WritersLogic Verifiable AI Agent Hub

{
  "protocolVersion": "0.3.0",
  "name": "WritersLogic Verifiable AI Agent Hub",
  "description": "Pay-per-call research, security, legal and finance agents. Every response is a W3C Verifiable Credential with a C2PA-aligned ingredient manifest, payable per call in USDC on Base via x402.",
  "url": "https://agents.writerslogic.com",
  "preferredTransport": "HTTP+JSON",
  "provider": {
    "organization": "WritersLogic",
    "url": "https://writerslogic.com"
  },
  "iconUrl": "https://writerslogic.com/favicon.svg",
  "version": "2.0.0",
  "documentationUrl": "https://writerslogic.com/agents",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "stateTransitionHistory": false,
    "extensions": [
      {
        "uri": "https://github.com/google-a2a/a2a-x402/v0.1",
        "description": "Payment per call in USDC on Base (x402 v2 exact scheme)",
        "required": true
      },
      {
        "uri": "https://www.w3.org/TR/vc-data-model-2.0/",
        "description": "Responses are VCs issued by did:web:agents.writerslogic.com (eddsa-jcs-2022)",
        "required": false
      },
      {
        "uri": "https://c2pa.org/specifications/",
        "description": "C2PA-aligned actions, hash and ingredient assertions on every response",
        "required": false
      }
    ]
  },
  "securitySchemes": {
    "x402": {
      "type": "http",
      "scheme": "x402",
      "description": "Pay per request: send PAYMENT-SIGNATURE (x402 v2) after a 402 challenge."
    },
    "apiKey": {
      "type": "apiKey",
      "in": "header",
      "name": "X-API-KEY",
      "description": "Prepaid/enterprise access."
    }
  },
  "security": [
    {
      "x402": []
    },
    {
      "apiKey": []
    }
  ],
  "defaultInputModes": [
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json"
  ],
  "skills": [
    {
      "id": "lead-enrichment",
      "name": "Autonomous Lead Enrichment",
      "description": "Scrapes a company homepage, deduces its value proposition and buyer persona, and drafts a targeted B2B cold email. Price: 0.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/enrich-lead",
      "tags": [
        "business",
        "lead",
        "enrichment",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"url\":\"https://stripe.com\",\"senderContext\":\"We sell AI-driven chargeback dispute automation for online merchants.\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "contract-auditor",
      "name": "Smart Contract Auditor",
      "description": "Source-level security review of Solidity: pass/warn/fail verdict, 0-100 risk score, severity-ranked findings with exact file:line, exploit scenario and a fix, plus a SARIF 2.1.0 log. Accepts raw code, a list of files, or an on-chain address (verified source is read from Sourcify). A deterministic detector pass (reentrancy ordering, tx.origin, delegatecall, unchecked calls, weak randomness, pre-0.8 arithmetic) runs beside one model review, and every model finding is checked against the source: its quoted snippet must exist and its line is corrected. A pre-audit triage, not a substitute for a manual audit; it cannot see deployed bytecode, off-chain components or economic assumptions, and not_checked lists what was missing. Price: 1.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/audit-contract",
      "tags": [
        "crypto",
        "contract",
        "auditor",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"code\":\"pragma solidity ^0.8.20;\\ncontract Vault {\\n  mapping(address => uint256) public balances;\\n  function deposit() external payable { balances[msg.sender] += msg.value; }\\n  function withdraw() external {\\n    (bool ok, ) = msg.sender.call{value: balances[msg.sender]}(\\\"\\\");\\n    require(ok);\\n    balances[msg.sender] = 0;\\n  }\\n}\",\"contractName\":\"Vault\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "market-predictor",
      "name": "Prediction Market Analyzer",
      "description": "Independent probability that a Polymarket or Kalshi market resolves Yes, checked against the live book. Pass a market (slug, URL, conditionId or Kalshi ticker) and/or news text: the agent reads the rules, end date and best asks, estimates 0-100 with live web search (falling back to model knowledge if search is slow), and returns verdict.action BUY_YES / BUY_NO / NO_TRADE with edge in bps after taker fees, a confidence gate, quarter-Kelly size and sourced factors for and against. Resolved markets return their outcome without a model call. Not financial advice. Price: 0.10 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/predict-market",
      "tags": [
        "crypto",
        "market",
        "predictor",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"market\":\"will-jd-vance-win-the-2028-us-presidential-election\",\"minEdgePct\":5,\"bankrollUsd\":10000}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "arbitrage-lawyer",
      "name": "Cross-Platform Arbitrage & Resolution Rules Lawyer",
      "description": "Finds fine-print divergences between two prediction markets (e.g. Polymarket vs Kalshi), prices basis risk after fees, and returns verdict.action ARBITRAGE_SAFE / LOW_ANNUALIZED_YIELD / BASIS_RISK_TRAP / NO_EDGE / INSUFFICIENT_EVIDENCE with edge in bps, the probability both legs lose, days to resolution, annualized return and Kelly hedge size capped by top-of-book depth. Each market can be given as a Polymarket slug or URL or a Kalshi ticker (rules, best asks and per-leg fees are read live) or as pasted rules and prices (USD per share, 0-1). Every cited clause is checked verbatim against the rules you supplied. If the rules analysis fails after live prices were read, you still get the signed price math as a partial result. Not financial advice. Price: 0.75 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/arbitrage-lawyer",
      "tags": [
        "crypto",
        "arbitrage",
        "lawyer",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"marketA\":{\"platform\":\"Polymarket\",\"title\":\"Will Bitcoin reach $150,000 by December 31, 2027?\",\"resolutionRules\":\"This market will resolve to Yes if any Binance 1 minute candle for BTC/USDT between Jan 1, 2027 00:00 and Dec 31, 2027 23:59 ET has a final High price of $150,000 or higher. Otherwise it resolves to No. The resolution source is Binance BTC/USDT with the 1m candle selected.\",\"yesPrice\":0.31,\"noPrice\":0.7,\"feeBps\":0,\"endDate\":\"2027-12-31T23:59:00-05:00\"},\"marketB\":{\"platform\":\"Kalshi\",\"title\":\"Bitcoin price at the end of 2027: above $150,000?\",\"resolutionRules\":\"If the CF Benchmarks BRTI price at 5:00 PM EST on December 31, 2027 is above $150,000, then the market resolves to Yes. Otherwise it resolves to No. The Source Agency is CF Benchmarks; the value is the average BRTI over the 60 seconds before the expiration time.\",\"yesPrice\":0.22,\"noPrice\":0.79,\"yesFeeBps\":546,\"noFeeBps\":147,\"endDate\":\"2027-12-31T17:00:00-05:00\"},\"minEdgeBps\":100,\"bankrollUsd\":10000}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "heal-scraper",
      "name": "Self-Healing Scraper & DOM-to-JSON Compiler",
      "description": "Synthesizes durable CSS selectors (Cheerio; no XPath) for a target JSON schema, proves them against the live DOM in-request, and returns the extracted data plus a ready-to-run TypeScript Cheerio extractor. Price: 0.40 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/heal-scraper",
      "tags": [
        "developer",
        "heal",
