affaan-m/ECC/docs/zh-CN/skills/agent-eval/SKILL.md
agent-eval
Use it for engineering tasks; the detail page covers purpose, installation, and practical steps.
- Source repository stars
- 234,327
- Declared platforms
- 2
- Static risk flags
- 1
- Last source update
- 2026-07-27
- Source checked
- 2026-07-28
Decision brief
What it does—and where it fits
一个轻量级 CLI 工具,用于在可复现的任务上对编码代理进行头对头比较。每个“哪个编码代理最好?”的比较都基于感觉——本工具将其系统化。
Not for
- Tasks that require unconfirmed production actions or broad system permissions.
- Environments where the pinned source and install steps cannot be inspected.
Compatibility matrix
Platform support, with evidence labels
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Declared | Source record | Install path and trigger |
| Claude Code | Declared | Source record | Install path and trigger |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
Inspect first. Install second.
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/agent-eval"Inspect the Agent Skill "agent-eval" from https://github.com/affaan-m/ECC/blob/4e973d3eaf92d97f8d2e2d8abb39d8bdc8711b38/docs/zh-CN/skills/agent-eval/SKILL.md at commit 4e973d3eaf92d97f8d2e2d8abb39d8bdc8711b38. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
What the source asks the agent to do
- 01
何时使用
在你自己的代码库上比较编码代理(Claude Code、Aider、Codex 等) 在采用新工具或模型之前衡量代理性能 当代理更新其模型或工具时运行回归检查 为团队做出数据支持的代理选择决策
在你自己的代码库上比较编码代理(Claude Code、Aider、Codex 等)在采用新工具或模型之前衡量代理性能当代理更新其模型或工具时运行回归检查 - 02
安装
Review the “安装” section in the pinned source before continuing.
Review and apply the “安装” source section. - 03
pinned to v0.1.0 — latest stable commit
pip install git+https://github.com/joaquinhuigomez/agent-eval.git@6d062a2f5cda6ea443bf5d458d361892c04e749b yaml name: add-retry-logic description: Add exponential backoff retry to the HTTP client repo: ./my-project files: - src/httpclient.py prompt: | Add retry logic with expone…
src/httpclient.pytype: pytesttype: grep - 04
核心概念
以声明方式定义任务。每个任务指定要做什么、要修改哪些文件以及如何判断成功:
以声明方式定义任务。每个任务指定要做什么、要修改哪些文件以及如何判断成功:每个代理运行都获得自己的 git 工作树——无需 Docker。这提供了可复现的隔离,使得代理之间不会相互干扰或损坏基础仓库。
Permission review
Static risk signals and limitations
Network access
The documentation includes network, browsing, or remote request actions.
pip install git+https://github.com/joaquinhuigomez/agent-eval.git@6d062a2f5cda6ea443bf5d458d361892c04e749bEvidence record
Why each signal appears
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 68/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 234,327 | Source | Repository attention, not individual Skill quality |
| Compatibility | 2 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- affaan-m/ECC
- Skill path
- docs/zh-CN/skills/agent-eval/SKILL.md
- Commit
- 4e973d3eaf92d97f8d2e2d8abb39d8bdc8711b38
- License
- MIT
- Collected
- 2026-07-28
- Default branch
- main
View the original SKILL.md
Agent Eval 技能
一个轻量级 CLI 工具,用于在可复现的任务上对编码代理进行头对头比较。每个“哪个编码代理最好?”的比较都基于感觉——本工具将其系统化。
何时使用
- 在你自己的代码库上比较编码代理(Claude Code、Aider、Codex 等)
- 在采用新工具或模型之前衡量代理性能
- 当代理更新其模型或工具时运行回归检查
- 为团队做出数据支持的代理选择决策
安装
# pinned to v0.1.0 — latest stable commit
pip install git+https://github.com/joaquinhuigomez/agent-eval.git@6d062a2f5cda6ea443bf5d458d361892c04e749b
核心概念
YAML 任务定义
以声明方式定义任务。每个任务指定要做什么、要修改哪些文件以及如何判断成功:
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 工作树隔离
每个代理运行都获得自己的 git 工作树——无需 Docker。这提供了可复现的隔离,使得代理之间不会相互干扰或损坏基础仓库。
收集的指标
| 指标 | 衡量内容 |
|---|---|
| 通过率 | 代理生成的代码是否通过了判断? |
| 成本 | 每个任务的 API 花费(如果可用) |
| 时间 | 完成所需的挂钟秒数 |
| 一致性 | 跨重复运行的通过率(例如,3/3 = 100%) |
工作流程
1. 定义任务
创建一个 tasks/ 目录,其中包含 YAML 文件,每个任务一个文件:
mkdir tasks
# Write task definitions (see template above)
2. 运行代理
针对你的任务执行代理:
agent-eval run --task tasks/add-retry-logic.yaml --agent claude-code --agent aider --runs 3
每次运行:
- 从指定的提交创建一个新的 git 工作树
- 将提示交给代理
- 运行判断标准
- 记录通过/失败、成本和时间
3. 比较结果
生成比较报告:
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% │
└──────────────┴───────────┴────────┴────────┴─────────────┘
判断类型
基于代码(确定性)
judge:
- type: pytest
command: pytest tests/ -v
- type: command
command: npm run build
基于模式
judge:
- type: grep
pattern: "class.*Retry"
files: src/**/*.py
基于模型(LLM 作为判断器)
judge:
- type: llm
prompt: |
Does this implementation correctly handle exponential backoff?
Check for: max retries, increasing delays, jitter.
最佳实践
- 从 3-5 个任务开始,这些任务代表你的真实工作负载,而非玩具示例
- 每个代理至少运行 3 次试验以捕捉方差——代理是非确定性的
- 在你的任务 YAML 中固定提交,以便结果在数天/数周内可复现
- 每个任务至少包含一个确定性判断器(测试、构建)——LLM 判断器会增加噪音
- 跟踪成本与通过率——一个通过率 95% 但成本高出 10 倍的代理可能不是正确的选择
- 对你的任务定义进行版本控制——它们是测试夹具,应将其视为代码
链接
Alternatives
Compare before choosing
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
affaan-m/ECC
agent-eval
Use it for engineering tasks; the detail page covers purpose, installation, and practical steps.
affaan-m/ECC
dmux-workflows
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
affaan-m/ECC
dmux-workflows
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.