affaan-m/ecc

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/affaan-m/ecc --skill agent-eval

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Agent Eval 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 Activate

  • 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:

yaml
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

MetricWhat It Measures
Pass rateDid the agent produce code that passes the judge?
CostAPI spend per task (when available)
TimeWall-clock seconds to completion
ConsistencyPass rate across repeated runs (e.g., 3/3 = 100%)

Workflow

1. Define Tasks

Create a tasks/ directory with YAML files, one per task:

bash
mkdir tasks
# Write task definitions (see template above)

2. Run Agents

Execute agents against your tasks:

bash
agent-eval run --task tasks/add-retry-logic.yaml --agent claude-code --agent aider --runs 3

Each run:

  1. Creates a fresh git worktree from the specified commit
  2. Hands the prompt to the agent
  3. Runs the judge criteria
  4. Records pass/fail, cost, and time

3. Compare Results

Generate a comparison report:

bash
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)

yaml
judge:
  - type: pytest
    command: pytest tests/ -v
  - type: command
    command: npm run build

Pattern-Based

yaml
judge:
  - type: grep
    pattern: "class.*Retry"
    files: src/**/*.py

Model-Based (LLM-as-judge)

yaml
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

タスクに関連する項目

同じリポジトリから

関連する Skills

すべての Skills
affaan-m
コミュニティ

rust-testing

Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology. Use when writing Rust tests — unit, integration, async, property-based, or coverage.

24時間の導入数
489
GitHub Stars
30.8万
更新日
11月20日
affaan-m
コミュニティ

search-first

Research-before-coding workflow: search npm/PyPI, MCP servers, skills, and GitHub for existing tools before writing custom code, then adopt, extend, or build. Launches the researcher agent for non-trivial needs. Use when starting a feature, adding a dependency or integration, or about to write a utility that may already exist.

1時間の導入数
5
GitHub Stars
30.8万
更新日
11月20日
affaan-m
コミュニティ

browser-qa

Run automated post-deploy UI verification with a browser automation MCP (claude-in-chrome, Playwright, or Puppeteer): console-error and Core Web Vitals smoke checks, form and auth-flow interaction tests, screenshot visual regression across three breakpoints, and axe-core accessibility audits ending in a SHIP / DO-NOT-SHIP verdict. Use when testing a deployed feature on staging or preview, before shipping frontend changes, reviewing a frontend PR, or checking responsive layout and accessibility.

1時間の導入数
2
GitHub Stars
30.8万
更新日
11月20日
affaan-m
コミュニティ

docker-patterns

Docker and Docker Compose patterns for local development, hardened CLI installer harnesses, container security, networking, volumes, and multi-service orchestration. Use when creating or reviewing Dockerfiles and Compose services, testing installers across Linux distributions, or planning accurate native macOS and Windows validation.

1時間の導入数
2
GitHub Stars
30.8万
更新日
11月20日