        "scraper",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"url\":\"https://news.ycombinator.com\",\"targetSchema\":{\"type\":\"array\",\"items\":{\"type\":\"object\",\"required\":[\"title\",\"link\"],\"properties\":{\"title\":{\"type\":\"string\"},\"link\":{\"type\":\"string\"},\"points\":{\"type\":\"integer\"}}}},\"previousBrokenSelectors\":{\"title\":\".storylink\"}}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "token-trap-detector",
      "name": "On-Chain Bytecode & Unverified Token Trap Detector",
      "description": "Reads live Base bytecode, proxy slots (EIP-1967/beacon/zeppelinos/EIP-1822/EIP-1167), ERC-20 state, and privileged selectors to score honeypot and rug risk in code: SAFE | CAUTION | HONEYPOT_RUG | INSUFFICIENT_EVIDENCE. Adds honeypot.is buy/sell simulation and GoPlus tax and honeypot flags, disclosed per source, and degrades to a lower-confidence bytecode-only score when they fail. Price: 0.25 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/detect-token-trap",
      "tags": [
        "crypto",
        "token",
        "trap",
        "detector",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"tokenAddress\":\"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "competitor-battlecard",
      "name": "SaaS Pricing & Competitor Battlecard Spy",
      "description": "Reads up to 3 competitor sites (homepage and pricing page, fetched in parallel) and returns a deal battlecard in under a minute: a verdict headline with confidence, pricing tiers whose amounts are checked against the page text, a scenario cost comparison computed in code, hidden fees and limits, landmine questions, objection handling, wedge features and a talk track. If a site or model step fails you get a signed partial result that names what is missing. Pricing is only as current as the public pages; unverified prices are flagged. Price: 1.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/competitor-battlecard",
      "tags": [
        "business",
        "competitor",
        "battlecard",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"ourProductDescription\":\"Acme Support is an AI-first help desk with usage-based pricing ($0.40 per resolved ticket), SSO on every plan, and native Slack and Shopify integrations.\",\"competitorUrls\":[\"https://www.zendesk.com\",\"https://www.intercom.com\",\"https://www.freshworks.com/freshdesk/\"]}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "diff-gatekeeper",
      "name": "PR / Dependency Breaking-Change & Exploit Gatekeeper",
      "description": "Merge gate for a pull request: pass/warn/fail verdict, 0-100 risk score, the top findings with file:line and a fix, drop-in patches, GitHub Checks annotations and a SARIF 2.1.0 log. Accepts a raw unified diff, a GitHub PR, commit or compare URL, or per-file patches. Deterministic scanners (secrets, SQL and command injection, weak crypto, risky package.json changes) run beside a model review for bugs, race conditions and silent API breaks, and every model finding must point at a line inside the diff or it is marked ungrounded and never blocks. Large diffs are reviewed in up to 4 parts and anything beyond is reported as unreviewed. A review aid, not a replacement for tests or human review. Price: 0.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/gatekeep-diff",
      "tags": [
        "developer",
        "diff",
        "gatekeeper",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"gitDiff\":\"diff --git a/src/users.ts b/src/users.ts\\n--- a/src/users.ts\\n+++ b/src/users.ts\\n@@ -10,3 +10,4 @@ export async function findUser(db, req) {\\n-  return db.query('SELECT * FROM users WHERE id = $1', [req.params.id]);\\n+  const id = req.params.id;\\n+  return db.query(`SELECT * FROM users WHERE id = ${id}`);\\n }\\n\",\"context\":\"Refactor user lookup for readability.\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "medical-bill-auditor",
      "name": "Medical Bill Upcoding & Overcharge Slasher",
      "description": "Paste an itemized hospital or physician bill and get a decision first: dispute it or not, the estimated dollars above a defensible price, and a dispute letter ready to send. Flags E/M upcoding, NCCI unbundling, duplicates and unit errors line by line, prices professional claims against the CMS physician fee schedule, checks the No Surprises Act self-pay dispute deadline, and lists the letter's placeholders. Facility-charge benchmarks are model estimates and are labeled as such. Not legal or medical advice. Price: 3.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/audit-medical-bill",
      "tags": [
        "business",
        "medical",
        "bill",
        "auditor",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"facilityType\":\"emergency_room\",\"claimType\":\"professional\",\"coverage\":\"uninsured_self_pay\",\"patientState\":\"TX\",\"visitSummary\":\"Twisted ankle, 40-minute visit, one X-ray, no fracture, given an ACE bandage and ibuprofen.\",\"goodFaithEstimateAmount\":1200,\"billReceivedDate\":\"2026-10-20\",\"lineItems\":[{\"cptOrHcpcsCode\":\"99285\",\"description\":\"ED visit level 5\",\"chargedAmount\":1850,\"units\":1,\"serviceDate\":\"2026-09-14\"},{\"cptOrHcpcsCode\":\"73610\",\"description\":\"X-ray ankle 3 views\",\"chargedAmount\":640,\"units\":1,\"serviceDate\":\"2026-09-14\"},{\"cptOrHcpcsCode\":\"A4570\",\"description\":\"Splint / elastic bandage\",\"chargedAmount\":185,\"units\":1,\"serviceDate\":\"2026-09-14\"},{\"cptOrHcpcsCode\":\"99070\",\"description\":\"Supplies and materials\",\"chargedAmount\":95,\"units\":1,\"serviceDate\":\"2026-09-14\"}]}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "chargeback-fighter",
      "name": "E-Commerce Chargeback Representment Builder",
      "description": "Tells a merchant whether to fight or accept a card dispute: scores win probability against the network rubric for the reason code (Visa, Mastercard, Amex, Discover), runs deterministic Visa CE3.0 eligibility and invalid-dispute checks, computes expected recovery net of the contest fee and days to the deadline, and returns a processor-ready submission (summary under 4,000 characters, evidence fields in dispute-form order, missing items marked NOT AVAILABLE). Uses only supplied evidence and never fabricates it. Not legal advice; the issuer decides. Price: 2.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/fight-chargeback",
      "tags": [
        "business",
        "chargeback",
        "fighter",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"network\":\"visa\",\"reasonCode\":\"13.1\",\"disputeDate\":\"2026-10-20\",\"orderDetails\":{\"orderId\":\"SHOP-10442\",\"amount\":189,\"currency\":\"USD\",\"transactionDate\":\"2026-09-28\",\"items\":[{\"name\":\"Trail running shoes, size 10\",\"quantity\":1,\"unitPrice\":189}],\"shippingAddress\":\"42 Elm St, Austin, TX 78701\",\"productType\":\"physical\"},\"evidence\":{\"trackingNumber\":\"1Z999AA10123456784\",\"carrier\":\"UPS\",\"deliveryConfirmation\":\"Delivered 2026-10-02 14:12, left at front door, 42 Elm St Austin TX\",\"deliveryDate\":\"2026-10-02\",\"avsResult\":\"Y (full match)\",\"cvvResult\":\"M (match)\",\"customerCommunications\":\"2026-10-03 customer email: 'Got the shoes, they run a bit small.'\"}}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "contract-terminator",
      "name": "Dark Pattern Contract & Subscription Exit Lawyer",
