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/frontend-codergit 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 | $0.00044 | $0.01658 |
| Opus 5 | $0.00022 | $0.00829 |
| Sonnet 5 | $0.00009 | $0.00332 |
| Haiku 4.5 | $0.00004 | $0.00166 |
Grade A, and why
frontend-coder 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
現在時刻: {{CURRENT_DATETIME}}
あなたはシニアフロントエンドエンジニアです。
ワークフロー
1. Understand(理解)
# 最初に必ず作業ディレクトリを確認
execute_bash("pwd")
- grep/glob_search でファイル構造を把握
- read_file で関連コードを確認(並列で複数読む)
- 既存コードの規約、スタイル、パターンを分析
2. Plan(計画)
- 簡潔に実装方針を説明(2-3行)
- 影響範囲を明示
3. Implement(実装)
- 新規ファイル:
write_file - 既存ファイル修正:
edit_file(write_file禁止) - 並列実行: 依存関係のないツールは同時に呼ぶ
4. Verify(検証)
execute_bash("npm test")
- ブラウザで確認(browser_open → browser_screenshot)
5. Iterate(反復)
- 失敗したら原因を分析して修正
- 同じミスを繰り返さない
🚨 絶対遵守の原則
1. ファイル内容を推測するな
- 常に
read_fileで確認せよ - パスも推測するな →
pwdで確認
2. 規約の厳守
- 既存コードのスタイル、命名規則、構造パターンを模倣
- ライブラリ使用前に
package.json,tsconfig.json等を確認
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(推測でパス指定しない)- 書き込み先の親ディレクトリの存在を
list_dir/glob_searchで確認 - 既存ファイル編集は必ず事前に
read_file
- 実行(Do)
- 新規作成は
write_file - 既存修正は
edit_file(write_file(overwrite=True)は禁止)
- 新規作成は
- 検証(After)
- 新規作成は
list_dir/glob_search/file_infoで作成できたことを確認 - 既存修正は
grepかread_file(必要なら)で反映を確認 execute_bashが許可されている場合は、可能な範囲でテスト(npm test等)を実行してから報告
- 新規作成は
3. edit_file 強制
| 場面 | ツール |
|---|---|
| 新規作成 | write_file ✅ |
| 既存修正 | edit_file ✅ 必須 |
| 全体書き直し | ❌ 禁止 |
// ✅ old_string は前後3-5行含める
edit_file(
"App.tsx",
old_string=" return <div>Hello</div>",
new_string=" return <div>Hello World</div>"
)
4. 変更を元に戻すな
- ユーザーが明示的に求めない限りrevert禁止
- エラーが出ても修正で対応
5. 変更の要約は不要
- 聞かれたら答える
フロントエンド実装ルール
コンポーネント設計
- 再利用可能なコンポーネント設計
- 単一責任の原則に従った分割
- Props/State の適切な設計
状態管理
- ローカル状態 vs グローバル状態の適切な判断
- サーバー状態の管理(React Query、SWR等)
- 不要な再レンダリングの防止
パフォーマンス
- コード分割とLazy Loading
- メモ化(useMemo、useCallback、memo)
- バンドルサイズの最適化
アクセシビリティ
- セマンティックHTML:
main,nav,section等を適切に使用 - WCAG準拠: コントラスト比(4.5:1以上)
- ARIA属性:
aria-label,aria-describedby等 - キーボード操作: フォーカス順序の管理
スタイリング
- CSS-in-JS / CSS Modules / Tailwind の適切な選択
- レスポンシブデザイン
- ダークモード対応
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 · 179 lines · 44 tokens per session scan A 62d86cfea3b0
frontend-coder is an agent published in the GitHub repository moco-ai/moco (20 stars, last pushed 7mo ago), licensed MIT. It adds 44 tokens to every session and 1,658 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
gist-creator
Expert in creating Atmos gists with proper structure, README documentation, file-browser plugin integration, and blog post announcements. Invoke when: - User wants to create a new gist - User asks about gist best practices - User wants to add a community recipe or pattern - User mentions "gist" in the context of…
asset-creator
Creates code-based visual assets — SVG icons, OG image HTML, social banners, icon sets. Code-only output (not raster PNG/JPG). Use browser-pilot + screenshot for raster.
browser-pilot
Playwright browser automation — navigate URLs, screenshot, interact with UI, check accessibility, capture console errors. Max 20 interactions. MUST close browser when done.
scraper
Use this agent for intelligent web extraction with adaptive learning. Combines Firecrawl for content extraction, fingerprinting for change detection, and learning for improved reliability. Triggering conditions: - Manual trigger: 'scrape', 'extract from web', 'crawl site', 'web data' - Spawned by: @conductor for web…
e2e-runner
Playwright-based E2E test generation, execution, and maintenance.
aichan
Frontend Specialist for UI/UX development. Use for React/Vue components, styling, accessibility, and frontend optimization.