Description
agent-eval is an agent skill from ECC, Affaan Mustafa's open-source agentic engineering toolkit, listed on skills.sh. It compares coding agents such as Claude Code, Aider and Codex head to head on reproducible tasks defined in YAML, so choosing an agent or model rests on data. 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
- Head-to-head agent comparison
- YAML task definitions
- Regression checks after model updates
Ratings & Reviews
No ratings yet
Be the first to rate agent-eval.
People also visit
agent-eval FAQ
What does the agent-eval skill do?
It compares coding agents such as Claude Code, Aider and Codex head to head on reproducible tasks defined in YAML, so choosing an agent or model rests on data.
How do I install the agent-eval skill?
Run: npx skills add https://github.com/affaan-m/ecc --skill agent-eval
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-eval alternatives?
Popular alternatives to agent-eval include agent-architecture-audit, agent-introspection-debugging and agent-payment-x402. See all agent-eval alternatives