      "description": "Paste a contract or Terms URL and get the decision first: send notice by a computed date, or the window has passed. Quotes auto-renewal, notice-window and early-termination traps verbatim, computes the renewal and last-notice dates in code, estimates the renewal cost you avoid from your fee, maps the exit to ROSCA, state automatic-renewal laws and EU/UK consumer law with links, and drafts a notice with its placeholders listed. General information, not legal advice. Price: 1.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/terminate-contract",
      "tags": [
        "business",
        "contract",
        "terminator",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"contractText\":\"This Agreement renews automatically for successive 12-month terms unless either party gives written notice of non-renewal by certified mail at least 60 days before the end of the then-current term. Early termination requires payment of all remaining fees for the current term.\",\"vendorName\":\"Acme Fitness Clubs\",\"userJurisdiction\":\"California\",\"reasonForExit\":\"Moved out of state; signed up online.\",\"customerType\":\"consumer\",\"signupMethod\":\"online\",\"contractStartDate\":\"2026-03-15\",\"monthlyFee\":49.99}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "tariff-engineer",
      "name": "Global Customs & Tariff Engineering Optimizer",
      "description": "Classifies a product under the HTS with GRI reasoning and verifies the code and general (MFN) rate against the live USITC schedule, flags when a specific sibling subheading may outrank the chosen residual one, separates lower-duty options from reclassification risk with dollar exposure, lists lawful physical tariff-engineering changes, and drafts an accurate commercial invoice description. Leads with a decision, the dollars at stake and the next step. Section 301/232/IEEPA add-ons are model estimates and marked unverified. Not legal advice or a binding ruling. Price: 1.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/optimize-tariff",
      "tags": [
        "business",
        "tariff",
        "engineer",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"productName\":\"Women's waterproof ankle boot\",\"materialsBreakdown\":[{\"material\":\"Rubber/plastics outer sole\",\"percentByWeight\":45},{\"material\":\"Polyurethane-coated textile upper\",\"percentByWeight\":40},{\"material\":\"Textile lining\",\"percentByWeight\":15}],\"intendedUse\":\"Everyday wet-weather footwear\",\"originCountry\":\"Vietnam\",\"destinationCountry\":\"United States\",\"customsValueUsd\":85000,\"importStateOfAssembly\":\"fully_assembled\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "patent-design-around",
      "name": "Patent Design-Around & Freedom-to-Operate Architect",
      "description": "Paste patent claims or give a patent number. Splits the independent claims into lettered limitations in code, charts your product against each one (literal and doctrine of equivalents), scores claims under the all-elements rule, and proposes 3 engineering design-arounds that each remove a limitation of every independent claim, checked in code. Leads with a decision and optional dollar exposure. A screening aid, not a freedom-to-operate opinion or legal advice. Price: 2.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/bypass-patent",
      "tags": [
        "legal-ip",
        "patent",
        "design",
        "around",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"patentNumber\":\"US 9,999,999 B2\",\"patentClaimsText\":\"1. A method of notifying a user, comprising: receiving, at a server, a location of a mobile device; determining that the location is within a geofence associated with a merchant; and transmitting a push notification comprising a coupon to the mobile device in response to the determining.\\n2. The method of claim 1, wherein the geofence is circular.\",\"proposedProductDescription\":\"Our app checks the phone's location on-device against a list of nearby store polygons downloaded daily, and shows a local in-app banner with a discount when the user opens the app inside a store area. No location is sent to our servers.\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "accessibility-patcher",
      "name": "ADA / WCAG Lawsuit Shield & DOM Auto-Patcher",
      "description": "Returns a FAIL / REVIEW / PASS verdict for a page's HTML (pasted or fetched from a URL) against the WCAG failures most cited in ADA demand letters: alt text, form labels, unnamed buttons and links, lang, headings, landmarks, skip links, zoom. Each issue carries a CSS selector, source line and fix, with a top-five list, a SARIF 2.1.0 log, a litigation risk score, per-element patched HTML and an interim <script> hotfix. Static HTML only: color contrast, keyboard behaviour and JavaScript-rendered content are not checked, and the output is not legal advice or a conformance claim. If the model patch step fails you still get the full deterministic audit, marked partial. Price: 0.75 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/patch-accessibility",
      "tags": [
        "business",
        "accessibility",
        "patcher",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"html\":\"<html><head><title>Shop</title></head><body><nav><a href=\\\"/\\\"><img src=\\\"logo.png\\\"></a></nav><h1>Running shoes</h1><h3>Bestsellers</h3><img src=\\\"IMG_2041.jpg\\\" alt=\\\"IMG_2041.jpg\\\"><form><input type=\\\"email\\\" placeholder=\\\"Email\\\"><button><svg></svg></button></form></body></html>\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "clarification-impact",
      "name": "Prediction-Market Clarification Impact Pricer",
      "description": "Prices a prediction-market rules clarification as a trade. Given an open Polymarket market (slug, URL or conditionId; Kalshi ticker supported), reads the posted clarification (Additional context) from the UMA adapter on Polygon, or takes your clarificationText to price a pending or hypothetical one. Finds the real-world outcomes whose resolution changed, quotes each changed clause verbatim, shifts fair probability by their ensemble-estimated mass with an adversarial check, walks the live order book at your size after fees and slippage, and returns verdict.action BUY_YES / BUY_NO / EXIT / HOLD / NO_MATERIAL_CHANGE with edge in bps, fractional-Kelly size, confidence and reason_code. Closed markets return HOLD without a model call; if the estimate stage fails you still get the verified scenarios as a partial result. Not financial advice. Price: 0.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/clarification-impact",
      "tags": [
        "crypto",
        "clarification",
        "impact",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"market\":\"will-jd-vance-win-the-2028-us-presidential-election\",\"clarificationText\":\"Clarification: if no person has been inaugurated by January 20, 2029 because the election result is contested or decided by a House contingent election, this market resolves 50-50 rather than to the person eventually seated.\",\"bankrollUsd\":10000,\"sizeUsd\":250}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "legal-cite-verifier",
      "name": "Legal citation and quotation verifier (US case law)",
      "description": "Extracts US reporter citations from a brief (U.S., S. Ct., L. Ed., F., F.2d, F.3d, F.4th, F. Supp., state and regional reporters) and checks each against Harvard's Caselaw Access Project and, when the operator has configured a token, the CourtListener Citation Lookup API. Reports FOUND, MISMATCH (case name, year or circuit differs), NOT_FOUND, AMBIGUOUS, or UNCHECKED with the reason, and never marks an unchecked citation FOUND. Quotations are searched in the cited opinion with deterministic matching and every normalization is listed. Statutes, id., supra and Westlaw/Lexis cites are reported as UNCHECKABLE_TYPE. Without a CourtListener token the result is partial for volumes outside CAP (roughly pre-2019). The optional proposition check is off by default and can only point at a verified passage. Not legal advice. Price: 1.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/legal-cite-verifier",
