{"domain":"toll402.dev","count":1,"changes":[{"captured_at":"2026-09-08T03:37:53","card_hash":"6964afa5fc9903a7ac8293d02ffdc3aead63123c1305e44ecdf6c1aa76e2102d","previous_card_hash":null,"diff":{"skills_added":[{"id":"business_details","name":"business_details","description":"Deep profile of a business from its OWN website: crawls up to 5 relevant pages (menu, services, prices, hours, contact, booking) and returns a machine-readable profile — summary, hours (OSM syntax), services with prices, booking channels, payments, languages, social links. First-party data only, cached 30 days per business (force=true re-crawls).","tags":["business","profile","menu","services","hours","local"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"business_search","name":"business_search","description":"Verified local-business directory for agents. Search by city, category, text or proximity; every result carries a dated verification score (0-100), level (unverified/listed/corroborated/verified/owner_verified) and, on request, the evidence behind it. Open data + live checks + owner claims, never scraped review sites.","tags":["business","directory","local","places","verified","trust","curation"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"business_verify","name":"business_verify","description":"Is this business real, and is its contact info live? Give an id, website, phone or name: matches it against the directory and runs live checks now (site up, name on site, phone on site, domain age, phone format). Returns evidence, score and verdict.","tags":["business","verify","fraud","trust","local"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"do","name":"do","description":"One endpoint for everything (OpenRouter-style): describe what you need and pass the input; Toll402 picks the best tool from the whole catalog (built-in, community-forged, external x402 services) and runs it. Tools priced above maxPriceUsd are returned as a match instead of executed.","tags":["router","gateway","auto","any"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"extract_structured","name":"extract_structured","description":"Turn a web page or raw text into JSON that matches YOUR JSON Schema. LLM-powered, schema-constrained output — no parsing needed.","tags":["extraction","llm","json","scraping"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"forge_tool","name":"forge_tool","description":"Create a NEW tool from a description, an input schema and test examples. The code is generated, run in a sandbox against your examples (up to 3 attempts), and on success published as a paid endpoint /v1/t/<name> for every agent. Infinite tools, on demand.","tags":["forge","create","marketplace","codegen","custom"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"fx_rate","name":"fx_rate","description":"Exchange rate between two ISO currencies (ECB reference rates), optionally converting an amount.","tags":["finance","currency","fx"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"judge_output","name":"judge_output","description":"Independent LLM-as-judge: scores a candidate output against a task and criteria (0-100), with pass/fail, issues and suggestions. Use it for self-verification, best-of-N, or QA gates.","tags":["evaluation","llm","quality","judge"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"pdf_to_text","name":"pdf_to_text","description":"Download a PDF from a URL and return its full text, page count and title.","tags":["pdf","documents","text"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"provenance","name":"provenance","description":"Human or synthetic? Provenance evidence for a URL: archive first-capture date, domain age, authorship markup, curated source tier, AI disclosures and stylometric signals, aggregated into a calibrated 0-100 human-origin score with every piece of evidence. Add deep=true for an LLM stylometric assessment.","tags":["provenance","ai-detection","human","synthetic","trust","curation"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"read_url","name":"read_url","description":"Fetch any public web page (or PDF) and return clean, LLM-ready Markdown with title, metadata and links. Boilerplate, ads and scripts removed.","tags":["web","scraping","markdown","reader"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"summarize","name":"summarize","description":"Faithful summary of a URL or text in the style, length and language you choose.","tags":["summarization","llm","reading"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"t/crypto_price","name":"crypto_price","description":"Spot price in USD for a crypto asset symbol using https://api.coinbase.com/v2/prices/<SYMBOL>-USD/spot","tags":["crypto","price","finance"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"t/github_repo_stats","name":"github_repo_stats","description":"Stars, forks, open issues, license and last push for a GitHub repo via https://api.github.com/repos/<owner>/<repo>","tags":["github","code"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"t/hn_top","name":"hn_top","description":"Top N Hacker News stories (title, url, score) via https://hacker-news.firebaseio.com/v0/topstories.json and /v0/item/<id>.json","tags":["news","hackernews"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"t/ip_geolocate","name":"ip_geolocate","description":"Country, region, city, timezone and ASN for an IPv4/IPv6 address via https://ipapi.co/<ip>/json/","tags":["network","geo"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"t/json_schema_validate","name":"json_schema_validate","description":"Validate a JSON value against a JSON Schema subset (type, properties, required, enum, minimum/maximum, minLength/maxLength, items) and return errors","tags":["json","validation"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"t/npm_package_info","name":"npm_package_info","description":"Latest version, description, license, weekly downloads (via api.npmjs.org) and homepage for an npm package","tags":["npm","code"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"t/rss_latest","name":"rss_latest","description":"Parse an RSS/Atom feed URL and return the latest N items (title, link, published)","tags":["rss","news","feeds"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"t/text_stats","name":"text_stats","description":"Word/sentence/paragraph counts, reading time (200 wpm), top 10 keywords (stopwords removed) for a text","tags":["text","nlp"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"t/url_status","name":"url_status","description":"HTTP status, final content-type and response size for a URL (HEAD then GET fallback)","tags":["web","monitoring"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"t/wikipedia_summary","name":"wikipedia_summary","description":"Summary extract and canonical URL for a Wikipedia topic via https://<lang>.wikipedia.org/api/rest_v1/page/summary/<title>","tags":["reference","wikipedia"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"trusted_lookup","name":"trusted_lookup","description":"Answer from TRUSTED sources only (Wikipedia, Wikidata, arXiv, Crossref/DOI, World Bank): returns passages with URL, reliability tier and retrieval time for citation. With synthesize=true you also get an LLM answer that cites the passages and admits when they don't contain the answer.","tags":["research","facts","citations","trusted","reference","science","curation"],"inputModes":["application/json"],"outputModes":["application/json"]},{"id":"verify_email","name":"verify_email","description":"Validate an email address: syntax, MX/A records, disposable-domain, free-provider and role-account detection, with a 0-100 score.","tags":["email","validation","leads"],"inputModes":["application/json"],"outputModes":["application/json"]}],"skills_removed":[],"skills_changed":[],"fields_changed":[{"field":"name","before":null,"after":"Toll402"},{"field":"description","before":null,"after":"The OpenRouter for AI-agent tools: one gateway, one wallet, every capability. Built-in tools, community-forged tools and other x402 services, all paid per call in USDC via x402 (HTTP 402). No signup, no API key."},{"field":"version","before":null,"after":"0.2.0"},{"field":"url","before":null,"after":"https://toll402.dev"},{"field":"documentationUrl","before":null,"after":"https://toll402.dev/llms.txt"}],"other_changed":true,"is_empty":false,"human_summary":"added 24 skills · name ∅ → Toll402 · description ∅ → The OpenRouter for AI-agent tools: one g · version ∅ → 0.2.0 · url ∅ → https://toll402.dev · documentationUrl ∅ → https://toll402.dev/llms.txt"}}]}