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.
git clone --depth 1 https://github.com/acaprino/daodanWrote 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/plugins/acaprino/daodan/grabber-development)<a href="https://agentmods.dev/plugins/acaprino/daodan/grabber-development"><img src="https://agentmods.dev/badge/plugins/acaprino/daodan/grabber-development/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/plugins/acaprino/daodan/grabber-development"><img src="https://agentmods.dev/badge/plugins/acaprino/daodan/grabber-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
grabber-development 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 yesterday.
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.
What it actually says
{
"author": {
"name": "Alfio Caprino"
},
"description": "Expert Python web scraping - coordinator (grabber-architect) plus three specialists: stealth-browser-expert (Patchright/Camoufox/Nodriver + CAPTCHA), http-fingerprint-expert (JA4+/curl_cffi/primp + proxies/Web Unlocker), ai-scraping-expert (Crawl4AI/Firecrawl/ScrapeGraphAI + Pydantic + GraphQL RE)",
"license": "MIT",
"name": "grabber-development",
"version": "1.8.5"
}
What it installs
The manifest is a name and a version. 1 skill, 1 command, 4 agents travel with it, and installing the plugin installs all of them — 534 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- yesterday Changed 8ae6eff862d4
- 5d ago Changed 6787225994ec
- 8d ago Changed 92407451824d
- 14d ago Changed 735bfd38060e
- 16d ago Changed ed1e726ccdc1
- 1mo ago Changed f2955e3dc513
- 1mo ago First seen · 10 lines scan A edda33221e16
grabber-development is a plugin published in the GitHub repository acaprino/daodan (9 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-05.
Other plugins, from other repositories
axon
Axon research, ingestion, retrieval, and operator skills for an existing service.
tesseron
MCP gateway that lets any web app expose typed actions to Claude over WebSocket — no browser automation. Reverse-connection architecture: the gateway is a pure WebSocket client that discovers apps via /.tesseron/tabs/ — no fixed ports, no env vars. Plus a framework skill for the Tesseron mental model, a tesseron.
tao-skill-bank
NVIDIA TAO skill bank with generated capability discovery for model training, data processing, application workflows, AutoML, and platform execution.
clip-aware-embeddings
Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries. Activate on "CLIP", "embeddings", "image similarity", "semantic…
twelvelabs
TwelveLabs video AI integration. Index, search, and analyze videos using TwelveLabs' multimodal AI platform.
kernel-sdks
TypeScript and Python SDK skills for building browser automation with Kernel's Typescript and Python SDKs.