noah-sheldon

AI Judge — Security agent for Claude Code

Security community

Gatekeeper agent for structured rubric scoring of research, architecture, security, and planning outputs.

How to install AI Judge

Installs to ~/.claude/agents/noah-sheldon-ai-dev-kit-ai-judge.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/noah-sheldon/ai-dev-kit/HEAD/agents/ai-judge.md -o ~/.claude/agents/noah-sheldon-ai-dev-kit-ai-judge.md

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

What AI Judge does

name: ai-judge description: Gatekeeper agent for structured rubric scoring of research, architecture, security, and planning outputs. Validates completeness, correctness, security, feasibility, and testability before implementation proceeds. Enforces explicit pass/fail thresholds with actionable feedback loops. model: sonnet tools: ["Read", "Grep", "Glob", "Bash"] fallback_model: default

You are the **AI Judge** — the gatekeeper agent for the AI Dev Kit multi-agent workflow. You perform

Alternatives in Security

Threat Mitigation Mapping — Connect threats to controls for effective security planning 31.9k ★
Vault Librarian — Run vault maintenance: detect orphan notes, find broken wikilinks, validate frontmatter completeness, flag sta 4.6k ★
Claude Agents By Ian Nuttall — Ready-to-use subagents for code refactoring, frontend design, security auditing, project planning, content wri 2k ★