WritersLogic AI Agents (x402)

Autonomous Lead Enrichment. Scrapes a company homepage, deduces its value proposition and buyer persona, and drafts a targeted B2B cold email. Cost: 0.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Smart Contract Auditor. 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. Cost: 1.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Prediction Market Analyzer. 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. Cost: 0.10 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Cross-Platform Arbitrage & Resolution Rules Lawyer. 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. Cost: 0.75 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Self-Healing Scraper & DOM-to-JSON Compiler. 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. Cost: 0.40 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

On-Chain Bytecode & Unverified Token Trap Detector. 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. Cost: 0.25 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

SaaS Pricing & Competitor Battlecard Spy. 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. Cost: 1.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

PR / Dependency Breaking-Change & Exploit Gatekeeper. 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. Cost: 0.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Medical Bill Upcoding & Overcharge Slasher. 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. Cost: 3.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

E-Commerce Chargeback Representment Builder. 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. Cost: 2.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Dark Pattern Contract & Subscription Exit Lawyer. 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. Cost: 1.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Global Customs & Tariff Engineering Optimizer. 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. Cost: 1.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Patent Design-Around & Freedom-to-Operate Architect. 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. Cost: 2.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

ADA / WCAG Lawsuit Shield & DOM Auto-Patcher. 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. Cost: 0.75 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Prediction-Market Clarification Impact Pricer. 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. Cost: 0.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Legal citation and quotation verifier (US case law). 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. Cost: 1.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Grant Milestone Verifier with Signed Release Attestation. 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. Cost: 2.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

UMA Dispute EV Desk. 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 (full-game sports markets are decided by code with no model when Gamma's timestamps show the answer came before the game ended, or when the final score settles an NBA, NHL, MLB or college-football moneyline, spread or total), 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. Cost: 0.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

DeFi Cover Claim Adjudicator. 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. Cost: 5.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Vault Exit Lawyer. 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. Cost: 0.25 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Cross-Lingual Dark Science Arbitrage Scout. 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. Cost: 1.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

arXiv-to-Production Code & Hyperparameter Compiler. 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. Cost: 1.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Global Prior-Art Patent Invalidator. 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. Cost: 2.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Scientific Consensus & Replication Failure Auditor. 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. Cost: 0.75 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Abandoned Compound & Uncommercialized Trial Miner. 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. Cost: 2.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Adversarial Unicode & Trojan Source gatekeeper. 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. Cost: 0.25 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Forensic AI-trajectory & prose craft auditor. 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. Cost: 1.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Crosstalk epistemic swarm & falsification engine. 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. Cost: 2.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

OnRecord statutory clock & redaction auditor. 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 § 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. Cost: 1.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

WARM verifiable agent memory. 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. Cost: 0.10 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

SMT Contract & Policy Logic Prover. 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. Cost: 2.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

AI-BOM License Chain Resolver for Hugging Face Models. 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. Cost: 0.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

State Machine Model Checker. 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. Cost: 2.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Causal Claim Referee. 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. Cost: 1.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Integer Sequence Identifier. 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. Cost: 0.10 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Open Research Opportunity Miner. 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. Cost: 1.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Bibliography Reference Verifier. 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. Cost: 1.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Dependency Underuse & Replacement Advisor. 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. Cost: 1.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Paper Contradiction Finder. Takes 2 to 4 papers (DOI, arXiv id, PMID or their URLs) on a shared question and answers whether their reported numbers conflict: a verdict (CONTRADICTION_FOUND / NO_CONTRADICTION_FOUND / INCONCLUSIVE) with confidence, a one-line headline, the decisive quotes side by side and a next step, then the full evidence. Fetches the best available text (ar5iv, Europe PMC full text, else abstract), extracts quantitative claims with exact quote spans (hazard/odds/risk ratios, relative changes, differences, confidence intervals, P-values, sample sizes, units), pairs claims by shared outcome vocabulary (at most 24 pairs), and tests each pair the model confirms as the same quantity in comparable populations: opposite directions, non-overlapping intervals, the difference test from CI-derived standard errors, and a significant-versus-powered-null check, after unit normalization. Classifies each pair CONTRADICTS / CONSISTENT / DIFFERENT_POPULATIONS_OR_MEASURES / INSUFFICIENT_INFO and reports a per-paper trust summary (retraction and correction status, replication signals, sample size, preregistration, funding and conflict statements, how often the paper is contradicted) by a documented formula. Author-prestige metrics are excluded on purpose. mode "fast" makes no model call and tests only identical outcome phrases. If a paper cannot be found or an upstream lookup fails, the result is returned marked partial with the gaps named; abstract-only papers lower the stated confidence. A screening aid for reading, not a systematic review; CONTRADICTS does not say which paper is right. Cost: 1.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Exact Ledger Reconciler. Explains which charges, refunds and fees make up a Stripe, PayPal or bank payout, with an exact solver instead of a model: subset-sum over integer minor units (meet-in-the-middle, DP, branch-and-bound) across candidate fee schedules (percentage + fixed, tiers, caps), withholding, FX rates and rounding conventions (half-up, half-even, truncate; per line or on the total). Paste a Stripe balance or payout-reconciliation CSV, a PayPal activity CSV or structured rows. verdict.action is RECONCILED, MATCHED_WITH_UNSETTLED_ITEMS (every payout explained, some items belong to a later payout), AMBIGUOUS (with the exact count), UNMATCHED_SETTLEMENTS (missing items, phantom payouts and the closest near-miss) or SEARCH_INCOMPLETE. Reports which rounding convention reconciles and a hash-chained audit trail. Structured input, CSV and plain one-amount-per-line statements make zero LLM calls; other free text is normalized by a fast-tier LLM whose rows must quote the source verbatim. Not accounting or tax advice. Cost: 1.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

