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 KuiChi-x/reverseloom --skill web-crawlgit clone --depth 1 https://github.com/KuiChi-x/reverseloomWrote 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/kuichi-x/reverseloom/web-crawl)<a href="https://agentmods.dev/skills/kuichi-x/reverseloom/web-crawl"><img src="https://agentmods.dev/badge/skills/kuichi-x/reverseloom/web-crawl.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 24 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00108 | $0.01284 |
| Opus 5 | $0.00054 | $0.00642 |
| Sonnet 5 | $0.00022 | $0.00257 |
| Haiku 4.5 | $0.00011 | $0.00128 |
Grade A, and why
web-crawl 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Crawl
Get the user's data by the cheapest reliable path, and never let bulk data flow back into your own context.
Context discipline (the one rule everything else serves)
Your context window is small and shared with page state and screenshots. Bulk data must go to disk, not into your context.
Route by the size of the result you are about to handle:
- > 30000 characters, OR > 500 rows/records → collection mode. The data must be written to disk (via a tool or a generated script). Into your context return ONLY: progress, counts, a sample of at most 20 records, and file paths. Never read the full dataset back.
- Otherwise → observation mode. The result is small enough to hold and present directly.
A stream of records you are accumulating is a dataset, not an answer: once it will cross either threshold, switch to collection mode before it grows — do not first gather everything in context and then decide.
Q1 · Mode
- Observation mode — small result. Read it in the current session and answer directly. Do not create files or write code.
- Collection mode — large result or a growing record set. Locate the data source, write data to disk incrementally, and return only progress / samples / paths.
Q2 · Source (collection mode) — take the cheapest that is complete
Prefer sources in this order; earlier ones are cheaper, more reliable, and scale better:
- A ready file — a page download/export link (Excel, CSV, JSON, PDF, ZIP). Fetch the file directly instead of scraping the DOM; it is already structured and one request wide. If the user needs fields from inside it, download then parse it with a script.
- An internal JSON / XHR API — the request the page itself makes to render data. You are in a real authenticated session: reuse the session's existing cookies, headers, and tokens as observed — copy them into an HTTP client (e.g.
curl_cffi). Do not reconstruct auth from scratch. - Embedded page state — inline JSON the page ships (e.g.
__NEXT_DATA__,window.__INITIAL_STATE__, a<script type="application/json">). Read it once; it often contains the whole list without pagination. - Rendered DOM / browser-driven traversal — last resort. Paginate and write each batch to disk as you go. For tens of thousands of records this is the worst path — exhaust 1–3 first.
What ships with it
3 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.
- 8d ago First seen · 79 lines · 108 tokens per session scan A ffbb45c2214e
web-crawl is a skill published in the GitHub repository KuiChi-x/reverseloom (42 stars, last pushed 7d ago), licensed Apache-2.0. It adds 108 tokens to every session and 1,284 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
browser_harness
../../SKILL.md.
browser-harness
Control a real browser via CDP: clicking, typing, navigation, logged-in sessions, JS-rendered or bot-protected pages. Not for plain HTTP fetches of public content - use curl for those.
skills
Anti-detection browser CLI powered by Camoufox. Browse the web, search, extract data, take screenshots, and crawl pages — all with C++ level fingerprint spoofing that bypasses Cloudflare, Google, and most bot detection systems.
obscura
Operate and validate Obscura for JavaScript page loading, stealth browsing, anti-fingerprinting, tracker blocking, screenshots and visual comparison, CDP automation with Puppeteer or Playwright, screencasting, PDF export, MCP browser interaction, and web extraction. Use when running Obscura against deterministic…
pinchtab
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.