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/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/commands/anusoft/ultrastealth/craft-scraper)<a href="https://agentmods.dev/commands/anusoft/ultrastealth/craft-scraper"><img src="https://agentmods.dev/badge/commands/anusoft/ultrastealth/craft-scraper/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/commands/anusoft/ultrastealth/craft-scraper"><img src="https://agentmods.dev/badge/commands/anusoft/ultrastealth/craft-scraper.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 | $0.00021 | $0.00454 |
| Opus 5.5 | $0.00008 | $0.00182 |
| Sonnet 5.5 | $0.00004 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
craft-scraper scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
script there, then show the two curl+bash bootstrap commands, `--help`, and What it actually says
You are operating as the craft-scraper agent. First read the SKILL.md next
to this commands/ folder and the relevant reference/*.md files, then author a
reusable script for this task:
$ARGUMENTS
Run the loop from SKILL.md:
-
Plan —
out/craft/<task_id>/plan.mdwith a# Parameterstable (defaults = the concrete values in the task above, so a no-arg run reproduces the task) and a# Critical Pointschecklist. Seereference/verification.md. -
Triage — use the Ultrastealth MCP network-capture flow in
reference/triage.mdto find the JSON API (Path A) or confirm a browser is required (Path B). Capture any headers/cookies/tokens the endpoint needs. -
Author —
- Path A: a Bun scrapling-js scraper per
reference/path-a-scrapling-js.md(no runtime browser,Fetcher,stealthyHeaders,--resume/--help). - Path B: an Ultrastealth headful Python script per
reference/path-b-ultrastealth.md(one reusable function + argparse, import-safe).
- Path A: a Bun scrapling-js scraper per
-
Execute the script once and capture output.
-
Self-verify every Critical Point per
reference/verification.md. Diagnose → fix → re-run on failure. -
Deliver — propose the destination path, confirm with the user, write the script there, then show the two curl+bash bootstrap commands,
--help, and the final datum/row count.
Never drive Playwright/Selenium directly; use scrapling-js (HTTP) or
UltrastealthFetcher (browser). Always run JS with Bun and Python with
python3.
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.
- 1mo ago First seen · 41 lines · 21 tokens per session scan A 4f9bb01a2609
craft-scraper is a command published in the GitHub repository anusoft/ultrastealth (0 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 454 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
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.
verify-pr
Verify a PR's frontend changes through browser automation.
gh-issue-use-cypress
Like /gh-issue-use-browser, but pinned to the Cypress MCP — use when your project runs the Cypress MCP for browser automation. Example — /gh-issue-use-cypress "Composer > Save" saving toasts failure but the record persists.
can-i-use
Check browser support for web platform features against the project's browser targets.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.
capture_full_page
Capture a full-page (entire scrollable page, beyond the viewport) or single-element screenshot through the Chrome debugger and save it under screenshots/. Unlike takescreenshot (viewport only, no debugger), this uses CDP to render the whole page or a specific element.