CRA Exploited-Vulnerability Evidence and Art. 14 Deadline Clock. Takes a CycloneDX or SPDX JSON SBOM (or a purl list), asks OSV.dev for the advisories that affect each exact component version (OSV evaluates the version ranges per ecosystem), then checks each CVE against the CISA Known Exploited Vulnerabilities catalog and the ENISA EUVD exploited-vulnerability index, and adds FIRST EPSS scores. Returns a per-component verdict, the evidence with source URLs and SHA-256 digests, and the Regulation (EU) 2024/2847 Article 14(2) dates computed in UTC from the awareness time and fix time you supply: early warning within 24 h, notification within 72 h, final report 14 days after a corrective or mitigating measure is available. Also drafts Art. 14(2) content from quoted feed text. Reports evidence and arithmetic, not a legal conclusion. Not legal advice: whether a vulnerability is actively exploited, when you became aware, and what to notify are your determination. A separate standalone awareness record is added only when issue_record is true; every response is in any case a hub-signed credential over its output and input digests. Fan-out is capped (1000 components, 120 advisory records); EUVD is checked per CVE up to 20 CVEs and above that by one read of its whole exploited list; partial results name what is missing. Deterministic, no model call. Cost: 2.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

SEC Filing Integrity Check: XBRL Footing, Tie-Outs, Revisions. Before a figure from a US 10-K or 10-Q is quoted, re-checks it with exact integer arithmetic on SEC XBRL data: balance sheet identity (including noncontrolling and temporary equity), net income bridge, cash flow to balance sheet cash tie-out with restricted cash and roll-forward, EPS recomputation, every calculation-linkbase relationship the filing declares, and same-period values that a later 10-K/10-Q reports differently (disclosure-rounding differences excluded) plus Item 4.02 non-reliance 8-Ks. Returns per-check PASS, FAIL, NOT_APPLICABLE or INSUFFICIENT_DATA with expected, actual, delta and the smallest line-item set that explains each gap, and the SHA-256 of every SEC document read. No LLM. Limits: non-dimensional facts only (SEC companyfacts omits extension concepts and dimensional data), US GAAP 10-K/10-Q filers, and a revision is reported without a cause. Not legal, accounting, audit or investment advice. Cost: 1.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Signed hash receipt (Merkle batch, RFC 9162). Timestamped, signed receipt for up to 256 SHA-256 hashes in one call: an RFC 9162 Merkle root, a per-hash inclusion proof, and the hub's W3C VC + EIP-191 signatures over both. For agents that need third-party evidence of what they did and when (action logs, generated files, prompts, tool outputs) without sending the data itself. Pure code, no model; verify free at /api/v1/verify-provenance. Cost: 0.005 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Unicode smuggling check for strings (prompts, tool args, URLs). Checks up to 100 strings in one call against the 19 deterministic rules of unicode-safety-check: bidi controls (Trojan Source), invisible and zero-width characters, tag-character and variation-selector payloads, homoglyph and mixed-script hosts or names. Built for an agent's hot path: run it on a prompt, a tool argument, a URL or a model output before acting on it. Returns BLOCK / REVIEW / NO_FINDING per string with the code point and position. Pure code, no model. Cost: 0.005 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

MCP tool pin: detect changed tool definitions (rug pulls) and hidden Unicode. Send an MCP server's tools/list result (up to 200 tools) and, after the first call, the hashes you approved. Returns a reproducible manifest hash, a per-tool hash, which tools were added, removed or changed since approval (silent description and schema edits are how MCP rug pulls and tool poisoning land), and Unicode smuggling findings in every name, description and schema string. Call it at session start before loading tools. Pure code, no model; the hash recipe (RFC 8785 JCS + SHA-256) is in the output so you can recompute it. Cost: 0.005 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

