Description
agent-architecture-audit is an agent skill from ECC, Affaan Mustafa's open-source agentic engineering toolkit, listed on skills.sh. It is a diagnostic workflow for agent and LLM apps whose failures hide behind wrapper layers, stale memory, retry loops or changed output, recommended before releasing any agent to production. A skill is a SKILL.md file of instructions (sometimes with scripts and reference notes) that an AI agent loads only when a task calls for it, so the agent knows the steps to follow and what to avoid. It is free and open source.…
Highlights
- Full-stack agent diagnosis
- Finds wrapper and memory issues
- Pre-release check
Ratings & Reviews
No ratings yet
Be the first to rate agent-architecture-audit.
People also visit
agent-architecture-audit FAQ
What does the agent-architecture-audit skill do?
It is a diagnostic workflow for agent and LLM apps whose failures hide behind wrapper layers, stale memory, retry loops or changed output, recommended before releasing any agent to production.
How do I install the agent-architecture-audit skill?
Run: npx skills add https://github.com/affaan-m/ecc --skill agent-architecture-audit
Is it free?
Yes. It is free and open source.
What is an agent skill?
A SKILL.md file of instructions, sometimes with scripts and reference notes, that an AI agent such as Claude Code loads when a task needs it, so it handles that task the same careful way every time.
Has it been checked for security?
skills.sh lists three audits: Gen Agent Trust Hub Pass, Socket Pass and Snyk Pass. A Warn is worth reading before you install.
What are the best agent-architecture-audit alternatives?
Popular alternatives to agent-architecture-audit include agent-introspection-debugging, agent-eval and agent-payment-x402. See all agent-architecture-audit alternatives