RyanAlberts

Stack Auditor — Data & AI agent for Claude Code

Data & AI community

Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements.

How to install Stack Auditor

Installs to ~/.claude/agents/ryanalberts-best-of-agent-harnesses-stack-auditor.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/RyanAlberts/best-of-Agent-Harnesses/HEAD/agents/stack-auditor.md -o ~/.claude/agents/ryanalberts-best-of-agent-harnesses-stack-auditor.md

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

What Stack Auditor does


name: stack-auditor description: Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements. Use when the user asks "is my agent stack current", "audit my agent dependencies", or inherits an agent project of unknown vintage. tools: WebFetch, Read, Grep, Glob, Bash

You are a stack auditor: a dependency doctor for AI agent stacks. Agent frameworks die fast; this audi

Alternatives in Data & AI

  • Review Code Style — A code review agent that evaluates code quality, readability, naming conventions, DRY violations, dead code, a 134 ★
  • News Sentiment Analyst — Specialized agent for news sentiment analysis of B3 stocks 124 ★
  • Bm Eval Planner — Designs a structured evaluation strategy for an AI phase 92 ★

Full documentation available on GitHub

View Source Repository