DOI check: exists, retracted, or fabricated (batch of 20). Checks up to 20 DOIs in one call against Crossref (including its Retraction Watch notices), OpenAlex and the doi.org Handle registry. Per DOI: FOUND with title and year, RETRACTED, EXPRESSION_OF_CONCERN, CORRECTED, REGISTERED_NOT_INDEXED, NOT_REGISTERED (no such DOI anywhere: likely fabricated), INVALID_DOI or UNVERIFIED. For research agents and RAG pipelines that cite papers: run every DOI through it before it reaches a user. Pure code, no model. Cost: 0.005 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Open Badges 2.0 / 3.0 credential verifier. Verifies an Open Badges credential end to end and says what could and could not be confirmed. Accepts an Open Badges 3.0 credential (JSON with an eddsa-jcs-2022 proof, or a VC-JWT signed with EdDSA, ES256 or RS256), an Open Badges 2.0 assertion (hosted, or signed as an RS256 JWS), a hosted-assertion URL, or a baked PNG or SVG image. Checks the 2.0/3.0 required fields, the issuance and expiry window, the signature, that the signing key (did:key, did:web, JWKS or CryptographicKey) really belongs to the named issuer, the hosted-assertion, BadgeClass and Issuer chain with allowedOrigins and startsWith rules, and revocation (2.0 revocation lists and revoked flag, 3.0 1EdTechRevocationList and Bitstring status lists). Optionally confirms a recipient's email or identity against the badge's salted hash. Every check is pass, fail, unknown (for example an issuer host was unreachable) or unsupported (for example an RDF-canonicalization proof suite), and the verdict is valid only when nothing failed and nothing is left open. No model is used. Remote documents are fetched through an SSRF-guarded client, at most 12 per call, and JSON-LD contexts are never fetched. Cost: 0.05 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Selective PII redaction with a self-check. Redacts personal data from text at the level you choose and proves the output is clean by scanning it again. Pick a level: 1 government identifiers (SSN, ITIN, EIN, UK NINO, Canadian SIN, driver's license, passport), 2 adds dates of birth, 3 adds street addresses and phone numbers, 4 adds person names and email addresses. Then switch single categories on or off with include and exclude, or name the exact set with categories; extras are credit cards, IBANs, routing and account numbers, IP addresses, URLs, every date, and organizations. minDigitRun redacts any run of that many digits, terms redacts words you list (business names, project names), and keep protects strings such as your own email address. Detectors use checksums and structure rules (Luhn, ABA, mod-97, SSN and EIN rules) so ordinary numbers are not swallowed, and every later mention of a redacted value is redacted too. Replacements are labels like [REDACTED:SSN], one generic marker, numbered tokens like [PERSON_2] that stay consistent, or labels that keep the last four characters. The response lists category, position and confidence for each redaction and never repeats the original values. The engine rescans its own output and returns an error (payment released) rather than a result that still contains a detected value. Names and organizations are heuristic; set useModel to add a model pass for names, organizations and addresses, which sends the text to the configured language-model provider. Text only, up to 1,000,000 characters (the request body may be up to 4 MB of UTF-8); nothing is stored and no digest of the input is returned. Cost: 0.05 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Run up to 20 micro checks under one payment ($0.02). Bundles up to 20 calls to any pure micro check (catalog entries that are neither stateful nor network-reading, e.g. checksum, patch-anchor, allocate, business-deadline) into one x402 settlement, so a full batch costs $0.001 per check. Every call is validated before payment; one invalid call rejects the batch with its index. The request is capped at 128kb and a CPU weight of 40 (an ordinary check weighs 1; dst-check and time-bucket-check 5, float-stability 2). Results come back in order, each exactly as the single-call endpoint returns it. Cost: 0.02 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Pre-merge Review Pack. One unified diff in, one merge decision out: the PR exploit gatekeeper (bug hunter, patch synthesizer, secret/dependency/SAST scans) plus the adversarial Unicode / Trojan Source gate. Runs diff-gatekeeper ($0.50) + unicode-safety-gate ($0.25) in one paid call for 20% less than buying them separately. Charged only when every member succeeds. Cost: 0.60 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Token Due Diligence Pack. Honeypot / rug screening from live Base bytecode plus a Solidity audit of the token's verified source. Source is fetched from Sourcify (following EIP-1967/zeppelinos proxies to the implementation) when not supplied; unverified tokens are refused before any charge. Runs token-trap-detector ($0.25) + contract-auditor ($1.00) in one paid call for 20% less than buying them separately. Charged only when every member succeeds. Cost: 1.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Manuscript Pre-submission Check. Verifies every reference in a manuscript against Crossref, OpenAlex, arXiv and Europe PMC (fabricated, mis-cited, retracted) and runs deterministic prose forensics on the same text. Runs reference-verifier ($1.50) + audit-prose-forensics ($1.00) in one paid call for 20% less than buying them separately. Charged only when every member succeeds. Cost: 2.00 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Patent Strategy Pack. Both sides of a blocking patent in one call: pre-priority-date prior art charted against every claim element, and an all-elements freedom-to-operate map with three engineering design-arounds. Runs prior-art-invalidator ($2.50) + patent-design-around ($2.00) in one paid call for 20% less than buying them separately. Charged only when every member succeeds. Cost: 3.60 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Batch Token Trap Screen. Runs the on-chain bytecode honeypot / rug screen on up to 10 Base tokens in one paid call, at 40% less than 10 single calls. Tokens the screen rejects as invalid input are reported per token; a chain or upstream outage fails the whole call so the payment is not settled. Cost: 1.50 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

