note against the library: finds the passages that state or support i
PR Message Reviewer
Expert PR message reviewer from a maintainer's perspective. Use PROACTIVELY when a PR message has been drafted
Green Hat
Creative problem-solving across the full complexity spectrum. Finds solutions nobody proposed.
Product Innovation
Finds materially better ways to satisfy the underlying objective, beyond what was asked. Leaf agent.
Related Skills
Logo Finder Skill
Logo finder skill for Claude and other AI agents (open Agent Skills standard) — finds the current official com
Evidence Quality Rules
Governs how to treat vague, unquantified, or unsourced claims in any research data used across Country Finder
Twin Sparrow Grounded Collaboration
Multi-agent collaboration discipline: claims must carry evidence, requests must be read for their object befor