      "tags": [
        "legal-ip",
        "legal",
        "cite",
        "verifier",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"text\":\"Plaintiff's position follows from Brown v. Board of Education, 347 U.S. 483, 495 (1954) (\\\"Separate educational facilities are inherently unequal.\\\"). Defendant's liability under the Montreal Convention is established by Varghese v. China Southern Airlines Co., Ltd., 925 F.3d 1339 (11th Cir. 2019).\",\"quotes\":[{\"citation\":\"347 U.S. 483\",\"quote\":\"Separate educational facilities are inherently unequal.\"}]}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "milestone-verifier",
      "name": "Grant Milestone Verifier with Signed Release Attestation",
      "description": "Decides whether a grantee met a milestone before a DAO releases the next tranche or stream. Checks GitHub as of the due date (commits, tags, releases, CI, files), npm/PyPI/crates.io publish times, Snapshot proposal state, on-chain deployments (bytecode selector scan through proxies, Sourcify, creation transaction), and URLs; judges the rest with an ensemble plus a skeptical reviewer, reads Sablier Lockup streams on-chain, and returns a decision headline, a per-criterion PASS/FAIL/UNVERIFIABLE verdict, releaseBps, and an EIP-712 signed attestation. Advisory: it never moves funds, and if a source such as GitHub is unreachable those criteria come back UNVERIFIABLE in a signed partial result instead of an error. Price: 2.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/verify-milestone",
      "tags": [
        "crypto",
        "milestone",
        "verifier",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"milestone\":{\"title\":\"Maintenance and ecosystem support\",\"acceptanceCriteria\":[\"A tagged release v0.2.0 is published\",\"A changelog is maintained in the repository\",\"Continuous integration passes on the main branch\",\"Public documentation describes ArbSys and ArbGasInfo local support\"],\"dueDate\":\"2026-02-28\"},\"evidence\":{\"repoUrl\":\"https://github.com/Supercoolkayy/Ox-rollup\",\"ref\":\"main\",\"deployments\":[{\"chain\":\"arbitrum\",\"address\":\"0xaf88d065e77c8cC2239327C5EDb3A432268e5831\",\"expectedFunctions\":[\"transferWithAuthorization(address,address,uint256,uint256,uint256,bytes32,uint8,bytes32,bytes32)\"]}],\"urls\":[\"https://www.ox-rollup.com/docs/01-overview\"]},\"payout\":{\"protocol\":\"sablier\",\"chain\":\"ethereum\",\"streamId\":\"3\",\"lockup\":\"0xcF8ce57fa442ba50aCbC57147a62aD03873FfA73\",\"recipient\":\"0xc616B2449E9765EDF9FFb485Da42420971299519\",\"amountTotal\":\"1000000000000000000000\"},\"releasePolicy\":{\"mode\":\"proportional\"}}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "dispute-ev",
      "name": "UMA Dispute EV Desk",
      "description": "For a Polymarket market inside its roughly two-hour UMA challenge window, reads the live proposal on Polygon (adapter, optimistic oracle, bond, finalFee, expiry), judges P(proposal wrong or too early) against the literal rules with an ensemble plus red-team pass and verified quotes, and computes DISPUTE vs ABSTAIN expected value (bond win/loss, DVM lock cost, gas, your position and reset delay). Returns verdict.action DISPUTE / DO_NOT_DISPUTE / MONITOR_UNTIL with a UTC submit-by deadline, edge in USD and bps of the stake, and the full EV breakdown. Outside a live window it says why (settled, already disputed, no proposal yet) with the proposed and resolved outcome. For a market with no proposal yet, pass proposal.outcome to replay a what-if (mode what_if); the catalog example does this on a long-dated market. Not financial advice. Price: 0.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/dispute-ev",
      "tags": [
        "crypto",
        "dispute",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"market\":\"will-jd-vance-win-the-2028-us-presidential-election\",\"proposal\":{\"outcome\":\"first\"},\"position\":{\"outcome\":\"No\",\"shares\":400,\"avgPrice\":0.83},\"params\":{\"aprOpportunity\":0.15,\"minEdgeUsd\":2}}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "cover-claim",
      "name": "DeFi Cover Claim Adjudicator",
      "description": "Predicts whether a DeFi cover claim (Nexus Mutual or any provider's wording) will be approved and for how much. Reads the wording, postmortems and the claimant's transactions, quantifies net token loss with Chainlink prices at the loss block, maps facts to covered events, exclusions and conditions with verbatim verified clauses, cites similar past claims, and returns verdict.action (FILE / FILE_WITH_MORE_EVIDENCE / DO_NOT_FILE) with calibrated P(approved), expected payout and filing value in the cover asset, an assessor vote (APPROVE/DENY/ABSTAIN) and the missing evidence that would change the verdict. A failed hard gate (cover period, filing window) is decided in code with no model call; if a model stage fails you still get the verified gates, timing and loss valuation as a partial result. Not financial or legal advice. Price: 5.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/cover-claim",
      "tags": [
        "crypto",
        "cover",
        "claim",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"wording\":{\"productName\":\"Pocket Universe\"},\"incident\":{\"description\":\"A transaction of about 2.08 ETH made on the Lido frontend on 2024-10-04 at 11:31:28 UTC was replaced with a plain transfer to a scam address by malware on the user's machine, and Pocket Universe did not flag it as malicious. The claimant cites covered event 3b, malicious sending of funds.\",\"postmortemUrls\":[\"https://forum.nexusmutual.io/t/1538\"],\"occurredAt\":\"2024-10-04T11:31:28Z\"},\"transactions\":[{\"chain\":\"ethereum\",\"hash\":\"0x1b84e51a0b3f682ce7636170f9a18fcb3cc532661c1ce65f9733e2b5ce74a29f\"}],\"claimant\":\"0x760513ef6f45da1964128848f8962c02fb4770c9\",\"cover\":{\"amount\":250000.23,\"asset\":\"USDC\",\"start\":\"2024-09-25T00:00:00Z\",\"end\":\"2024-10-25T00:00:00Z\"},\"claimedLoss\":{\"amount\":5027.91},\"claimDate\":\"2024-10-11T00:00:00Z\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "vault-exit-lawyer",
      "name": "Vault Exit Lawyer",
      "description": "Before moving treasury funds out of an ERC-4626 or ERC-7540 vault: reads the chain at one pinned block and returns how much can exit now, the haircut vs convertToAssets, partial-exit maximum, liquidity coverage, queue/cooldown timing, admin-power flags (upgrade, pause, multisig threshold, timelock), and a verdict EXIT_NOW_FULL / EXIT_PARTIAL / QUEUED / BLOCKED / UNKNOWN. With a holder it simulates redeem via eth_call. Optional docsUrls are checked against the contract for contradictions. All numbers are computed deterministically; the model only reads documentation. Answers in seconds to about a minute; if a data source stalls it returns a signed partial result (partial, missing) that names what was not read instead of timing out. Not financial advice. Price: 0.25 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/vault-exit",
      "tags": [
        "crypto",
        "vault",
        "exit",
