agent-eval

agent-eval is a skill for Claude Code, Codex from mturac/everything-openai-codex. It costs 65 tokens per session (1,516 once invoked), scanned A, original, MIT.

A command-line tool for comparing coding agents on repeatable tasks. It measures whether tasks pass their checks, along with cost, completion time, and consistency across runs.

In plain words
What is it for?
Use it to compare agents such as Codex or Aider on a codebase, test model or tool changes, and record results using task definitions and judges such as tests or file checks.
Why use it?
It replaces subjective impressions with repeatable evidence when choosing agents or checking for regressions after updates.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for aider. Also seen: positional $N argument; mentions Codex; built for aider.

Good fit Use it to compare agents such as Codex or Aider on a codebase, test model or tool changes, and record results using task definitions and judges such as tests or file checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mturac/everything-openai-codex/agent-eval
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mturac/everything-openai-codex --skill agent-eval
Clone the repo
git clone --depth 1 https://github.com/mturac/everything-openai-codex

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-eval

README.md
[![agentmods](https://agentmods.dev/badge/skills/mturac/everything-openai-codex/agent-eval/github.svg)](https://agentmods.dev/skills/mturac/everything-openai-codex/agent-eval)
Your own site
<a href="https://agentmods.dev/skills/mturac/everything-openai-codex/agent-eval"><img src="https://agentmods.dev/badge/skills/mturac/everything-openai-codex/agent-eval/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-eval

Your own site · 80×15
<a href="https://agentmods.dev/skills/mturac/everything-openai-codex/agent-eval"><img src="https://agentmods.dev/badge/skills/mturac/everything-openai-codex/agent-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,516 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.01516
Opus 5 $0.00032 $0.00758
Sonnet 5 $0.00013 $0.00303
Haiku 4.5 $0.00006 $0.00152

Measured 5d ago against content hash 908c2b320bcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-eval scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/ja-JP/skills/agent-eval/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

エージェント評価スキル

再現可能なタスクでコーディングエージェントをヘッドツーヘッドで比較するための軽量 CLI ツールです。「どのコーディングエージェントが最適か?」という比較はすべて感覚に頼りがちです — このツールはそれを体系化します。

起動タイミング

  • 自分のコードベースでコーディングエージェント(OpenAI Codex、Aider、Codex など)を比較する
  • 新しいツールやモデルを採用する前にエージェントパフォーマンスを測定する
  • エージェントがモデルやツールを更新した際にリグレッションチェックを実行する
  • チームにデータに基づいたエージェント選択の判断を提供する

インストール

注意: agent-eval はソースを確認した後、リポジトリからインストールしてください。

コアコンセプト

YAML タスク定義

タスクを宣言的に定義します。各タスクは何をするか、どのファイルを操作するか、成功をどう判定するかを指定します:

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"  # 再現性のために特定コミットに固定

Git ワークツリー分離

各エージェント実行は独自の git ワークツリーを取得します — Docker 不要。これにより再現性の分離が提供され、エージェントが互いに干渉したりベースリポジトリを破壊したりしません。

収集メトリクス

メトリクス 測定内容
合格率 エージェントはジャッジをパスするコードを生成できたか?
コスト タスクあたりの API 費用(利用可能な場合)
時間 完了までのウォールクロック秒数
一貫性 繰り返し実行での合格率(例:3/3 = 100%)

ワークフロー

1. タスクの定義

タスクごとに 1 つの YAML ファイルを持つ tasks/ ディレクトリを作成します:

mkdir tasks
# タスク定義を作成(上記のテンプレートを参照)

2. エージェントの実行

タスクに対してエージェントを実行します:

agent-eval run --task tasks/add-retry-logic.yaml --agent codex --agent aider --runs 3

各実行:

  1. 指定されたコミットから新しい git ワークツリーを作成
  2. エージェントにプロンプトを渡す
  3. ジャッジ基準を実行
  4. 合格・不合格、コスト、時間を記録

3. 結果の比較

比較レポートを生成します:

agent-eval report --format table
Task: add-retry-logic (3 runs each)
┌──────────────┬───────────┬────────┬────────┬─────────────┐
│ Agent        │ Pass Rate │ Cost   │ Time   │ Consistency │
├──────────────┼───────────┼────────┼────────┼─────────────┤
│ codex  │ 3/3       │ $0.12  │ 45s    │ 100%        │
│ aider        │ 2/3       │ $0.08  │ 38s    │  67%        │
└──────────────┴───────────┴────────┴────────┴─────────────┘

Read the full file on GitHub · 146 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 146 lines · 65 tokens per session scan A 908c2b320bcb

Subscribe to this mod's changes

agent-eval is a skill published in the GitHub repository mturac/everything-openai-codex (89 stars, last pushed 15d ago), licensed MIT. It adds 65 tokens to every session and 1,516 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

sips-control-plane

Inspect SIPS Homebase status, manifest wiring, routes, host visibility, and MCP freshness. Use when asked for SIPS status, command center, host audit, plugin visibility, or whether Homebase is fresh.

RasputinKaiser/Self-Improvement-Plugin · 48 tokens

sips-selfloop

Start, inspect, or continue a persistent SIPS self-improvement loop. Use when the user asks for /selfloop, wants the agent to iteratively improve itself, or wants a goal dedicated only to SIPS and agent capability.

RasputinKaiser/Self-Improvement-Plugin · 52 tokens

audio-hooks

Use whenever the user asks to install, configure, uninstall, snooze, mute, test, troubleshoot, or change settings for the echook audio notification system. Trigger phrases include "audio hooks", "audio notifications", "snooze audio", "mute claude", "claude is too loud", "test audio", "switch audio theme", "rate limit…

ChanMeng666/echook · 321 tokens

sips-memory-fabric

Search, inspect, and record SIPS-owned Memory Fabric lessons. Use when a task needs prior lessons, recurring-fix memory, recall health, scoped historical context, or when a just-fixed bump or error should be recorded.

RasputinKaiser/Self-Improvement-Plugin · 51 tokens

sips-perception-plan

Plan browser, app, screenshot, or UI checks before visual claims. Use when a task includes app shots, visual QA, generated assets, or runtime UI proof.

RasputinKaiser/Self-Improvement-Plugin · 39 tokens

sips-delegation-router

Route a task through SIPS commands, agents, scripts, MCP tools, or bounded delegation. Use when asked to route, split, fan out, escalate, or choose the right SIPS path.

RasputinKaiser/Self-Improvement-Plugin · 47 tokens