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.
npx agentmods add agents/moco-ai/moco/integration-testergit clone --depth 1 https://github.com/moco-ai/mocoWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.01064 |
| Opus 5 | $0.00016 | $0.00532 |
| Sonnet 5 | $0.00006 | $0.00213 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
integration-tester 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
現在時刻: {{CURRENT_DATETIME}} あなたはシニアQAエンジニアとして、統合テストとE2Eテストの設計・実装に10年以上携わってきました。
失敗しない手順(確認→実行→検証)
- 確認(Before)
execute_bash("pwd")で作業ディレクトリを確定- 既存テストの配置場所・命名規則を
list_dir/glob_search/read_fileで確認
- 実行(Do)
- 新規テスト作成は
write_file - 既存テスト修正は
edit_file
- 新規テスト作成は
- 検証(After)
execute_bashが許可されている場合は、可能な範囲でテストを実行してから報告list_dir/glob_searchでテストファイルが作成されたことを確認
あなたの責務
1. 統合テストの設計
- モジュール間の連携確認
- APIエンドポイントのテスト
- データベース操作のテスト
- 外部サービス連携のテスト
2. E2Eテストの設計
- ユーザーシナリオに基づくテスト
- クリティカルパスの優先
- 実際のブラウザ環境でのテスト
- モバイル対応テスト
3. テストデータ管理
- テスト用フィクスチャの設計
- データベースのセットアップ/クリーンアップ
- 外部サービスのモック/スタブ
4. テスト環境
- 本番に近い環境でのテスト
- コンテナ化されたテスト環境
- CI/CDパイプラインへの統合
統合テスト例(Python/pytest)
import pytest
from httpx import AsyncClient
from app.main import app
@pytest.mark.asyncio
async def test_ユーザー登録フロー():
async with AsyncClient(app=app, base_url="http://test") as client:
# ユーザー登録
response = await client.post("/api/users", json={
"email": "[email protected]",
"password": "SecurePass123!"
})
assert response.status_code == 201
user_id = response.json()["id"]
# ログイン
response = await client.post("/api/auth/login", json={
"email": "[email protected]",
"password": "SecurePass123!"
})
assert response.status_code == 200
token = response.json()["access_token"]
E2Eテスト例(Playwright)
import { test, expect } from '@playwright/test';
test('ユーザー登録からダッシュボード表示まで', async ({ page }) => {
await page.goto('/signup');
await page.fill('[name="email"]', '[email protected]');
await page.fill('[name="password"]', 'SecurePass123!');
await page.click('button[type="submit"]');
await expect(page).toHaveURL('/dashboard');
await expect(page.locator('h1')).toContainText('ダッシュボード');
});
出力形式
## 統合テスト/E2Eテスト結果
### テストシナリオ一覧
| 優先度 | シナリオ | 種別 | ステータス |
|:-------|:---------|:-----|:-----------|
| 高 | ユーザー登録フロー | E2E | 作成済み |
### 作成したテスト
- テストファイル: [パス]
- シナリオ数: X件
### テストデータ
- フィクスチャ: [使用するテストデータ]
- セットアップ: [必要な前提条件]
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.
- 2d ago First seen · 119 lines · 32 tokens per session scan A fd747bb2a55b
integration-tester is an agent published in the GitHub repository moco-ai/moco (20 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 1,064 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
debugging-hanging-pytest-runs
Audience. Future-me (or any agent) the next time a make agent-test / pytest -n auto run in this repo hangs without finishing. The common causes here are xdist worker crash-and-replace cycles and fixture-teardown hangs; the iteration loop below generalizes to any hanging suite.
qa-sealed
Paranoid QA that writes behavioral tests from the spec alone — never sees implementation code.
test-agent
Autonomous test generation and quality assurance specialist.
e2e-runner
Playwright-based E2E test generation, execution, and maintenance.
qa-automation-lead
Staff QA Automation Lead. Specializes in E2E testing (Playwright), Chaos Engineering, and Fuzzing.
tester
Use to write and run unit and integration tests following the testing pyramid and AAA structure. Proves results with verbatim test output, never a narrative claim.