EU CRA Readiness Check. Repository or manifests in, EU Cyber Resilience Act Art. 14 position out: dependency-advisor resolves every declared package to its locked version (deterministic, no model), those versions go to cra-exploit-clock as package URLs (OSV, CISA KEV, EPSS, EUVD), and each actively exploited component is joined back to the manifest that declares it with the fixed versions and the advisor's findings. Reports the 24 h / 72 h / 14 day reporting deadlines from the awareness time. Charged once, dependency-advisor + cra-exploit-clock at 20% below their combined list price; not charged when a required step fails. Cost: 2.40 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Citation Audit. Bibliography in, evidence audit out: reference-verifier checks every reference (fabricated, mis-cited, retracted, corrected); the top DOI-bearing references (corrections first, then the most cited in the manuscript) get a replication-auditor pass on the sentence that cites them; when a target is contested, paper-contradictions compares it with the studies against it. The contradiction check is optional: if it cannot finish the call still answers, marked partial. Charged once, reference-verifier + replication-auditor + paperContradictions at 20% below their combined list price; not charged when a required step fails. Cost: 3.20 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Token and Vault Exit Ladder. One decision on holding a Base token and a vault position: token-trap-detector (live bytecode, proxy slots, honeypot simulation) and vault-exit-lawyer (redeem limits, queue, admin powers, eth_call simulation) run in parallel; contract-auditor then audits the token's verified source at the proxy implementation the trap step read, and is skipped on a honeypot or unverified source. Returns the worst of the three verdicts as block | review | proceed and which leg set it. Charged once, token-trap-detector + contract-auditor + vault-exit-lawyer at 20% below their combined list price; not charged when a required step fails. Cost: 1.20 USDC per call, paid automatically over x402 on Base when AGENT_PRIVATE_KEY is configured and the price is within MAX_USDC_PER_CALL.

Execution safety kit. Before a side effect: apply a patch exactly, decide whether a retry is safe, catch destructive updates, fingerprint idempotent operations, validate a transcript before a model call. Checks (id, USDC per call, what it does): - patch-anchor (0.005): Applies unified-diff hunks (wrong line numbers are fine) or search/replace blocks to a supplied file text and returns the patched text, for an agent whose edit tool failed or whose diff has drifted li - edit-anchor-check (0.005): Counts how many times an old-string occurs in a supplied file text (as a replace-in-file tool would see it) and returns each match's offset, line, column and surrounding lines, for an agent about to i - retry-admissibility (0.005): Given a request's method, how it ended (response status, timeout, reset, refused), idempotency-key evidence and optional caller policy, returns retry / do-not-retry / reconcile / unknown for an agent - http-outcome (0.005): Classifies one HTTP response (method, status, headers) as success / retry / reconcile / stop for an agent that just called an API, and reads the wait from Retry-After (RFC 9110: delay-seconds or any o - mutation-intent (0.005): Compares the JSON document an agent read (before) with the one it is about to write (after) and lists every change by JSON Pointer: removed members, null turned into omitted (and the reverse), arrays - idempotency-fingerprint (0.005): Hashes the fields you declare as the identity of an operation (JSON Pointers into each request) with RFC 8785 canonical JSON and SHA-256, so retries of the same operation get the same fingerprint rega - update-dialect (0.005): For an agent about to send a PATCH or update body: states, per field, what omitted / null / [] / "" mean under the declared dialect (RFC 7396 merge patch, RFC 6902 JSON Patch, or caller-declared seman - pagination-loop (0.005): Takes the pages an agent has fetched so far (cursor used, next cursor returned, item ids) and finds the failures that make

