Compare Coding Agents
Get data-driven comparisons of coding agents on your own tasks with pass rate, cost, time, and consistency metrics. It runs isolated tests on your codebase using YAML task definitions and git worktrees for reproducible results.
affaan-m on GitHub
Curated by PromptsEdge from a public repo · MIT license. All credit goes to the author.
What is this skill?
A lightweight CLI tool for comparing coding agents head-to-head on reproducible tasks. Every "which coding agent is best?" comparison runs on vibes — this tool systematizes it.
When to use
- Comparing coding agents (Claude Code, Aider, Codex, etc.) on your own codebase
- Measuring agent performance before adopting a new tool or model
- Running regression checks when an agent updates its model or tooling
- Producing data-backed agent selection decisions for a team
Installation
Note: Install agent-eval from its repository after reviewing the source.
Core Concepts
YAML Task Definitions
Define tasks declaratively. Each task specifies what to do, which files to touch, and how to judge success:
name: add-retry-logic
description: Add exponential backoff retry to the HTTP client
repo: ./my-project
files:
- src/http_client.py
prompt: |
Add retry logic with exponential backoff to all HTTP requests.
Max 3 retries. Initial delay 1s, max delay 30s.
judge:
- type: pytest
command: pytest tests/test_http_client.py -v
- type: grep
pattern: "exponential_backoff|retry"
files: src/http_client.py
commit: "abc1234" # pin to specific commit for reproducibility
Git Worktree Isolation
Each agent run gets its own git worktree — no Docker required. This provides reproducibility isolation so agents cannot interfere with each other or corrupt the base repo.
Metrics Collected
| Metric | What It Measures |
|---|---|
| Pass rate | Did the agent produce code that passes the judge? |
| Cost | API spend per task (when available) |
| Time | Wall-clock seconds to completion |
| Consistency | Pass rate across repeated runs (e.g., 3/3 = 100%) |
Workflow
1. Define Tasks
Create a tasks/ directory with YAML files, one per task:
mkdir tasks
# Write task definitions (see template above)
2. Run Agents
Execute agents against your tasks:
agent-eval run --task tasks/add-retry-logic.yaml --agent claude-code --agent aider --runs 3
Each run:
- Creates a fresh git worktree from the specified commit
- Hands the prompt to the agent
- Runs the judge criteria
- Records pass/fail, cost, and time
3. Compare Results
Generate a comparison report:
agent-eval report --format table
Task: add-retry-logic (3 runs each)
┌──────────────┬───────────┬────────┬────────┬─────────────┐
│ Agent │ Pass Rate │ Cost │ Time │ Consistency │
├──────────────┼───────────┼────────┼────────┼─────────────┤
│ claude-code │ 3/3 │ $0.12 │ 45s │ 100% │
│ aider │ 2/3 │ $0.08 │ 38s │ 67% │
└──────────────┴───────────┴────────┴────────┴─────────────┘
Judge Types
Code-Based (deterministic)
judge:
- type: pytest
command: pytest tests/ -v
- type: command
command: npm run build
Pattern-Based
judge:
- type: grep
pattern: "class.*Retry"
files: src/**/*.py
Model-Based (LLM-as-judge)
judge:
- type: llm
prompt: |
Does this implementation correctly handle exponential backoff?
Check for: max retries, increasing delays, jitter.
Best Practices
- Start with 3-5 tasks that represent your real workload, not toy examples
- Run at least 3 trials per agent to capture variance — agents are non-deterministic
- Pin the commit in your task YAML so results are reproducible across days/weeks
- Include at least one deterministic judge (tests, build) per task — LLM judges add noise
- Track cost alongside pass rate — a 95% agent at 10x the cost may not be the right choice
- Version your task definitions — they are test fixtures, treat them as code
Links
- Repository: github.com/joaquinhuigomez/agent-eval
Install this skill
- 1
Get the skill — it’s free
Use the Get this skill panel. Unlocked skills stay in My skills. - 2
Download or clone the files
Download the zip, or clone the repo and copy theskills/agent-evalfolder. - 3
Put it where your agent looks for skills
For Claude Code, use your personal skills folder (every project) or a project’s own folder:~/.claude/skills/agent-eval/SKILL.md # all projects .claude/skills/agent-eval/SKILL.md # this project only
- 4
Just ask
No command needed. The agent reads the skill’s description and loads it on its own when your request matches.
SKILL.md frontmatter
What your agent reads to decide when to load this skill.
--- name: agent-eval description: Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression. ---
Files
Open any Markdown file to read it here.
Related skills
View all →- Create and Improve SkillsFreeYour AI helps you create new skills or improve existing ones by drafting, testing, evaluating, and rewriting them. It runs test prompts, analyzes results quantitatively and qualitatively, and guides you through iterative refinement.
- Create and Evaluate SkillsFreeTurn manual workflows into agent skills, improve existing skills, or evaluate their quality. Your AI guides you through skill creation, benchmarking, and targeted improvements using best-practice patterns.
- Audit Workspace CapabilitiesFreeYour AI audits your repo, servers, plugins, and environment to reveal current capabilities and recommend next steps. It identifies available skills, hooks, agents, and missing integrations without exposing secrets.
- Verify Claude Code SessionsFreeYour AI runs a multi-step verification for Claude Code projects before completion. It checks builds, types, linting, tests, security scans, and code diffs to ensure quality and readiness for pull requests.