Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
Data sourced from ClawHub. View on ClawSkills
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install agent-evalOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install agent-evalβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/agent-eval/π‘Extract and place the folder at the path above, then restart your agent.
What agent-eval can do for your AI workflow
Head-to-head comparison directly from your Claude conversation
Native Claude integration via the open Model Context Protocol (MCP)
One-command installation β no complex setup required
Combine with other skills to build powerful multi-step AI workflows
Try these prompts with your AI agent after installing agent-eval
Help me get started with agent-eval
Explains what agent-eval does, walks through the setup, and runs a quick demo based on your current project
Use agent-eval to head-to-head comparison of coding agents (Claude Code, Aider, Codex...
Invokes agent-eval with the right parameters and returns the result directly in the conversation
What can I do with agent-eval in my ai agent workflow?
Lists the top use cases for agent-eval, with example commands for each scenario
Guides & tutorials for AI skills
10 Fresh GitHub Agent Skills Added in June 2026
A hand-checked shortlist of recently updated GitHub agent skills that were not already in our catalog, excluding marketplaces, awesome lists, managers, and generic skill directories.
The 7 AI Skills Every Software Developer Should Have Installed in 2026
After testing dozens of developer-focused AI skills, these are the seven that have proven genuinely useful across different tech stacks and workflows β not just impressive demos, but tools that hold up under daily use.
agent-eval extends your AI assistant with the ability to head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Rather than leaving your conversation to handle this manually, you can ask your Claude agent directly β and it will take care of the task end-to-end, using agent-eval as its underlying capability.
agent-eval integrates with Claude through the Model Context Protocol (MCP) standard. The skill is version-controlled and shareable β if you work with a team, you can commit the skill to your project repo and everyone gets the same capability without any extra setup.
Getting started with agent-eval takes about two minutes. Place the skill at `~/.claude/skills/agent-eval/` (personal, all projects) or `.claude/skills/agent-eval/` (project-specific), then restart your AI client. From that point, typing `/agent-eval` in any conversation activates it, or the AI will use it on its own when it detects a relevant request.
agent-eval is a community-contributed AI productivity skill available through DiscoverAISkills. Like all skills on DiscoverAISkills, it is free to install and use. The broader AI skills ecosystem continues to expand as developers contribute new capabilities across categories like developer tools, data analysis, writing, automation, and more.
Place the skill folder at ~/.claude/skills/agent-eval/ for personal use (all projects), or .claude/skills/agent-eval/ for project-specific use. Restart your AI client, then invoke with /agent-eval or let the AI discover it automatically.
agent-eval supports Claude. It integrates seamlessly with these AI platforms to extend their capabilities.
agent-eval is free to install. Check the repository for licensing information.
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
Platforms
Automate my ai agent tasks using agent-eval
Identifies repetitive steps in your workflow and sets up agent-eval to handle them automatically
Agent Phone Call gives every AI agent a phone number and the ability to get things done over the phone β finding contacts, making calls, and completing tasks...