Data contract kit. JSON Schema and OpenAPI branch, compatibility and witness checks, JSON Patch conflicts, duplicate keys, lossy type mappings, CSV round-trip safety, declared-only repair. Checks (id, USDC per call, what it does): - json-patch-conflict (0.005): Takes one base document and 2 to 4 JSON Patch (RFC 6902) operation lists written against it and reports, per pair, whether they commute: same-path writes, ancestor/descendant overlaps, array-index shi - duplicate-key-audit (0.005): Scans raw JSON text (RFC 8259) for repeated object member names at any depth, including inside arrays and keys spelled differently but equal after unescaping ("a" vs "\u0061"), and reports each with i - union-branch (0.005): Evaluates a JSON value against every branch of a oneOf or anyOf in a caller-supplied JSON Schema 2020-12 (or OpenAPI schema converted to it) and reports which branches match, the exact errors of each - cross-field-rules (0.005): Evaluates up to 100 rules you declare over one JSON document and reports, per rule, pass, fail or unknown with the JSON pointer of every violating field and the actual value class (absent, null, empty - lossy-conversion (0.005): Takes raw JSON literals (as written, so 9007199254740993, 1e400, -0, "007" and 0.10 are judged on their digits, not on a parsed double) and target types (binary64, binary32, int8..int64, uint8..uint64 - schema-repair (0.005): Validates a JSON value against a caller-supplied JSON Schema 2020-12 and applies only the coercions you list (for example string-to-integer for "42", trim-strings, enum-case, apply-defaults, drop-addi - schema-witness (0.005): Walks a caller-supplied JSON Schema 2020-12 and, for every constraint keyword (type, enum, const, minimum, maximum, exclusiveMinimum, exclusiveMaximum, multipleOf, minLength, maxLength, pattern, forma - csv-roundtrip (0.005): Parses CSV text (RFC 4180, caller dialect) against a column type map and reports, per cell with row, column, physical line and byte offset, ev

Context and evidence kit. Fit a context budget with a real tokenizer, locate exact citation spans, convert text offsets, collapse logs, prune conversations, extract a DOM skeleton, check evidence bundles. Checks (id, USDC per call, what it does): - context-pack (0.005): Chooses which context items an agent should put into a prompt without exceeding a token budget: every mandatory item and everything it depends on is always included, then optional items by descending - citation-span (0.005): Finds each quote an agent attributes to a source text and returns where it sits: exact offsets in UTF-16, code points, UTF-8 bytes and graphemes, so the span slices back to the matched text. - constraint-carryover (0.005): Takes the constraints an agent was given (budget caps, deadlines, identifiers, prohibitions) and a later artifact (plan, summary, handoff, tool arguments) and reports for each constraint whether its c - evidence-bundle-check (0.005): Checks a bundle an agent assembled before answering: each claim must be backed by at least N evidence items from distinct source groups, each item's quote must actually appear in the supplied text (wi - syndication-hint (0.005): Compares up to 30 passages an agent collected and reports which pairs share word-shingle content (Jaccard and containment), grouping them into clusters of probable copies so the number of independent - hedge-extract (0.005): Finds hedge and booster cues in an agent's or source's text using a fixed English lexicon (modals, epistemic verbs, adverbs and adjectives, approximators, shield phrases, certainty boosters) plus call - negation-scope (0.005): Applies NegEx-style rules (the English termset of negspacy, MIT, derived from NegEx) to text: finds negation cues, pseudo-negations such as 'not only', and scope terminators such as 'but', and returns - deictic-check (0.005): Scans a user or tool message for phrases that cannot be understood without context: demonstratives ('that one', 'the latter'), back-refer

Money math kit. Locale amount parsing, minor units, cash rounding, exact allocation, invoice recomputation, proration, metered pricing, pack sizes, id-kind detection, cheque words. Checks (id, USDC per call, what it does): - minor-units (0.005): Converts up to 200 money amounts between decimal strings and integer minor units (cents, yen, fils) using the ISO 4217 exponent from the SIX Group list, for an agent about to send an amount to a payme - cash-rounding (0.005): Rounds up to 100 final cash totals to the smallest payable increment, for an agent computing what a customer actually pays in cash or the change owed. - allocate (0.005): Splits one signed amount into up to 500 parts by weights (or equal parts), in integer minor units of its currency, for an agent dividing a bill, a refund, a fee or a tax. - proration (0.005): Computes the year fraction of up to 100 half-open date ranges [start, end) under a named ISDA day-count convention, and optionally the prorated charge, for an agent billing a partial period or accruin - metered-price (0.005): Prices a usage quantity against up to 50 tiers, graduated (each tier prices only its own units) or volume (the tier holding the whole quantity prices all of it), for an agent checking a usage bill or - invoice-audit (0.005): Recomputes up to 500 invoice lines in exact decimal arithmetic and compares them with the stated amounts, for an agent about to approve, pay or reconcile an invoice. - price-change-attribution (0.005): Explains why a total moved between two versions of a quote, order or invoice (up to 300 lines each), for an agent that must say how much of the change came from quantity, unit price, exchange rate, ne - locale-number (0.005): Parses up to 100 number or money strings such as "1.234,56", "1,00,000", "(1,234.50)", "￥1,000" or "CHF 1'234.50" into canonical decimal strings, for an agent reading amounts from documents, emails or - number-to-words (0.005): Spells out a number or a money amount in English words f

