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 skills add Mingye-Lu/AgenticCrawler --skill acrawl-mcpgit clone --depth 1 https://github.com/Mingye-Lu/AgenticCrawlerWrote 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/mingye-lu/agenticcrawler/acrawl-mcp)<a href="https://agentmods.dev/skills/mingye-lu/agenticcrawler/acrawl-mcp"><img src="https://agentmods.dev/badge/skills/mingye-lu/agenticcrawler/acrawl-mcp/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/skills/mingye-lu/agenticcrawler/acrawl-mcp"><img src="https://agentmods.dev/badge/skills/mingye-lu/agenticcrawler/acrawl-mcp.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 | $0.00200 | $0.04124 |
| Opus 5 | $0.00100 | $0.02062 |
| Sonnet 5 | $0.00040 | $0.00825 |
| Haiku 4.5 | $0.00020 | $0.00412 |
Grade A, and why
acrawl-mcp 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 today.
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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
acrawl MCP
acrawl exposes 39 MCP tools: 31 browser/DevTools tools, 7 script tools, and 1 autonomous agent (run_goal). All 39 share one persistent browser session across calls — except run_goal, which builds its own isolated agent and browser.
What makes acrawl different from other browser MCPs is the observability half: you can read network traffic, console logs, WebSocket frames, cookies, storage, coverage, and axe-core audits from a live page. Reach for those instead of guessing why a page misbehaves.
Tool names below are bare (navigate). Your client may namespace them (acrawl_navigate, mcp__acrawl__navigate) — use whatever prefix your tool list shows.
1. Pick an execution mode first
Three ways to get work done. Choosing wrong is the most expensive mistake available, because it either burns tokens on a loop that should have been a script, or spends a script debugging cycle on a one-off click.
| Mode | Use when | Cost |
|---|---|---|
| Manual tool calls | Exploring an unfamiliar page; <10 actions; you need to see each result to decide the next step | 1 LLM round-trip per action |
run_script |
Same operation over 3+ pages/items, and the page structure is already known | Zero LLM round-trips during execution |
run_goal |
Whole task is delegable in one sentence and you don't need intermediate control | 1 call; agent burns its own tokens internally |
The practical pattern: explore manually until the shape is known, then script the repetition. Do one page by hand, confirm your selectors, then turn the loop into a script. A 50-page crawl becomes one tool call instead of 150.
Reach for run_goal when the target is genuinely unknown and adaptive ("find the pricing page and extract every tier"). It needs ~/.acrawl/credentials.json configured; the other 38 tools do not. If credentials are missing, run_goal fails and the correct move is manual tools or a script, not repeated retries. See references/setup.md.
What ships with it
4 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.
- today First seen · 195 lines · 200 tokens per session scan A 47eed4d97836
acrawl-mcp is a skill published in the GitHub repository Mingye-Lu/AgenticCrawler (12 stars, last pushed today), licensed MIT. It adds 200 tokens to every session and 4,124 once invoked, about $0.0010 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 2026-09-13.
Other skills, from other repositories
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
browser-doctor
Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.
chrome-devtools
Browser automation and debugging using Puppeteer for API testing, screenshot capture, and web scraping. Use when you need to interact with web interfaces programmatically.
debug-failed-action
When your last vsact returned an unexpected result (NOTFOUND, no visible state change, suspected silent failure), run this skill with the action's pre-token. Pulls console errors, network failures, and current performance into one report.
playwright-interactive
Persistent browser and Electron interaction through jsrepl for fast iterative UI debugging.