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/cloudnative-co/claude-code-starter-kit/web-content-extractionnpx skills add cloudnative-co/claude-code-starter-kit --skill web-content-extractiongit clone --depth 1 https://github.com/cloudnative-co/claude-code-starter-kitWhat 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 | $0.00110 | $0.02280 |
| Opus 5 | $0.00055 | $0.01140 |
| Sonnet 5 | $0.00022 | $0.00456 |
| Haiku 4.5 | $0.00011 | $0.00228 |
Grade A, and why
web-content-extraction 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Content Extraction
Purpose
Webページ本文を抽出し、LLMが読みやすい Markdown/JSON に整形する。 Claude Code が Webページ、URL、公式ドキュメント、ブログ記事、ニュース記事、OSSページを読む場合は、原則として毎回このSkillを使う。
Mandatory Rule
When reading any public web URL, use Defuddle first.
Do not summarize, analyze, compare, or review a web page from raw HTML unless Defuddle extraction fails or the page type is explicitly unsupported.
Use Cases
- URL要約 / 公式ドキュメント確認 / OSS調査
- ブログ記事分析 / ニュース記事分析 / 競合サイト分析
- ベンダー公式ブログの調査 / Web上の一次情報確認
- 技術記事の読み取り / LLM・RAG向けのWeb本文抽出
Standard Commands
# 公開URLを取得して本文をMarkdown/JSON化（SSRFガードあり）
~/.claude/skills/web-content-extraction/scripts/run-node.sh \
~/.claude/skills/web-content-extraction/scripts/defuddle-url.mjs <url>
# ローカルHTMLファイルを本文抽出（外部通信なし）
~/.claude/skills/web-content-extraction/scripts/run-node.sh \
~/.claude/skills/web-content-extraction/scripts/defuddle-file.mjs <file>
出力は JSON（stdout）。最低限 success, url, fetchedAt/parsedAt, title, author,
site, domain, published, description, wordCount, content(Markdown) を含む。
warnings / fetchWarnings がある場合は抽出の信頼性に注意する。
Output Fields
| フィールド | 意味 |
|---|---|
success |
本文抽出に成功したか（false は抽出失敗/空） |
warnings |
本文が短い・空など低信頼の警告 |
url / requestedUrl / finalUrl |
対象URL（リダイレクト後の最終URL含む） |
fetchedAt / parsedAt |
取得・解析時刻（ISO8601, 監査用に必ず保持） |
title author site domain published description |
メタデータ |
wordCount |
語数（空白区切り。日本語は極端に小さく出る） |
charCount |
非空白の文字数（日本語の実分量はこちらで判断） |
cjkCharCount |
CJK文字数（日本語/中国語/韓国語の量の目安） |
content |
本文（HTMLはMarkdown、PDFはプレーンテキスト） |
extractorType |
サイト固有抽出器が使われた場合の種別 |
extractorEngine |
PDF抽出時のみ "pdf"。pageCount も付く |
Security Rules
- 同期コア + 非フェッチDOM で動作する（
useAsyncはupstreamに存在しないため意図を構造で担保）。 - 外部フォールバック・サブリソース外部取得・ページ内スクリプト実行は行わない。
- 社内URL、顧客URL、認証付きURL、個人情報・機密を含むページを外部送信しない。
localhost/ プライベートIP(10/8,172.16/12,192.168/16,127/8,169.254/16,100.64/10 等) /.local/.internal等 / 単一ラベルの内部ホスト名 / 非http(s) / 認証情報付きURL は標準で拒否。- IP判定はバイト単位。10進/8進/16進 IPv4 も拒否。IPv6はdefault-deny（グローバルユニキャスト
2000::/3以外は全拒否。Teredo/site-local/documentation/NAT64/IPv4-mapped/6to4(private埋め込み)等を含む）。 - 接続IPをpin（guarded undici dispatcher）して DNSリバインディング/TOCTOU を封じる。
- リダイレクトは手動追従し各ホップを送信前に再検査。本文はストリームでサイズ上限（メモリDoS対策）。
- 開発用途で明示的に許可する場合のみ
ALLOW_PRIVATE_URLS=true（バイパスは stderr に監査記録）。 - 抽出結果には必ず URL と取得日時を残す。
- 抽出結果だけを唯一の真実として扱わない。重要な事実は一次情報で再確認する。
What ships with it
16 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.
- .gitignore 36 B
- package-lock.json 37 KB
- package.json 595 B
- README.md 8.7 KB
- scripts/defuddle-file.mjs 2.5 KB runs code
- scripts/defuddle-url.mjs 8.8 KB runs code
- scripts/lib/defuddle-core.mjs 6.6 KB runs code
- scripts/lib/pdf-extract.mjs 6.4 KB runs code
- scripts/lib/url-guard.mjs 9.4 KB runs code
- scripts/run-node.sh 2.7 KB runs code
- scripts/update-deps.mjs 15 KB runs code
- test/defuddle-core.test.mjs 1.2 KB runs code
- test/defuddle-url.test.mjs 5.2 KB runs code
- test/extract-smoke.test.mjs 3.3 KB runs code
- test/update-deps-lock.test.mjs 8.1 KB runs code
- test/url-guard.test.mjs 7.9 KB runs code
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 · 127 lines · 0 tokens per session scan A 7fe25cd5dad2
web-content-extraction is a skill published in the GitHub repository cloudnative-co/claude-code-starter-kit (147 stars, last pushed 9d ago), licensed MIT. It adds 110 tokens to every session and 2,280 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.