agent-eval
/agent-eval
Compares coding agents head to head on custom tasks by pass rate, cost and time. Use when choosing between agents or agent setups.
- Author
- ghvinashvili ↗
- Repository
- specagent ↗
- Licence
- Apache-2.0
- Last repository change
- 02.11.2026
Assessment and security
- Files in this package
- 3
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 1
No signals detected. Repository changed on 02.11.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Compares coding agents head to head on custom tasks by pass rate, cost and time. Use when choosing between agents or agent setups.
Original author description
Compares coding agents head to head on custom tasks by pass rate, cost and time. Use when choosing between agents or agent setups.
How it works
- When to Activate
- Installation
- Core Concepts
- Workflow
- Judge Types
- Best Practices
- Links
SKILL.md preview
---
name: agent-eval
description: Compares coding agents head to head on custom tasks by pass rate, cost and time. Use when choosing between agents or agent setups.
license: MIT
metadata:
origin: ECC
---
# 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: 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:
```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: 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
- Repository: [github.com/joaquinhuigomez/agent-eval](https://github.com/joaquinhuigomez/agent-eval)
Files in this package (3)
- LICENSE 1 KB
- SHA256SUMS 1 KB
- SKILL.md 4 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · ghvinashvili/specagent | 100 | Apache-2.0 |
| ericrisco/rsc-harness | 100 | MIT |
| colbymchenry/codegraph | 100 | MIT |
| affaan-m/ECC | 100 | MIT |
| SHRIJANAGAIN/Nemo-Cli | 100 | Apache-2.0 |
| EthanYoQ/Skill-hub | 100 | MIT |
| bdfinst/agentic-dev-team | 95 | MIT |
Database snapshot: 13.11.2026 · package version c9c8f302ca42 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100agent-scorecard
Test and compare AI coding agents (Claude Code, Codex, Hermes, OpenCode, local models and others) on 5 real tasks with agent-scorecard, where every check is done by code. Use when the user wants to benchmark an agent or model on their own computer, compare two setups, or explain a scorecard result. - 86agent-eval-compare
Compare two or more agents (skills, plugins or MCP servers) head-to-head on the same weights, budget and host, rank them and recommend one with the trade-offs. Use when the user asks which of several skills, plugins or MCP servers to pick, or to compare versions of one agent. Not for a single agent. - 100eval-harness
Eval-driven development (EDD) framework for AI coding sessions — define capability and regression evals before coding, grade with code-based, model-based, rule, or human graders, and track pass@k and pass^k reliability. Use when defining pass/fail criteria for agent tasks,… - 100roostr
Orchestrate multi-agent coding crews in Herdr with the roostr board (`roostr` / `crew-board`). Use whenever planning, spawning, supervising, or reviewing worker panes in Herdr, routing tasks by empirical pass-rate data (`roostr recommend`, `roostr tasks`, `roostr summary`,… - 95byted-ark-agent-eval-lab
用于 Agent 评测相关需求,包括评估 Agent 的能力与效果、设计评测方案、 比较不同 Agent 或同一 Agent 的模型、Skill、Tool 配置, 以及准备评测数据、配置运行策略、执行评测、查询和分析结果、 诊断失败、取消、重跑与重评分、分析历史重评分与评分器稳定性、导入外部 Evidence、对已有输出或轨迹评分, 以及评测使用中的问题与体验反馈。 用户提到“评测 Agent”“测试智能体效果”“比较 Agent 表现”等需求时使用, 无需明确提及平台或工具名称。具体操作通过 agent-eval CLI 对接 Agent Eval Lab 服务。 - 100custom-agent-definitions
Write and configure custom agent definitions in Claude Code agents/ directory. Use when creating an agent .md file, defining a specialized agent, or configuring agent tools.