Agent Architecture Audit

by affaan-m

Agent Architecture Audit is an AI Engineering skill for Claude Code, published by affaan-m in ECC.

239.8K stars36.4K forkson affaan-m/ECCAdded 2026/08/13Repository updated 2026/08/12

View source on GitHub Download repo ZIP

ai-agentsanthropicclaudeclaude-codedeveloper-toolsllmmcpproductivity

Install in seconds

Install Agent Architecture Audit

Copy Agent Architecture Audit into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/affaan-m/ECC/tree/main/skills/agent-architecture-audit ~/.claude/skills/agent-architecture-audit

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/affaan-m/ECC.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/agent-architecture-audit/SKILL.md in affaan-m/ECC
Installs to: ~/.claude/skills/agent-architecture-audit
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Agent Architecture Audit does

Agent Architecture Audit diagnoses failures in agent and LLM applications by auditing the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Use it when an agent misbehaves and the failing layer is unknown, or before shipping an agent stack.

Agent Architecture Audit is cataloged under AI Engineering on DirSkills. Agent Architecture Audit comes from a repository tagged ai-agents, anthropic, claude, claude-code and developer-tools.

Documentation

README

Excerpt

Agent Architecture Audit

A diagnostic workflow for agent systems that hide failures behind wrapper layers, stale memory, retry loops, or transport/rendering mutations.

When to Activate

MANDATORY for:

Releasing any agent or LLM-powered application to production
Shipping features with tool calling, memory, or multi-step workflows
Agent behavior degrades after adding wrapper layers
User reports "the agent is getting worse" or "tools are flaky"
Same model works in playground but breaks inside your wrapper
Debugging agent behavior for more than 15 minutes without finding root cause

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Agent Architecture Audit

What else does affaan-m publish alongside Agent Architecture Audit?
Agent Architecture Audit is one of 25 skills that DirSkills catalogs from affaan-m/ECC, the repository it ships in. Its siblings there include AI Regression Testing, AI-First Engineering and API Connector Builder. Each one is a separate skill with its own page in this directory, installs the same way Agent Architecture Audit does, and is maintained by affaan-m in that same repository. The rest of the collection is listed on the affaan-m/ECC page.
How does Agent Architecture Audit compare to other AI Engineering skills?
Agent Architecture Audit ranks #2 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agent Architecture Audit against them. Open each page to compare what they document and how they install.