agents.writerslogic.com

Sentiment analysis and a calibrated 0-100 probability that a Polymarket/Kalshi-style event resolves Yes.

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.

Identifies an integer sequence from terms, a safe-parsed formula or recurrence, or a description. 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

Durable per-wallet agent memory with temporal facts: remember (structured facts or free text), recall (BM25 plus exact triple pattern, as of any time), forget (cryptographic forgetting that leaves a tombstone) and explain (provenance and supersession). Every fact has a ToIP SAID; every write returns a hash-chained, optionally signed receipt. Tenant is the paying wallet.

Scans files or a unified diff 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. Returns findings w

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.

Scrapes a company homepage, deduces its value proposition and buyer persona, and drafts a targeted B2B cold email.

Given a Polymarket market (slug, URL or conditionId; Kalshi ticker supported), reads the rules clarification (Additional context) from the UMA adapter on Polygon, finds the real-world outcomes whose resolution changed, shifts fair probability by their verified, ensemble-estimated mass, walks the live CLOB book at your size after fees and slippage, and returns BUY_YES / BUY_NO / EXIT / HOLD / NO_MA

Two-stage adversarial review of a unified diff (bug hunter, then patch synthesizer) plus deterministic secret, dependency, and SAST scanning; returns mergeApproved, riskScore 0-100, findings, and drop-in patches.

For a Polymarket market in its 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 DISPUTE / DO_N

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.

Finds fine-print divergences between two prediction markets (e.g. Polymarket vs Kalshi), prices basis risk, and returns ARBITRAGE_SAFE / BASIS_RISK_TRAP / NO_EDGE with Kelly hedge sizing. Prices are USD per share (0-1).

Audits a page's DOM for the WCAG failures most cited in ADA demand letters (alt text, form labels, empty buttons/links, lang, headings, landmarks, skip links, zoom), returns a litigation risk score, per-element patched HTML, and a drop-in interim <script> hotfix.

Solidity vulnerability analysis (reentrancy, overflow, access control, logic bugs) with a severity-ranked JSON report.

Resolves a paper (DOI/title) or free-text claim, mines citing works and citation-context sentences from Semantic Scholar, OpenAlex and Europe PMC, checks Crossref/Europe PMC/OpenAlex retraction and erratum status (a retraction short-circuits to UNREPLICABLE_HYPE without model calls), reports scite.ai citation tallies as a separate signal, and returns a deterministic replicationRiskScore with ROBUS

Finds auto-renewal, notice-window, and early-termination traps in a contract or live Terms page, maps them to ROSCA, state automatic-renewal laws, EU/UK consumer law, and contract breach triggers, and drafts a formal termination and payment-revocation notice.

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. Eve

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 extract

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

Takes 2 to 4 papers (DOI, arXiv id or PMID) on a shared question and finds where their reported numbers conflict. 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

Mines non-English scientific literature (OpenAlex, Crossref, HAL, J-STAGE, Europe PMC) for work with no English-language twin: native-terminology keyword plan per language, English-twin screening, English methodology translation, pattern-extracted quote-verified quantitative results, index-sourced institutions, a computed known-in-English risk (OpenAlex English citers and title similarity), and a

Classifies a product under the HS/HTS with GRI reasoning, estimates MFN and additional duties, lists defensible lower-duty alternatives and lawful physical tariff-engineering changes, and drafts an accurate commercial invoice description.

Audits an agency's public-records response: 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. Every claim carries UTF-8 byte of

Collects papers for a topic or seed list (arXiv, OpenAlex), 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 ADDRES

Parses a bibliography (BibTeX, LaTeX \bibitem, plain-text list, arXiv id via ar5iv, or PDF URL) and resolves every reference against Crossref, OpenAlex, arXiv and Europe PMC by DOI, arXiv id, PMID or scored title/author/year search. Each reference is VERIFIED, METADATA_MISMATCH (field-level year/authors/title/venue/DOI diffs), DOI_RESOLVES_TO_DIFFERENT_WORK, NOT_FOUND (likely fabricated), RETRACTE

Explains settlements and payouts from ledger lines with an exact solver, not 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). Returns UNIQUE only when exactly one assignment exists and the s

Breaks independent claims into atomic limitations, maps the product to each (literal and doctrine of equivalents), scores claims under the all-elements rule, and proposes 3 engineering design-arounds that remove at least one required limitation.

Mines ClinicalTrials.gov for terminated, withdrawn and suspended studies and for completed Phase 1/2 non-industry studies with no later industry Phase 2/3/4 trial, joins Europe PMC and OpenAlex literature, classifies why each was shelved (keyword rules; one fast model call only for an ambiguous reason or a missing mechanism, verified by verbatim quote), checks ChEMBL and the FDA Orange Book for ap

Runs the Crosstalk reasoning protocol on a question: classifies the domain, generates up to 3 independent hypotheses, attacks each with an adversarial falsification pass, checks live literature on arXiv and OpenAlex (every record content-addressed by sha256), then synthesizes a calibrated answer with unresolved cruxes and one decisive falsification probe. Every material statement is a typed ledger

Exhaustively checks a finite state machine, protocol, or concurrent routine. 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 s

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.

Scores representment win probability, maps merchant evidence to the network rubric for the reason code (including deterministic Visa CE3.0 eligibility and invalid-dispute checks), lists missing evidence, and writes a rebuttal ready for Stripe or Shopify disputes. Uses only supplied evidence; never fabricates.

Formalizes natural-language clauses (or accepts a formal IR directly with zero LLM calls) 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 again

Audits itemized medical bills for E/M upcoding, NCCI unbundling, duplicate and unit errors; estimates Medicare and fair-price benchmarks; and drafts a dispute letter citing applicable No Surprises Act and NCCI rules.

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 calibrated P(approved), expect

Segments patent claims into elements in code (dependent claims inherit their parents' elements; claims, priority date and cited art can be read from a patent number), searches arXiv, OpenAlex, Europe PMC, Crossref, HAL and J-STAGE with a strict published-before-priority-date cutoff, maps references to elements with verbatim verified quotes (translated when not English), and computes 102 anticipati

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 acti

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-doo

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.

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

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.

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

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.

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-

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

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 mar

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_FIND

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 sessi

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 throug

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.