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 omnigentx/jarvis --skill crawlinggit clone --depth 1 https://github.com/omnigentx/jarvisWrote 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/omnigentx/jarvis/crawling)<a href="https://agentmods.dev/skills/omnigentx/jarvis/crawling"><img src="https://agentmods.dev/badge/skills/omnigentx/jarvis/crawling/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/omnigentx/jarvis/crawling"><img src="https://agentmods.dev/badge/skills/omnigentx/jarvis/crawling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.00855 |
| Opus 5.5 | $0.00027 | $0.00342 |
| Sonnet 5.5 | $0.00014 | $0.00171 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
crawling 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 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.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STORY CRAWLING WORKFLOW (recipe-based, AI-driven)
You analyse page STRUCTURE and emit a small RECIPE. The backend worker enumerates every chapter from that recipe and downloads them — the chapter list never passes through you, so this scales to 1000+ chapter stories without burning tokens.
Decision Tree
Add new story → has URL? use it : search_stories(query)
Check progress → get_crawl_status(job_id)
View library → local_list_stories()
Step 0: GET A URL
- User gave a URL → use it directly (skip search).
- No URL → serpapi (Google search, fast) to find the story page. scrapling
is for fetching a known URL, not searching. (Legacy
web_search_storiesis a slow per-site HTTP fallback — avoid unless serpapi is down.)
Step 1: DETECT STRUCTURE
detect_story_structure(url) renders the page (JS-aware) and returns, all
LANGUAGE-AGNOSTIC:
link_patterns: same-domain links grouped by URL shape (digits→#) with counts +within_story_rootflag +selector_hint. A high-count within-story pattern = the chapter links.content_candidates: scored by paragraph density (pick narrative, not nav).pagination_hints,story_root_guess.
Step 2: BUILD RECIPE (JSON)
- LIST mode (page lists many chapters):
{mode:"list", story_root:"/slug/", overview_url, chapter_url_pattern:"<sample chapter URL>", content_selector, title_selector, next_page_selector?} - CHAIN mode (single chapter page + a "next" link):
{mode:"chain", story_root:"/slug/", first_chapter_url, next_chapter_selector, content_selector, title_selector} story_rootis REQUIRED in both — the same-story guard that blocks drift into recommended/other stories.- Find
content_selectoron a CHAPTER page (overview pages have no chapter body). Re-run detect_story_structure on a sample chapter URL if needed.
Step 3: VERIFY — MANDATORY (3 chapters)
verify_chapters(recipe_json) fetches the first 3 chapters and checks length,
that chapters differ, and URL continuity.
- ok=false → read
issues, fix the recipe (usually content_selector), re-verify. - NEVER crawl an unverified recipe.
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 · 73 lines · 68 tokens per session scan A 7e2069d3b921
crawling is a skill published in the GitHub repository omnigentx/jarvis (39 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 855 once invoked, about $0.0003 per session on Opus 5.5. 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
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…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
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.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…