{"uid":"cap_4Scd9bK7otJpYssdZZbZL","slug":"shopify-spy-agentdiet-dev-dom-stripper-web-url-to-agent-ready-tokens-bf8123aa","name":"DOM Stripper — Web URL to Agent-Ready Tokens","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://shopify-spy.agentdiet.dev/v1/dom-stripper)","url":"https://shopify-spy.agentdiet.dev/v1/dom-stripper?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","minLength":1,"description":"Target webpage URL to fetch and distill (or builtin://stripe-docs)"},"html":{"type":"string","description":"Optional raw HTML string to distill directly without fetching"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Distillation mode"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token budget ceiling when mode=budget"}}},"responseSchema":{"type":"object","required":["status","roi_proof","data"],"properties":{"data":{"type":"object","description":"Distilled Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt."},"cache":{"type":"object","properties":{"status":{"enum":["HIT","MISS"],"type":"string"},"cache_key":{"type":"string"},"latency_ms":{"type":"number"}}},"status":{"type":"string","description":"Execution status ('ok')"},"billing":{"type":"object","properties":{"agent_id":{"type":"string"},"payment_method":{"type":"string"},"fee_charged_usd":{"type":"number"}}},"roi_proof":{"type":"object","properties":{"raw_tokens":{"type":"integer"},"tokens_saved":{"type":"integer"},"roi_multiplier":{"type":"number"},"distilled_tokens":{"type":"integer"},"llm_cost_saved_usd":{"type":"number"},"compression_ratio_pct":{"type":"number"}}}}},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.001","displayCostAsset":"USD","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.001/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_bjb2-Mtu0r60Nu526vcnm","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"shopify-spy.agentdiet.dev","brandSlug":"shopify-spy-agentdiet-dev-mpp","brandBaseUrl":"https://shopify-spy.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-readable content using markdown, structured, skeleton, or BM25 budget modes with token-count guarantees","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into clean markdown and keep it under 2000 tokens — use budget mode with 'payment intents' as the focus query so I only get the most relevant sections.","exampleUseCases":[{"title":"Fit docs into LLM context window","prompt":"Grab the Stripe documentation at https://stripe.com/docs/api and compress it into under 1500 tokens using budget mode, focusing on 'refund API' so I only get the relevant parts."},{"title":"Extract structured product data from a Shopify page","prompt":"Pull https://example-store.myshopify.com/products/sneakers and distill it in structured mode so I get the product tables, metadata, and pricing as clean JSON."},{"title":"Get a skeleton outline of a competitor landing page","prompt":"Fetch https://competitor.com and give me a skeleton outline of their homepage — just the headings and section structure, nothing else."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","max_tokens below minimum of 20 returns validation error","BM25 query specified without mode=budget may be ignored","Raw HTML too large may exceed processing limits","Paywalled or bot-blocked URLs may return empty or partial content","Missing required 'url' parameter returns 400 error"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of a webpage before passing it to an LLM, especially when working with large documentation pages, e-commerce product pages, or any URL where raw HTML would blow out a context window. The BM25 budget mode is uniquely suited for targeted extraction when you have a specific topic query and a hard token ceiling. Prefer this over generic scrapers when ROI metrics (tokens saved, compression ratio) matter to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:09.020Z","isFirstParty":false,"canonicalSlug":"shopify-spy-agentdiet-dev-dom-stripper-web-url-to-agent-ready-tokens-bf8123aa"}