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 skills/sean-sunagaku/claude-code-plugin/pencil-replicatornpx skills add sean-sunagaku/claude-code-plugin --skill pencil-replicatorgit clone --depth 1 https://github.com/sean-sunagaku/claude-code-pluginWrote 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/skills/sean-sunagaku/claude-code-plugin/pencil-replicator)<a href="https://agentmods.dev/skills/sean-sunagaku/claude-code-plugin/pencil-replicator"><img src="https://agentmods.dev/badge/skills/sean-sunagaku/claude-code-plugin/pencil-replicator.svg" alt="Measured on agentmods" 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 | $0.00128 | $0.05017 |
| Opus 5 | $0.00064 | $0.02508 |
| Sonnet 5 | $0.00026 | $0.01003 |
| Haiku 4.5 | $0.00013 | $0.00502 |
Grade A, and why
pencil-replicator 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 6d 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 — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pencil-replicator
Chrome で表示中の Web 画面を Pencil (.pen) ファイルに高精度で再現する Agent Team スキル。
概要
このスキルは 3 つの専門エージェントが連携して動作する:
screen-analyzer → (chrome-analysis.md) → design-builder
↕ (フィードバックループ)
quality-reviewer
| エージェント | 役割 | MCP |
|---|---|---|
| screen-analyzer | Chrome 画面の構造・スタイル・テキストを徹底分析 | Chrome DevTools |
| design-builder | 分析結果に基づいて .pen ファイルを構築 | Pencil |
| quality-reviewer | Chrome vs Pencil の差分検出と修正指示 | Chrome DevTools + Pencil |
精度目標: quality-reviewer の 10点満点スコアが 7点以上(「見分けがつかない」レベル)
Step 1: ヒアリング
ユーザーに以下を確認する:
- 対象 URL: Chrome で開いている画面の URL(例:
localhost:2626) - .pen ファイル: 既存ファイルへの追加 か 新規作成 か
- 既存ファイルの場合: ファイルパスを確認
- 新規作成の場合:
newを使用
- 対象セクション: 画面全体 か 特定のセクションのみか
確認できたら Step 2 へ。
Step 2: リーダー(自分)の準備
ToolSearch で Pencil MCP をロードしてから以下を実行:
ToolSearch(query: "+pencil get_editor_state")
ToolSearch(query: "+pencil open_document")
ToolSearch(query: "+pencil get_style_guide_tags")
ToolSearch(query: "+pencil batch_get")
ToolSearch(query: "+pencil get_guidelines")
2-1. .pen ファイルの準備
# 新規作成の場合
mcp__pencil__open_document(filePathOrNew: "new")
# 既存ファイルを開く場合
mcp__pencil__open_document(filePathOrNew: "{ユーザー指定のパス}")
# 現在の状態確認
mcp__pencil__get_editor_state(include_schema: true)
2-2. スタイルガイドの取得・適用
mcp__pencil__get_style_guide_tags()
# → 適切なタグを選択(例: "web-app", "dashboard", "saas")
mcp__pencil__get_style_guide(tags: ["web-app", ...])
2-3. コンポーネント一覧の取得
mcp__pencil__batch_get(
patterns: [{"reusable": true}],
readDepth: 2,
searchDepth: 3
)
2-4. コンテキストファイルの書き出し
以下の情報を .claude/pencil-replicator/pencil-context.md に書き出す:
# Pencil コンテキスト
## .pen ファイル情報
- パス: {path}
- ドキュメントID: {id}
## スタイルガイド
{get_style_guide の結果の主要情報}
## デザインシステムコンポーネント
{batch_get で取得したコンポーネント一覧(name, nodeId)}
## ガイドライン
{get_guidelines(topic: "web-app") の主要ルール}
2-5. 進捗ファイルの初期化
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 448 lines · 128 tokens per session scan A 3c41fc50ccd1
pencil-replicator is a skill published in the GitHub repository sean-sunagaku/claude-code-plugin (36 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 5,017 once invoked, about $0.0006 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 skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
中文可编辑简历制作技能:默认基于 ASu 单栏高密度技术简历模板,根据用户经历制作或复刻可编辑 HTML/PDF;用户也可以指定仓库内其他模板、本地 HTML 或参考截图。用户输入“/make-resume”“我要阿酥同款简历”或要求制作、修改、复刻简历文件时使用。.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.