        "lawyer",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"chain\":\"ethereum\",\"vault\":\"0xBEEF01735c132Ada46AA9aA4c54623cAA92A64CB\",\"exit\":{\"shares\":\"1000000000000000000000\"}}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "foreignResearchScout",
      "name": "Cross-Lingual Dark Science Arbitrage Scout",
      "description": "Finds scientific work that exists only in non-English literature. Give an English topic, a technical bottleneck, or a paper you know (seedPaper: DOI or arXiv id); the scout plans native-terminology searches in up to 6 languages (default zh, ja, de, fr, ko) across OpenAlex, Crossref, HAL, J-STAGE and Europe PMC, drops works that already have an English twin, and returns up to 8 ranked discoveries. The result leads with a verdict (LEADS_FOUND, WEAK_LEADS, NO_LEADS, INSUFFICIENT_EVIDENCE or PARTIAL), the top pick, its confidence and a concrete next step. Each discovery carries an English title and methodology translation, pattern-extracted quote-verified numeric results, index-sourced institutions, a computed known-in-English risk (OpenAlex English citers and title similarity) and a deterministic 0-100 commercial whitespace score built from a two-sample model judgment of novelty and readiness. Review articles are flagged and ranked below primary studies. Judgments rest on titles and abstracts, not full texts. If an index or the scoring model is unavailable you still get a signed partial result that names what is missing. Not investment, legal or technical due-diligence advice: confirm with the authors before acting. Price: 1.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/mine-foreign-research",
      "tags": [
        "research",
        "foreignResearchScout",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"researchTopic\":\"sulfide solid electrolytes for all-solid-state lithium batteries\",\"targetLanguages\":[\"ja\",\"zh\",\"de\"],\"fromDate\":\"2020-01-01\",\"maxResults\":5}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "arxiv-to-code",
      "name": "arXiv-to-Production Code & Hyperparameter Compiler",
      "description": "Fetches an arXiv paper's full text (ar5iv), selects method, pseudocode, hyperparameter tables and ablations, and returns a core-algorithm summary, hyperparameters each with a source pointer and a verbatim quote verified against the text, ablation warnings with evidence sentences, and one self-contained TypeScript or Python file that is compile/syntax-checked and literal-checked against the extracted values. Falls back to the abstract (lower confidence) when no full-text rendering exists. Answers within about 80 seconds: if the full text or a model stage is slow, it returns a PARTIAL result with partial and missing naming what was not produced, instead of timing out. Leads with status, confidence and nextStep. Generated code is never executed. Price: 1.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/arxiv-to-code",
      "tags": [
        "research",
        "arxiv",
        "code",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"arxivId\":\"1706.03762\",\"targetLanguage\":\"python\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "prior-art-invalidator",
      "name": "Global Prior-Art Patent Invalidator",
      "description": "Screens a patent's claims against scholarly literature published before the priority date (arXiv, OpenAlex, Europe PMC, Crossref, HAL, J-STAGE; English, Chinese, Japanese, German; not patent databases). Give claims plus a priority date, or a patent number to read them from Google Patents. Claims are split into elements in code; every claim-chart quote is verified verbatim against the title or abstract. Returns a headline decision (anticipation likely / obviousness likely / insufficient evidence), a rule-based invalidation score, 102 and minimal 103 paths, and a draft IPR / reexamination brief with [PLACEHOLDERS] for a registered practitioner to review. Abstract-level evidence only; not legal advice. Price: 2.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/find-prior-art",
      "tags": [
        "legal-ip",
        "prior",
        "invalidator",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"priorityDate\":\"2017-06-01\",\"patentClaimsText\":\"1. A method of approximate nearest neighbor search comprising: hashing each data vector with a plurality of locality-sensitive hash functions to generate hash codes; storing the vectors in hash tables indexed by the hash codes; and, for a query vector, retrieving candidate vectors from the buckets matching the query's hash codes and ranking the candidates by exact distance to the query vector.\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "replication-auditor",
      "name": "Scientific Consensus & Replication Failure Auditor",
      "description": "Give a DOI, arXiv id, PMID, URL, title or a free-text claim and get a verdict-first screen of whether the finding has been retracted, contradicted or failed to replicate: ROBUST / CONTESTED / UNREPLICABLE_HYPE / INSUFFICIENT_EVIDENCE with a 0-100 replicationRiskScore, confidence, a DO_NOT_RELY / VERIFY_BEFORE_RELYING / RELY_WITH_CAVEATS action, a one-line headline and a next step. Checks Crossref, Europe PMC and OpenAlex for retraction, expression of concern and correction (a retraction is decided in code with no model call, and the notice is returned as evidence), mines citing works and citation-context sentences from Semantic Scholar, OpenAlex and Europe PMC, and reports scite.ai tallies separately. Every contradicting study carries a verbatim quote verified against the source text. If a source is down the result is still returned, marked partial with the gaps named. Screening aid based on indexed citing literature, not a substitute for reading the papers; not scientific, legal or medical advice. Price: 0.75 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/audit-replication",
      "tags": [
        "research",
        "replication",
        "auditor",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"doi\":\"10.1016/S0140-6736(97)11096-0\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "abandoned-compound-miner",
      "name": "Abandoned Compound & Uncommercialized Trial Miner",
      "description": "Finds shelved drug and biologic candidates worth a second look. Give a disease or target (mines ClinicalTrials.gov for terminated, withdrawn and suspended trials and for completed Phase 1/2 non-industry trials with no later industry Phase 2/3/4 trial), a compound you already have in mind (drug name or ChEMBL id), a trial (NCT id), or a desired material property (literature mode, no trials). Every candidate is screened in code: the stop reason is classified by keyword rules (one fast model call only for an ambiguous reason or a missing mechanism, accepted only with a verbatim quote), ChEMBL and the FDA Orange Book exclude approved, withdrawn and boxed-warning molecules, and any safety, toxicity or drug-versus-placebo adverse-event excess excludes the candidate. The response leads with a verdict (PROMISING, WORTH_INVESTIGATING, WEAK, INSUFFICIENT_EVIDENCE or NO_CANDIDATES), a confidence level, the top pick and a concrete next step, then a Repurposing Dossier per survivor: trials with NCT links, mechanism, shelving reason, safety and dosage facts with quotes, estimated IP window, US regulatory pathway with non-compliant routes flagged, evidence grade, computed concerns and a deterministic de-risk score. If an index or the model is unavailable you still get a signed partial result that names what is missing. The screens can only exclude, never clear a compound, and a registry search misses unregistered and non-US programs. Not medical, legal, patent or regulatory advice. Price: 2.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/mine-abandoned-compounds",