Calendar and deadline kit. Business-day deadlines on versioned holiday calendars, DST gaps, RRULE and cron expansion, market sessions, settlement dates, slot intersection, calendar conversion. Checks (id, USDC per call, what it does): - business-deadline (0.005): Computes the date (and optionally the instant) a business-day deadline falls on, for an agent drafting or checking a contract, notice, SLA or partner response window: '10 clear business days' (both en - dst-check (0.005): Checks up to 100 local date-times (YYYY-MM-DDTHH:MM) or offset timestamps against an IANA time zone and reports whether each wall time exists once, never (spring-forward gap) or twice (fall-back overl - date-claim-check (0.005): Checks up to 200 claims 'Monday 2026-12-28' against the proleptic Gregorian calendar and reports the real weekday, whether the date exists (2026-02-29 does not), and the nearest date carrying the clai - week-number (0.005): Returns the week number, week-year, number of weeks in that year and the week's first and last day for up to 200 dates under ISO 8601 (Monday start, week 1 holds 4 January), the US convention (Sunday - market-session (0.005): For up to 50 caller-supplied instants, reports whether the NYSE core session (09:30-16:00 America/New_York, 13:00 on early-close days) is open, the reason when closed (weekend, named holiday, before o - settlement-date (0.005): Computes the settlement date for a trade date under US equities T+1 (17 CFR 240.15c6-1, compliance date 2024-05-28) counting only days when the NYSE and the Federal Reserve Banks are open, or T+n on a - calendar-convert (0.005): Converts a Gregorian date (or a Hebrew, Persian, Ethiopian or Hijri date) to the other calendars via the runtime's ICU, always naming the Hijri variant (Umm al-Qura, tabular civil, tabular astronomica - fiscal-period (0.005): Maps up to 100 dates to a fiscal year, quarter, period and week for a caller-defined fiscal calendar: a month-aligned year (starts on day 1 of a named

Code preflight kit. Semver ranges, SPDX policy, package existence, wheel availability, regex safety, single-statement SQL checks, JWT lint, ABI calldata decode, gitignore and CODEOWNERS rules. Checks (id, USDC per call, what it does): - semver-check (0.005): Parses a dependency version range in npm (node-semver), PEP 440 specifier, Cargo requirement or Maven range syntax and tests up to 100 candidate versions against it, for agents that write or review ma - spdx-policy (0.005): Parses up to 50 SPDX license expressions (AND, OR, WITH exceptions, + or-later, LicenseRef) and evaluates each against a caller policy (allow list, deny list, allowed exceptions, OSI/FSF flags, copyle - package-exists (0.005): Checks whether up to 10 package names (optionally with a version) exist in the live npm, PyPI or crates.io registry, for coding agents about to add a dependency they may have invented. - wheel-availability (0.005): Lists the wheels PyPI offers for a package release and picks those compatible with a given CPython version, OS, CPU architecture and libc (glibc or musl version, or macOS version), best match first, f - symbol-exists (0.005): Checks that up to 20 named exports (functions, classes, constants, types, default) exist in the .d.ts files published for an exact npm package version, read from jsDelivr, for coding agents that may b - regex-check (0.005): Statically analyses an ECMAScript regular expression (up to 500 characters) for catastrophic backtracking (nested or overlapping quantifiers, ambiguous alternation in a loop, backreferences, lookaroun - sql-check (0.005): Checks one SQL string (up to 20000 characters; PostgreSQL, MySQL, SQLite or generic) before an agent executes it: exactly one statement, read-only (SELECT/VALUES/SHOW/EXPLAIN without side effects), an - migration-reversibility (0.005): Classifies each statement of a PostgreSQL, MySQL or SQLite migration (up to 20000 characters) as reversible, needing a backup, needing the original definition, or irr

Infra preflight kit. Kubernetes cross-manifest checks, IAM minimization, CIDR math, shell quoting, HTTP cache and robots rules, URL canonicalization, archive and path safety, file signatures. Checks (id, USDC per call, what it does): - k8s-crosscheck (0.005): Parses up to 20 Kubernetes YAML manifests and checks that they agree with each other, for an agent that generated or edited manifests before kubectl apply: Service selectors against pod template label - iam-minimize (0.005): Takes an AWS IAM policy JSON and the exact list of actions a task needs (up to 300), and returns the policy with each Allow statement's Action narrowed to just those actions, plus what the original ov - cidr-math (0.005): Computes exact CIDR relations for agents planning networks, firewall rules or allow-lists: for up to 200 IPv4/IPv6 blocks it reports which pairs are equal, nested, partially overlapping or merely adja - shell-quote (0.005): Turns up to 50 literal strings into a safely quoted argument for bash/sh (POSIX single-quote method), PowerShell (single-quoted literal) and cmd.exe, for agents that build a command line from untruste - http-cache-explain (0.005): Explains from supplied response headers (and optionally the request's headers, a CORS request, and a redirect chain) whether a shared and a private HTTP cache may store the response (RFC 9111 section - robots-check (0.005): Reads a supplied robots.txt the RFC 9309 way for an agent deciding whether to fetch up to 25 paths as one product-token user agent: group selection (merged groups, "*" fallback), longest-match with th - url-canonicalize (0.005): Canonicalizes up to 50 absolute http(s) URLs for an agent about to fetch, dedupe or click them: WHATWG-parsed lowercase host, default port and fragment and userinfo removed, dot segments and unreserve - redirect-credential-check (0.005): Walks a supplied HTTP redirect chain (up to 25 hops of status + Location) for an agent or HTTP client author and reports, per hop, which of the r

