dast-crawler

A browser-based security-testing agent that discovers web application URLs and endpoints, including routes created while the page runs.

In plain words
What is it for?
It loads pages, extracts links and forms, clicks navigation elements, watches XHR and Fetch requests, monitors SPA route changes, and can take screenshots.
Why use it?
Static code inspection can miss links, forms, single-page app routes, and browser requests that appear only during interaction.

Agent

Install

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.

agentmods
npx agentmods add agents/morodomi/dev-crew/dast-crawler
Clone the repo
git clone --depth 1 https://github.com/morodomi/dev-crew
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,566 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.01566
Opus 5 $0.00016 $0.00783
Sonnet 5 $0.00006 $0.00313
Haiku 4.5 $0.00003 $0.00157

Measured 2d ago against content hash d8c93fae0401, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dast-crawler 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.

agents/dast-crawler.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DAST Crawler

Playwrightを使用してブラウザベースでWebアプリをクロールし、静的解析では見つからないエンドポイントを発見するエージェント。

Detection Targets

Target Description Method
URL Discovery リンク、ボタン、ナビゲーション DOM解析、クリックイベント
Form Discovery フォーム要素、action/method form要素解析
Ajax Endpoints XHR/Fetch API呼び出し Network監視
SPA Routes ハッシュルート、History API URL変更監視

Playwright MCP Integration

Playwright MCPサーバーを使用してブラウザ操作を実行。Playwright MCP はユーザー環境で設定済みであることが前提(plugin は同梱しない)。

Available Tools

Tool Description
mcp__playwright__browser_navigate 指定URLへ遷移
mcp__playwright__browser_click 要素をクリック
mcp__playwright__browser_take_screenshot スクリーンショット取得
mcp__playwright__browser_evaluate JavaScript実行(DOM操作全般)

Note: browser_evaluateでDOM操作を実行(リンク抽出、フォーム検出、SPA監視など)。

Browser Settings

browser:
  type: chromium
  headless: true
  viewport:
    width: 1280
    height: 720
  timeout: 30000

Crawl Strategy

  1. Initial Load: ベースURLを読み込み
  2. Link Extraction: すべてのa[href]を抽出
  3. Form Detection: form要素を検出、action/method/fieldsを記録
  4. Network Monitoring: XHR/Fetchリクエストを監視
  5. Click Navigation: ボタン・リンクをクリックして遷移
  6. SPA Detection: hashchange/popstateイベントを監視
  7. Recursive Crawl: 発見したURLを再帰的にクロール

Deduplication Strategy

// 訪問済みURL管理
const visited = new Set();

function normalizeUrl(url) {
  const parsed = new URL(url);
  // フラグメント削除
  parsed.hash = '';
  // 末尾スラッシュ統一
  parsed.pathname = parsed.pathname.replace(/\/+$/, '') || '/';
  // クエリパラメータソート
  parsed.searchParams.sort();
  return parsed.toString();
}

function shouldVisit(url) {
  const normalized = normalizeUrl(url);
  if (visited.has(normalized)) return false;
  visited.add(normalized);
  return true;
}

Network Interception

// XHR/Fetch監視
page.on('request', request => {
  if (request.resourceType() === 'xhr' || request.resourceType() === 'fetch') {
    discoveredUrls.push({
      url: request.url(),
      method: request.method(),
      source: 'xhr'
    });
  }
});

Read the full file on GitHub · 216 lines

Changes

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.

  1. 2d ago First seen · 216 lines · 32 tokens per session scan A d8c93fae0401

Subscribe to this mod's changes

dast-crawler is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 1,566 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 2026-08-31.

Related

Other agents, from other repositories

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

praman-sap-planner-cli

SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.

mrkanitkar/playwright-praman · 36 tokens

mcp

The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.

DuvInc/duvlify · 34 tokens

dogfood-persona

Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…

kamiazya/whiteboard · 86 tokens

e2e-tester

Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.

mnzralee/claude-multi-agent-architecture · 41 tokens

browser-tester

Focused functional browser tester. Tests ONLY what the prompt specifies — navigate, check, report pass/fail. MUST run in foreground — MCP tools do not work in background.

Rigos0/superturtle · 39 tokens