Agent Architecture Audit
Skill ActivePart of:Everything Claude Code
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.
Installation
/plugin install everything-claude-code@affaan-m-everything-claude-codeAwaiting evaluation
Trust Signals
Last commitabout 21 hours ago
GitHub owner affaan-m (opens in new tab)
Stars181k
Downloads 7k (opens in new tab)
LicenseMIT
Websiteecc.tools(opens in new tab)
Status