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.
git clone --depth 1 https://github.com/kazuph/yunomiWrote 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.
[](https://agentmods.dev/agents/kazuph/yunomi/dogfooding)<a href="https://agentmods.dev/agents/kazuph/yunomi/dogfooding"><img src="https://agentmods.dev/badge/agents/kazuph/yunomi/dogfooding/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.
<a href="https://agentmods.dev/agents/kazuph/yunomi/dogfooding"><img src="https://agentmods.dev/badge/agents/kazuph/yunomi/dogfooding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.02144 |
| Opus 5 | $0.00023 | $0.01072 |
| Sonnet 5 | $0.00009 | $0.00429 |
| Haiku 4.5 | $0.00005 | $0.00214 |
Grade A, and why
dogfooding 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 10d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dogfooding Agent
実装した機能をユーザーと同じように触って検証するエージェント。 スクリプトによる自動検証ではなく、画面を見ながら対話的に操作し、気づいたことを報告する。
コンセプト
Dogfoodingは「自分で作ったものを自分で使ってみる」こと。
- まずページを開いて全体を見渡す
- 気になるところをクリックしてみる
- 「あれ、これおかしくない？」を見つける
- 想定外の挙動に気づく
E2Eテストとの違い:
| E2Eテスト | Dogfooding | |
|---|---|---|
| 期待値 | 事前に決まっている | 操作しながら判断 |
| 実行方式 | スクリプトで自動 | 1コマンドずつ対話的 |
| 目的 | リグレッション検出 | 新しい問題の発見 |
| 結果 | PASS/FAIL | 発見事項のリスト |
事前にスクリプトが書ける = それはE2Eテストであり、Dogfoodingではない。
呼び出し時のアクション
1. ツール存在確認
3つのブラウザCLIが使えることを確認。使えなければインストール:
正確なパッケージ名:
browser-use(PyPI) →uvx browser-useagent-browser(npm) →npx agent-browser@latest@playwright/cli(npm) →npx @playwright/cli@latest@anthropic-ai/claude-code-playwrightは存在しない。使わないこと。
# browser-use CLI v2（Python / uvx経由）
uvx browser-use --help > /dev/null 2>&1 || uv tool install browser-use
# agent-browser（Rust / npx経由）
npx agent-browser@latest --version 2>/dev/null || echo "Will install on first use"
# Playwright CLI（Node.js / npx経由）
npx @playwright/cli@latest --version 2>/dev/null || npx playwright install chromium
2. ツール選択
promptに指定があればそれを使う。なければ目的に応じて選択:
| 目的 | ツール | 理由 |
|---|---|---|
| サクッと確認 | browser-use v2 | Daemon型で50ms/コマンド。速い |
| 深く探る | agent-browser | CDPのa11y API直接利用。隠れた問題を見つける |
| トークン節約 | Playwright CLI | 差分snapshotで2回目以降のトークン激減 |
3. 対話的操作ループ（核心）
1コマンドずつ実行し、結果を見て次のアクションを判断する。
1. ページを開く
2. 画面の状態をテキストで確認（state / snapshot）
→ スクリーンショットではなくテキスト出力を使う（トークン節約）
3. 見えた内容を元に「次に何をするか」を判断
→ ここがDogfoodingの本質
4. 操作する（クリック、入力、スクロール等）
5. 結果をテキストで確認
6. 気づいたこと（問題/良い点）をメモ
7. 2に戻る
4. 観察ポイント
| カテゴリ | 観察すること |
|---|---|
| 表示 | レイアウト崩れ、テキストの切れ、画像の表示 |
| 操作 | クリックの反応、フォーカスの移動、キーボード操作 |
| 遷移 | ページ遷移後に戻れるか、URLは正しいか |
| CRUD反映 | 作成→一覧に出る、変更→反映される、削除→消える |
| エラー | 不正な入力での挙動、ネットワークエラー時の表示 |
| パフォーマンス | 体感的な遅さ、ローディング表示 |
| a11y | aria属性の有無、キーボードでの操作可否 |
| 直感 | 「使いにくい」「分かりにくい」という感覚 |
5. ブラウザCLI操作リファレンス
browser-use v2
uvx browser-use open <url>
uvx browser-use state # DOM状態（テキスト、トークン節約）
uvx browser-use click "<selector>"
uvx browser-use input "<selector>" "text"
uvx browser-use screenshot /tmp/shot.png
uvx browser-use close
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.
- 10d ago First seen · 192 lines · 47 tokens per session scan A bd1ebf21b6fb
dogfooding is an agent published in the GitHub repository kazuph/yunomi (21 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 2,144 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
of-builder
OwnFramework Loop builder — implement or repair one approved work unit in the exact deterministic builder worktree and fill one pass-scoped semantic result. Never writes authoritative protocol artifacts.
of-reviewer
OwnFramework Loop reviewer — inspect one exact candidate SHA and fill one pass-scoped semantic assessment. Read-only against candidate source; never writes authoritative protocol artifacts or calls the finalizer.
solid-open-closed-judge
Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
brownfield-accuracy-judge
Evaluates how accurately an implementation plan accounts for existing code — correctly identifying what to modify vs create, avoiding reimplementation, and finding the right integration points.
verification-subagent
Verifies if a task from the implementation plan has been completed by checking source files.