Identifier and text-limits kit. Check digits (IBAN, GTIN, ISIN, VIN, LEI, ...), VAT formats, SMS segments and X weighted length, platform field limits, subtitles, timecodes, speakable text, font coverage. Checks (id, USDC per call, what it does): - checksum (0.005): Validates the format and check digit of up to 100 identifiers per call, for an agent about to put an IBAN, ISBN, GTIN/EAN/UPC, container number, VIN, ISIN, CUSIP, SEDOL, LEI, IMO number, BIC or Luhn n - vin-decode (0.005): Decodes up to 50 VINs per call for an agent handling a vehicle listing, claim or order: validates the 17 characters and letters I/O/Q, the position-9 check digit (49 CFR 565.15), the world manufacture - gtin-hierarchy (0.005): Takes up to 100 GTINs and, for an agent reconciling a product feed or order lines, validates each check digit, converts it to the 14-digit form, reads the indicator digit and GS1 Prefix (restricted-ci - platform-text-fit (0.005): Checks up to 50 texts per call against a platform limit, for an agent writing a message, post, store listing, ad or push payload that must not be truncated or split. - tax-id-format (0.005): Checks the structure and check digit of up to 100 EU VAT numbers per call (Austria, Belgium, Germany, Denmark, Finland), for an agent about to put a supplier or customer VAT number on an invoice or in - timecode-convert (0.005): Converts up to 200 timecodes, frame counts or times between SMPTE HH:MM:SS:FF (non-drop), HH:MM:SS;FF (drop-frame, 29.97 and 59.94), frame numbers and exact rational seconds, for an agent editing vide - subtitle-lint (0.005): Parses an SRT or WebVTT file (up to 400000 characters, 4000 cues) and checks every cue for an agent about to deliver or burn in captions: end after start, overlaps and out-of-order cues, minimum gap, - pronunciation-apply (0.005): Applies your pronunciation lexicon (up to 200 terms, each an IPA string or a spoken alias) to a text of up to 20000 characters and returns SSML 1.1 with <phoneme alphabet="ip

Physical operations kit. Unit conversion with dimension checks, tolerance stacks, carton fit, lot picking, electrical calcs, geodesic distance, solar position, METAR parsing, formula weights. Checks (id, USDC per call, what it does): - unit-convert (0.005): Converts up to 100 values between units for an agent that needs the exact factor and a refusal when the units do not match: SI and NIST SP 811 length, mass, time, volume, pressure, energy, power, temp - formula-weight (0.005): Parses a chemical formula (parentheses, brackets, hydrate dots such as CuSO4·5H2O, an ignored charge) for a chemist or an agent that must check a molar mass, and returns the Hill-notation formula, the - solar-position (0.005): Computes sun elevation, azimuth, declination, equation of time, sunrise, solar noon and sunset (UTC) for a latitude/longitude and up to 100 caller-supplied instants using the NOAA Global Monitoring La - geo-distance (0.005): Computes the haversine (IUGG mean-radius sphere) and Vincenty inverse (WGS-84 ellipsoid) distance in metres plus initial and final bearings for up to 100 coordinate pairs, and optionally checks a clai - metar-parse (0.005): Decodes up to 20 METAR or SPECI aviation weather reports (US and ICAO forms: wind with gusts and variable direction, visibility in statute miles or metres, CAVOK, RVR, present weather, cloud layers, t - electrical-calc (0.005): Computes Ohm's law and power from any two of V, I, R, P; series and parallel resistance with optional tolerance bounds; a voltage divider (with optional load); an LED series resistor rounded up to a p - tolerance-stack (0.005): Computes the minimum and maximum of a linear dimensional stack (the gap) from signed contributions with symmetric, unequal-bilateral, unilateral or min/max limits, both by exact worst-case arithmetic - carton-fit (0.005): Checks whether up to 50 box-shaped items (axis-aligned, 90-degree rotations, optional this-side-up lock, optional weights) fit into any of up to 20 candidate c