      "tags": [
        "research",
        "abandoned",
        "compound",
        "miner",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"biologicalTargetOrCondition\":\"amyotrophic lateral sclerosis\",\"includeCompletedNoFollowUp\":true,\"maxCandidates\":4}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "unicode-safety-gate",
      "name": "Adversarial Unicode & Trojan Source gatekeeper",
      "description": "Scans a public GitHub repo, a pull request, a unified diff or a list of files for adversarial Unicode with the 19 rules (USC001-USC019) of dcondrey/unicode-safety-check: bidi controls (Trojan Source), invisible and default-ignorable characters, variation-selector and tag-character payloads (Glassworm), private-use code points, homoglyph and mixed-script identifiers, confusable collisions, misplaced BOM and control characters. Leads with a block/warn/pass verdict, a 0-100 risk score, the top locations (file:line:column) grouped so one trick reads as one finding, and the fix; also returns every finding, a SARIF 2.1.0 log for GitHub code scanning, and model-written exploit explanations that are checked against the findings. Findings and verdict come from deterministic rules; only the explanations use a model. Repo scans read up to 1,000,000 characters, shallowest files first, and list what they skipped. Price: 0.25 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/unicode-safety-gate",
      "tags": [
        "developer",
        "unicode",
        "safety",
        "gate",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"files\":[{\"path\":\"src/auth.js\",\"content\":\"const isAdmin = false;\\nif (isAdmin\u202e \u2066// check later\u2069 \u2066) {\\n  grant();\\n}\\n\"}]}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "audit-prose-forensics",
      "name": "Forensic AI-trajectory & prose craft auditor",
      "description": "Deterministic prose forensics: word echoes within 50 words, repeated 3-6-grams, sentence-starter runs, hedge/filter/passive/nominalization density, burstiness, MATTR, Flesch-Kincaid, vocabulary fingerprints, AI syntactic tics (Not X. Y. pivots, verbless fragments, autonomous body parts), optional revision-history trajectory, and an editorial humanization map whose quotes are verified verbatim. Every finding has exact offsets and line:column. The response leads with a verdict bucket, a one-line summary, the top issues (first verbatim example with line:column and a fix) and next steps. English text only. The humanTrajectoryScore is a documented, uncalibrated heuristic, not proof of authorship; do not use it alone to accuse a writer. Price: 1.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/audit-prose-forensics",
      "tags": [
        "research",
        "audit",
        "prose",
        "forensics",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"text\":\"Not a mistake. A choice. Her heart pounded as she stepped inside. Pure silence. She felt that she could really see the room, and it seemed to be somewhat empty. This isn't just a house, it's a home. She made a decision to stay.\",\"revisionHistory\":[{\"timestamp\":\"2026-11-01T09:00:00Z\",\"text\":\"Not a mistake. A choice.\"},{\"timestamp\":\"2026-11-01T09:20:00Z\",\"text\":\"Not a mistake. A choice. Her heart pounded as she stepped inside.\"}],\"genre\":\"fiction\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "crosstalk-deliberate",
      "name": "Crosstalk epistemic swarm & falsification engine",
      "description": "Stress-tests a research question instead of answering it once. Classifies the domain, generates up to 3 independent hypotheses, attacks each with an adversarial falsification pass, checks live literature on arXiv and OpenAlex (plus any papers you supply by arXiv id or DOI; every record content-addressed by sha256), then synthesizes a calibrated answer. The output leads with a headline (status, answer, confidence, open cruxes) and one decisive falsification probe as the next step. Every material statement is a typed ledger entry (FACT, ASSUMPTION, INFERENCE, CONJECTURE, PROPOSAL) with evidence digests; FACT claims lacking a verified retrieved record are downgraded, invented citations are stripped, and the stage transcript is a recomputable sha256 hash chain. Model-generated reasoning over abstracts, not a systematic review; if synthesis fails you still get the hypotheses and critiques, marked HYPOTHESES_ONLY. Runs in about a minute with 5 to 8 model calls. Price: 2.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/crosstalk-deliberate",
      "tags": [
        "research",
        "crosstalk",
        "deliberate",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"question\":\"Does chain-of-thought prompting improve accuracy on multi-step arithmetic in large language models, and does the effect persist at larger scale?\",\"context\":\"Interested in published empirical results, not opinion.\",\"maxHypotheses\":2}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "audit-public-record",
      "name": "OnRecord statutory clock & redaction auditor",
      "description": "Audits an agency's public-records response and leads with a decision (late, redaction problems, incomplete, pending or no violation found). Computes the statutory response deadline and days late (California CPRA, with the court-day calendar and \u00a7 7922.535 extension rules), flags redactions without an exemption citation, passages redacted in one document but readable in another, referenced attachments that were not supplied, and gaps in the document timeline, and drafts a follow-up letter with the controlling Gov. Code sections linked and [BRACKETED] placeholders to fill. Every finding carries UTF-8 byte offsets and SHA-256 hashes of the exact span and the whole document; the narrative may cite only those ids. Other jurisdictions get the document checks but no clock. Not legal advice. Price: 1.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/audit-public-record",
      "tags": [
        "business",
        "audit",
        "public",
        "record",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"jurisdiction\":\"CA_CPRA\",\"requestDate\":\"2026-03-02\",\"responseDate\":\"2026-03-20\",\"agencyName\":\"City of Example Public Works Department\",\"requestReference\":\"PRA-2026-0142\",\"extensionNotices\":[{\"noticeDate\":\"2026-03-10\",\"expectedDate\":\"2026-03-24\",\"reason\":\"VOLUMINOUS_RECORDS\",\"noticeSource\":\"Portal message of 2026-03-10\"}],\"documents\":[{\"name\":\"response-letter.txt\",\"text\":\"Dated March 20, 2026. Records are released in part. Portions marked [REDACTED] are withheld. See attached Exhibit B for the log.\\nPersonnel email on 2025-11-03 follows.\"},{\"name\":\"release-2.txt\",\"text\":\"Email dated 2026-01-15. The manager wrote that Maria Alvarez approved the overtime budget request on Friday afternoon.\"},{\"name\":\"release-1.txt\",\"text\":\"Email dated 2026-01-15. The manager wrote that [REDACTED] approved the overtime budget request on Friday afternoon. Withheld per Gov. Code 7922.000.\"}]}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "warm-memory",
      "name": "WARM verifiable agent memory",
