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/anusoft/ultrastealth/craft-scrapernpx skills add anusoft/ultrastealth --skill craft-scrapergit clone --depth 1 https://github.com/anusoft/ultrastealthWrote 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/anusoft/ultrastealth/craft-scraper)<a href="https://agentmods.dev/skills/anusoft/ultrastealth/craft-scraper"><img src="https://agentmods.dev/badge/skills/anusoft/ultrastealth/craft-scraper.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 | $0.00177 | $0.02117 |
| Opus 5 | $0.00088 | $0.01059 |
| Sonnet 5 | $0.00035 | $0.00423 |
| Haiku 4.5 | $0.00018 | $0.00212 |
Grade C, and why
craft-scraper scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/anusoft/ultrastealth/main/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/anusoft/ultrastealth/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Craft-Scraper
Run an LLM-driven discovery loop once and emit a reusable, deterministic script the user reruns forever without any LLM. The browser and the agent are disposable; the script is the artifact. Optimize for a script that still works next month, with different arguments, run unattended.
Two pillars decide everything:
- Discover with stealth. Inspect the target with the Ultrastealth MCP
(real Chrome, passes bot detection,
navigator.webdriver:false). Never drive vanilla Playwright/Selenium — it fails bot checks and is project-banned. - Emit the right kind of script. Most sites expose a JSON API; the fastest, most robust artifact calls it directly with scrapling-js (Bun) and uses no browser at runtime. Fall back to an Ultrastealth headed Python script only when there is no usable API or the task needs real interaction.
Prerequisite: the Ultrastealth MCP must be connected — see https://anusoft.github.io/ultrastealth/#install . If MCP tools aren't available, say so and stop; discovery depends on them.
Runtime bootstrap for emitted scripts
When delivering any generated crawler, show a fresh-machine setup block before the run command. From the script's directory:
curl -fsSL https://raw.githubusercontent.com/anusoft/ultrastealth/main/install.sh | bash
curl -fsSL https://raw.githubusercontent.com/anusoft/scrapling-js/main/install.sh | bash
Path A scripts need scrapling-js at runtime; Ultrastealth is still needed for the discovery/MCP loop and for any future Path B fallback. Path B scripts need Ultrastealth at runtime; keep the scrapling-js command in the setup block so the same folder can run either generated script type.
The loop
Track each step (a TODO per step) and do them in order. One action per step; read the output before the next.
1. Plan
Write out/craft/<task_id>/plan.md with a # Parameters table (every value the
user could vary → a CLI flag whose default is the concrete task value, so a
no-arg run reproduces the task) and a # Critical Points checklist (each
constraint / required datum, independently verifiable). Contract in
reference/verification.md.
What ships with it
9 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.
- commands/craft-scraper.md 1.7 KB
- examples/egp-announcements.py 8.5 KB runs code
- reference/path-a-scrapling-js.md 3.3 KB
- reference/path-b-ultrastealth.md 4.8 KB
- reference/protected-apis.md 3.4 KB
- reference/triage.md 2.6 KB
- reference/verification.md 3.0 KB
- templates/scraper.scrapling-js.js 5.0 KB runs code
- templates/scraper.ultrastealth.py 5.1 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.
- 4d ago First seen · 144 lines · 177 tokens per session scan C 622758de8e2b
craft-scraper is a skill published in the GitHub repository anusoft/ultrastealth (0 stars, last pushed 1mo ago), licensed MIT. It adds 177 tokens to every session and 2,117 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
v8-jit
V8 JIT optimization patterns for writing high-performance JavaScript in Next.js server internals. Use when writing or reviewing hot-path code in app-render, stream-utils, routing, caching, or any per-request code path. Covers hidden classes / shapes, monomorphic call sites, inline caches, megamorphic deopt, closure…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.