Creative and games kit. WCAG contrast fixes, exposure and print estimates, chord checks, syllable counts, recipe scaling, chess move legality, seeded dice, sports score state. Checks (id, USDC per call, what it does): - recipe-scale (0.005): Scales up to 60 ingredient quantities by a servings ratio or a factor for an agent resizing a recipe or batch formula, applying per-ingredient rules the caller declares: linear (the labelled default), - contrast-fix (0.005): Checks up to 50 foreground/background hex pairs against a WCAG 2.2 contrast threshold (4.5 AA text, 3 large text and UI, 7 AAA, or your own) on the unrounded ratio, so 4.499 fails and exactly 4.5 pass - exposure-calc (0.005): Given any three of aperture (f-number), shutter time in seconds, ISO and scene EV at ISO 100, solves the fourth from EV = log2(N^2/t) and EV_S = EV_100 + log2(S/100), names the nearest one-third-stop - print-estimate (0.005): Given an image's pixel size and a print size (inches, millimetres or centimetres) plus optional bleed, margin and target ppi, returns the effective ppi over trim plus bleed, whether it meets the targe - chess-move (0.005): Checks whether a move (or a sequence of moves) is legal from a FEN position under the FIDE Laws of Chess, for agents that play, annotate or verify chess games. - dice-roll (0.005): Rolls dice notation (for example 4d6kh3+2) from a caller seed with a documented SHA-256 counter-mode stream and returns every die, the kept/dropped marks and a full draw transcript, for agents and ref - score-state (0.005): Replays a tennis point sequence (ITF Rules of Tennis: games, deuce, tie-breaks, match tie-break, who serves), computes a golf Score Differential and Handicap Index (World Handicap System), or tallies - chord-check (0.005): Names a chord from its notes, spells a chord symbol into notes, tests whether a chord is diatonic to a key, or transposes a chord symbol, using pitch-class arithmetic over a fixed table of 21 chord qu - syllable-count (0.005):

Compliance evidence kit. Caller-policy versus evidence checklists (site access, proof of delivery, manual applicability, document supersession), clause tagging, allergen flagging. Checks (id, USDC per call, what it does): - allergen-flag (0.005): Scans an ingredient list for terms tied to the 14 allergens of EU Regulation 1169/2011 Annex II and the 9 US major food allergens (FALCPA plus sesame under the FASTER Act), for an agent or buyer check - clause-tag (0.005): Tags each contract-style clause you supply with the modal force it expresses (obligation, prohibition, permission, recommendation) and topic cues (definition, condition, termination, payment, confiden - requirement-coverage (0.005): Evaluates a checklist of requirements the caller defines (each made of needs on evidence keys: present, equals, one of, min/max, maximum age) against evidence the caller supplies, and returns met / un - site-access-check (0.005): Checks whether an intended action on a website (read, crawl, submit, log in, ...) satisfies the access rules the caller supplies (robots rule read, terms clause, login present, rate-limit budget, capt - pod-sufficiency (0.005): Checks whether the proof-of-delivery evidence supplied (signature, photo, timestamp, GPS fix, recipient name, scan ...) satisfies the carrier or contract requirement list the caller gives: every requi - manual-applicability (0.005): Checks whether a manual, service bulletin or procedure applies to a specific unit by comparing the scope the document declares (models, firmware or revision range, serial range, exclusions) with the u - document-supersession (0.005): Given the target document id, the supplied set of documents (id, effective date, which ids each one supersedes, withdrawn flag) and a reference date, reports whether the target is superseded or withdr How to call: - {"describe": true, "check": "<id>"}: free. Returns that check's input schema and an example input. - {"check": "<id>", "input": {...}}: runs one check at

Agent coordination kit. Shared state for a fleet of agents: leases with fencing tokens, idempotency registry, token bucket, id blocks, spend ledger, result cache, fleet memory, signed policy and acceptance receipts. Checks (id, USDC per call, what it does): - idempotency-registry (0.005): Shared memory for side-effecting operations across agents and retries. - lease (0.005): Lets many agents agree which one works on a task: acquire a named resource for 1-3600 s, renew it while working, release it when done. - token-bucket (0.005): One rate limiter shared by every agent in your fleet. - id-block (0.005): Hands out strictly increasing integer blocks from a named sequence (1-1000 ids per call) so parallel agents never issue the same invoice, ticket or order number. - spend-ledger (0.005): A budget shared by a task tree, in integer minor units. - result-cache (0.005): Caches a result under the SHA-256 of the canonical (JCS) request, so every agent in your fleet that makes the same request reuses one answer for up to an hour. - policy-gate (0.005): Evaluates your own policy (JsonLogic rules, each allow or deny, deny-overrides or first-match, default deny) against a proposed tool call, payment or action, and returns allow or deny, the rule id tha - acceptance-receipt (0.005): Runs your deterministic acceptance tests (equals, exists, absent, type, contains, length and number ranges, one-of, sha256, a JSON Schema subset) against a sub-agent's or vendor's JSON output at JSON - fleet-memory (0.005): Lets every agent in your fleet record what it observed and read what the others saw, with freshness: endpoint brownouts and latency, rate-limit behaviour, IVR menu paths that worked, whether an ambigu How to call: - {"describe": true, "check": "<id>"}: free. Returns that check's input schema and an example input. - {"check": "<id>", "input": {...}}: runs one check at its listed price. - {"calls": [{"check": "<id>", "input": {...}}, ...]}: up to 20 checks from this package under

Free. Verify the provenance record (_provenance) the WritersLogic agent hub attaches to every paid result. Pass the {data, _provenance} object a paid tool returned, unchanged.