      "description": "Persistent memory for AI agents as a pay-per-call API, no database to run. op=remember stores subject-predicate-object facts (or extracts them from free text; only facts whose subject and object appear verbatim are kept); a newer value for the same subject and predicate supersedes the old one, and the history stays queryable. op=recall searches by BM25 keyword ranking or exact triple pattern, now or as of any past date. op=forget deletes the content and leaves a tombstone; op=explain returns provenance and the supersession chain. Every fact has a ToIP SAID and every write returns a hash-chained receipt (signed when the hub has a signing key). Memory is private to the paying wallet (API-key callers pass a tenantId). Limits: 50 facts and 8,000 characters of text per call, 10,000 live facts per tenant. Retrieval is keyword-based, not semantic embeddings. Price: 0.10 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/warm-memory",
      "tags": [
        "agent-infra",
        "warm",
        "memory",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"op\":\"remember\",\"facts\":[{\"subject\":\"alice\",\"predicate\":\"lives_in\",\"object\":\"Paris\",\"validFrom\":\"2020-01-01\"},{\"subject\":\"alice\",\"predicate\":\"lives_in\",\"object\":\"Berlin\",\"validFrom\":\"2025-01-01\"}]}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "smt-contract-prover",
      "name": "SMT Contract & Policy Logic Prover",
      "description": "Answers a yes/no logic question about contract clauses, IAM/OPA policies or business rules with a solver-backed result and a plain-language headline and next step. Takes clauses or pasted text (or a formal IR directly with zero LLM calls), formalizes them into typed Boolean, integer and rational constraints, then answers \"is P possible\", \"does invariant I always hold\" or \"are any clauses contradictory\" with a pure-TypeScript CDCL(T) solver (exact rational simplex, branch-and-bound, minimal unsatisfiable cores). SAT returns an exact counterexample checked against every original constraint; UNSAT reports the proof statement and the minimal conflicting clause ids; exhausted budgets return UNKNOWN. Natural-language input uses two independent formalizations whose logical equivalence is checked by the solver; disagreements are reported with a distinguishing assignment and lower confidence. Formal elements whose source quote is not in the text are dropped. The proof is exact for the formalization, not for the original wording, and is not legal advice. Price: 2.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/prove-contract-logic",
      "tags": [
        "developer",
        "contract",
        "prover",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"clauses\":[{\"id\":\"C1\",\"text\":\"Any payout request may be approved by a manager.\"},{\"id\":\"C2\",\"text\":\"Payouts above $10,000 require approval by a director.\"},{\"id\":\"C3\",\"text\":\"A manager is never a director.\"}],\"query\":\"Can a payout above $10,000 be approved by a manager?\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "ai-bom-license-resolver",
      "name": "AI-BOM License Chain Resolver for Hugging Face Models",
      "description": "Walks the Hugging Face lineage of up to 10 models (base_model chain, training datasets; at most 30 nodes, 4 generations) and applies a curated, hash-pinned table of license clauses (Apache-2.0, MIT, CC-BY, CC-BY-NC, CC-BY-SA, OpenRAIL variants, Llama 2 / 3 / 3.1 / 3.2 / 3.3, Gemma, Mistral Research License) to each intended use: commercial or not, API, weights or on-prem, fine-tuning, monthly active users, jurisdiction, sensitive fields of use. Per use it returns ALLOWED, CONFLICT or UNDETERMINED with the conflicting nodes, the clause, a verbatim quote, and the license source URL and SHA-256; the unsatisfiable core comes from the hub's deterministic SAT/LRA solver, with no LLM. Unknown, custom, missing or unreadable licenses are UNDETERMINED, never ALLOWED. Not legal advice. Price: 0.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/ai-bom-license-resolver",
      "tags": [
        "developer",
        "license",
        "resolver",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"models\":[\"NousResearch/Hermes-3-Llama-3.1-8B\",\"mistralai/Mistral-7B-Instruct-v0.2\"],\"uses\":[{\"id\":\"api-above-700m-mau\",\"commercial\":true,\"distribution\":\"api\",\"monthly_active_users\":800000000},{\"id\":\"api-below-700m-mau\",\"commercial\":true,\"distribution\":\"api\",\"monthly_active_users\":50000000}]}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "state-model-checker",
      "name": "State Machine Model Checker",
      "description": "Returns PASS, FAIL or INCONCLUSIVE for a finite state machine, protocol, or concurrent routine, with the shortest failing path as readable process.transition steps and a next step. Accepts a formal spec (no LLM), a plain-language workflow, or source code (translated to a spec by an LLM, with every transition quoted from the source and two independent translations compared). A pure TypeScript explicit-state checker explores all interleavings and returns computed verdicts: safety invariants with the shortest counterexample trace, deadlocks, liveness (eventually, always-eventually, leads-to) and livelocks under weak or strong fairness with lasso counterexamples. If the state budget runs out the status is BOUNDED, never a proof. Price: 2.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/check-state-machine",
      "tags": [
        "developer",
        "state",
        "model",
        "checker",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"spec\":{\"name\":\"flag-mutex\",\"vars\":{\"pc\":{\"type\":\"array\",\"size\":2,\"of\":{\"type\":\"enum\",\"values\":[\"test\",\"set\",\"crit\"]},\"init\":\"test\"},\"flag\":{\"type\":\"array\",\"size\":2,\"of\":{\"type\":\"bool\"},\"init\":false}},\"processes\":[{\"name\":\"P\",\"instances\":2,\"fairness\":\"weak\",\"transitions\":[{\"name\":\"test\",\"guard\":\"pc[self] == test && !flag[1 - self]\",\"updates\":[{\"var\":\"pc\",\"at\":\"self\",\"value\":\"set\"}]},{\"name\":\"set\",\"guard\":\"pc[self] == set\",\"updates\":[{\"var\":\"flag\",\"at\":\"self\",\"value\":true},{\"var\":\"pc\",\"at\":\"self\",\"value\":\"crit\"}]},{\"name\":\"exit\",\"guard\":\"pc[self] == crit\",\"updates\":[{\"var\":\"flag\",\"at\":\"self\",\"value\":false},{\"var\":\"pc\",\"at\":\"self\",\"value\":\"test\"}]}]}],\"invariants\":[{\"name\":\"mutualExclusion\",\"expr\":\"!(pc[0] == crit && pc[1] == crit)\"}]}}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "causalReferee",
      "name": "Causal Claim Referee",
      "description": "Referees a causal claim against an observational table (JSON rows, CSV text, or a published contingency table with counts) and leads with a verdict, confidence, whether the claim holds, the crude and adjusted effects with bootstrap intervals, and a concrete next step. Underneath: crude and stratified effects, Mantel-Haenszel pooling, Simpson's-paradox detection, d-separation and backdoor/front-door checks with minimal adjustment sets, g-formula standardization with positivity checks, exact or seeded Monte Carlo permutation tests, and a PC-algorithm check of the DAG against the data. Verdict by code rules; with a caller-supplied DAG no model is called and the result is reproducible. Conclusions hold only under the DAG and no-unmeasured-confounding assumptions, which are listed in the output; this is statistical analysis, not a substitute for a randomized trial. Price: 1.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/prove-causality",
      "tags": [
        "research",
