web-crawler

web-crawler is an agent for coding agents from hesedcasa/sdkck. It costs 53 tokens per session (508 once invoked), scanned A, original, Apache-2.0.

A web crawler that follows links on API documentation sites and collects endpoint text. It is used only by the extract skill when documentation spans multiple pages.

In plain words
What is it for?
Use it to crawl relevant internal API, reference, route, or schema pages up to three link levels and 30 pages.
Why use it?
It gathers information spread across linked documentation pages so API endpoints can be processed together.

Agent

Install

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.

agentmods
npx agentmods add agents/hesedcasa/sdkck/web-crawler
Clone the repo
git clone --depth 1 https://github.com/hesedcasa/sdkck

Wrote 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.

agentmods badge for web-crawler

README.md
[![agentmods](https://agentmods.dev/badge/agents/hesedcasa/sdkck/web-crawler.svg)](https://agentmods.dev/agents/hesedcasa/sdkck/web-crawler)
Your own site
<a href="https://agentmods.dev/agents/hesedcasa/sdkck/web-crawler"><img src="https://agentmods.dev/badge/agents/hesedcasa/sdkck/web-crawler.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 508 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.00508
Opus 5 $0.00026 $0.00254
Sonnet 5 $0.00011 $0.00102
Haiku 4.5 $0.00005 $0.00051

Measured 4d ago against content hash 2a7ccd41f2ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-crawler 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

tools: WebFetch, Read, Write, Bash(curl:*)
plugins/api/agents/web-crawler.md · 53 lines

What it actually says

You are a focused API documentation crawler. Your only job is to follow links on documentation sites and collect raw text content for API endpoint analysis. Do not perform analysis yourself — just collect and return the documentation.

Instructions

You will be given a starting URL for an API documentation site.

Phase 1 — Fetch the starting page

Fetch the starting URL with WebFetch. Collect:

  • The page's full text content
  • All hyperlinks found on the page

Phase 2 — Identify documentation links

From all links on the page, keep only internal links (same domain). Prioritize URLs whose paths contain:

  • /api/, /reference/, /endpoint, /resource/, /operation/
  • /v1/, /v2/, /v3/, /rest/, /graphql/
  • /docs/, /guide/, /methods/, /routes/

Skip URLs containing any of: login, signup, pricing, blog, changelog, support, contact, terms, privacy, status. Also skip fragment-only links (e.g. #section).

Phase 3 — Crawl recursively

Fetch the prioritized internal links. Follow their links one level further (depth 2), then one more level (depth 3). Stop at depth 3 from the starting URL.

Hard limits:

  • Maximum 30 pages total across all depths
  • Stop early if 100 or more distinct API operations (HTTP method + path pairs) have been spotted in the collected text
  • Skip any page whose content exceeds 500 KB

Phase 4 — Return aggregated content

Return a single plain-text block containing all collected documentation. Include:

  • The base API URL if found on any page
  • All HTTP methods and paths discovered
  • Parameter descriptions (path, query, request body)
  • Any request/response schema examples
  • Authentication requirements mentioned

Strip HTML markup. Return text content only. Do not summarize — return the raw documentation text so the extract skill can perform its own analysis.

Changes

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.

  1. 4d ago First seen · 53 lines · 53 tokens per session scan A 2a7ccd41f2ba

Subscribe to this mod's changes

web-crawler is an agent published in the GitHub repository hesedcasa/sdkck (9 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 508 once invoked, about $0.0003 per session on Opus 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.