Overview
agent-evaluation is an open-source workflow skill for Claude Code and compatible agents, published by sickn33. Its author describes it as: “Evaluate agent behavior with versioned cases and explicit verifiers. Use when comparing agent or prompt changes, reproducing failures, or running agent regression tests.”. The project has 47k stars on GitHub and is available under the MIT license. Add it to your setup with `/plugin marketplace add sickn33/agentic-awesome-skills`.
What agent-evaluation does
Evaluate observable agent behavior against task-specific cases. Modified by AAS maintainers on 2026-09-05 to remove unsupported benchmark claims, correct uncertainty/error reporting and separate optional architecture sketches from the operating procedure.
Best for
What’s inside
The SKILL.md for agent-evaluation is organised into these sections:
- When to Use
- Prerequisites
- Evaluation procedure
- Example: changed tool argument handling
- Worked uncertainty example
- Optional architecture patterns
- Limitations
Installation
Add agent-evaluation to your agent with:
/plugin marketplace add sickn33/agentic-awesome-skillsReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — ships a claude code plugin marketplace
- Codex — declared in the repository topics
- Cursor — declared in the repository topics
- Gemini CLI — declared in the repository topics
- Antigravity — declared in the repository topics
License
agent-evaluation is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in sickn33/agentic-awesome-skills, an established project with 46,693 GitHub stars
- Works with Claude Code, Codex, Cursor, Gemini CLI, Antigravity
- Actively maintained — repository updated in the last 30 days
- Its repository gained 2,482 GitHub stars over the last 52 days
Author
Topics
Frequently asked questions
- What does agent-evaluation do?
- Evaluate agent behavior with versioned cases and explicit verifiers. Use when comparing agent or prompt changes, reproducing failures, or running agent regression tests.
- How do I install agent-evaluation?
- Run /plugin marketplace add sickn33/agentic-awesome-skills in your agent, then reload your skills. Review the source at https://github.com/sickn33/agentic-awesome-skills before installing.
- Is agent-evaluation free to use?
- Yes. agent-evaluation is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does agent-evaluation work with?
- agent-evaluation lists Claude Code, Codex, Cursor, Gemini CLI, and Antigravity — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does agent-evaluation come from?
- agent-evaluation ships inside sickn33/agentic-awesome-skills, a repository that contains 70 catalogued skills in total. The repository's 46,693 GitHub stars apply to that whole collection, not to this skill on its own.