        "causalReferee",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"data\":[{\"treatment\":\"A\",\"stone_size\":\"small\",\"success\":1,\"n\":81},{\"treatment\":\"A\",\"stone_size\":\"small\",\"success\":0,\"n\":6},{\"treatment\":\"A\",\"stone_size\":\"large\",\"success\":1,\"n\":192},{\"treatment\":\"A\",\"stone_size\":\"large\",\"success\":0,\"n\":71},{\"treatment\":\"B\",\"stone_size\":\"small\",\"success\":1,\"n\":234},{\"treatment\":\"B\",\"stone_size\":\"small\",\"success\":0,\"n\":36},{\"treatment\":\"B\",\"stone_size\":\"large\",\"success\":1,\"n\":55},{\"treatment\":\"B\",\"stone_size\":\"large\",\"success\":0,\"n\":25}],\"countColumn\":\"n\",\"treatment\":\"treatment\",\"outcome\":\"success\",\"covariates\":[\"stone_size\"],\"treatedValue\":\"B\",\"claim\":\"Treatment B causes a higher recovery rate than treatment A.\",\"claimDirection\":\"positive\",\"dag\":{\"edges\":[{\"from\":\"stone_size\",\"to\":\"treatment\"},{\"from\":\"stone_size\",\"to\":\"success\"},{\"from\":\"treatment\",\"to\":\"success\"}]}}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "sequence-identifier",
      "name": "Integer Sequence Identifier",
      "description": "Identifies an integer sequence from terms (a JSON array or pasted text), an OEIS A-number, a safe-parsed formula or recurrence, or a description, and leads with a verdict, confidence, A-number, formula, next terms and a next step. Searches the OEIS directly, then superseeker-style (differences, partial sums, gcd, ratios, binomial, Euler, leading terms, plus a search without the last two terms to flag disagreeing terms) under an 8-search budget, aligns offsets, and marks which terms agree or disagree. Fits linear recurrences and polynomials exactly over the rationals and reports one only when it predicts held-out terms. Candidates are ranked in code; a model is used only for a description input (one fast call, OEIS confirms what it proposes) and for the optional explain sentence (one more call, quote verified against OEIS text). Output carries the CC BY-SA 4.0 OEIS attribution. Price: 0.10 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/identify-sequence",
      "tags": [
        "research",
        "sequence",
        "identifier",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"terms\":[1,1,2,5,14,42,132,429,1430,4862]}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "future-work-miner",
      "name": "Open Research Opportunity Miner",
      "description": "Leads with a verdict (OPEN_GAPS_FOUND, NO_CLEAR_OPEN_GAPS or NO_GAPS_EXTRACTED), a confidence, a headline naming the top gap with its quoted evidence, and the next step. Collects papers for a topic or seed list (arXiv ids or URLs, DOIs, PMIDs; arXiv and OpenAlex search), reads full text from ar5iv or Europe PMC, and extracts future-work, limitation and open-question sentences in code with exact section spans. Near-duplicates are clustered across papers, then each cluster is checked against later citing works (OpenAlex cites, Semantic Scholar citation contexts) and marked OPEN, POSSIBLY_ADDRESSED or ADDRESSED. Scores combine recurrence across independent author groups, recency, citation momentum and openness with documented formulas. mode \"fast\" makes zero model calls; the default makes two (cluster wording, addressed judgment) and lets them move a status at most one level. OPEN means no scanned citing paper covered the theme, not that nobody has: the check reads titles, abstracts and citation contexts of up to a few hundred citing works, not their full text. Papers without open full text contribute only abstracts. Price: 1.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/mine-future-work",
      "tags": [
        "research",
        "future",
        "work",
        "miner",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"query\":\"parameter-efficient fine-tuning of large language models\",\"maxPapers\":8,\"mode\":\"fast\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "reference-verifier",
      "name": "Bibliography Reference Verifier",
      "description": "Checks every reference in a bibliography against Crossref, OpenAlex, arXiv and Europe PMC and leads with a verdict (FIX_REQUIRED, REVIEW_RECOMMENDED, INCOMPLETE or ALL_VERIFIED), a confidence, a one-line headline, the next step and a prioritized fix list. Input: BibTeX, LaTeX \\bibitem, a plain-text list (APA, IEEE, Vancouver), an arXiv id (read via ar5iv), a PDF URL, or just a list of DOIs, arXiv ids and PMIDs. Each reference is VERIFIED, METADATA_MISMATCH (field-level year, author, title, venue and DOI diffs), DOI_RESOLVES_TO_DIFFERENT_WORK, NOT_FOUND (likely fabricated or mistyped), RETRACTED or HAS_CORRECTION (Crossref updated-by, OpenAlex is_retracted, Europe PMC notices), PREPRINT_NOW_PUBLISHED (with the version of record), DUPLICATE_ENTRY or UNRESOLVABLE (an index was down; reported as a partial result, never as NOT_FOUND). With manuscript text, unresolved \\cite keys and uncited entries are reported. All verdicts are computed in code with zero model calls; checkSupport adds one fast-tier call judging whether each cited abstract supports its citing sentence, both quotes verified. Limited to indexed works: books, theses, standards and web pages are often NOT_FOUND or UNRESOLVABLE, and a clean result is not an endorsement of the cited claim. Price: 1.50 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/verify-references",
      "tags": [
        "research",
        "reference",
        "verifier",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"references\":\"[1] Wakefield AJ, Murch SH, Anthony A, et al. Ileal-lymphoid-nodular hyperplasia, non-specific colitis, and pervasive developmental disorder in children. Lancet. 1998;351(9103):637-41.\\n[2] Abbott BP, et al. Observation of gravitational waves from a binary black hole merger. arXiv:1602.03837\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "dependency-advisor",
      "name": "Dependency Underuse & Replacement Advisor",
      "description": "Audits the dependencies of a public GitHub repo, commit or pull request (or uploaded manifests and sources) and returns a pass/warn/fail verdict, a 0-100 risk score, the top findings with manifest file:line and the fix, and a SARIF 2.1.0 log for GitHub code scanning. Parses JS/TS, Python and Rust imports with a tokenizer-level scanner and maps them to declared npm, PyPI and crates.io dependencies. Flags unused, dev-only, undeclared and trivially used packages; checks deps.dev, the npm registry and OSV for deprecation, advisories, staleness and OpenSSF Scorecard; matches a cited table of platform replacements (fetch, crypto.randomUUID, optional chaining) and ranks alternatives in code by Scorecard, recency, dependents, size and license compatibility. Reads repos through GitHub's API and falls back to the source archive when the API is rate limited; when some lookups still fail, it returns a signed partial result that lists what is missing. At most one optional model call maps used symbols to a replacement; deterministic mode makes none. Advisory data comes from OSV and deps.dev and can lag; findings are leads to verify, not a certification. Price: 1.00 USDC. Endpoint: POST https://agents.writerslogic.com/api/v1/audit-dependencies",
      "tags": [
        "developer",
        "dependency",
        "advisor",
        "x402",
        "verifiable"
      ],
      "examples": [
        "{\"repo\":\"star7th/htq\",\"mode\":\"auto\"}"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]


… truncated here: the card is 157,142 characters as printed. The complete card is published at https://agents.writerslogic.com/.well-known/agent-card.json.