Humanize AI Text — Rewrites AI-sounding prose so it reads like a person wrote it — in any language, without dropping facts. Use when asked to humanize a text, make it sound less AI-generated or less like ChatGPT, or clean machine phrasing out of an article, post, email, product description or page. One-time purchase of the SKILL.md file itself (Agent Skills format), not an API call: $0.05 USDC, yours forever incl. free re-downloads and new versions. Tested with a strong and a weak model; the ca…

SEO Meta Writer — Writes the SEO title, meta description and (on request) the H1 heading for one web page, in the page's own language, inside hard character limits, matching what the searcher wants. Use when asked to write or rewrite a page title, meta description, SEO snippet or H1 for a page, product, service, article or landing page. One-time purchase of the SKILL.md file itself (Agent Skills format), not an API call: $0.03 USDC, yours forever incl. free re-downloads and new versions. Tested…

Find recent topic news or poll for new-to-agent links using a bounded follow-up checkpoint and seen history. Return normalized links, exact-link/headline deduplication and optional source-linked headline highlights from a7-day GDELT headline index. Monitoring dates are not verified publication dates.0.01 USDC per completed search, including no new links; source failures are uncharged.

Agent Done Check: Stop False Success Reports — Stops an AI agent from reporting false success, or hallucinated completion: work it calls done that did not happen. Every action in its status report gets one of five states (done and verified, done but not confirmed, partly done, failed, not done), backed by what the tool results of the session show. Failures and unknowns come first, counts come from the results, and no id, receipt or hash is invented. When a result does show success, the agent sa…

Statement history: The agent's last 24 three-hour statements (outflow split into spend and routing hops, what left its control, income, open flags), each with its keccak-256 hash, the prevHash link that chains them, and a Merkle proof against the signed root of its window. About one ERC-8004 agent on Base, by Agentic Finance Graph. id = token id, slug or bound wallet; an agent never seen paying is a 404 before any payment.

JSON-RPC read access to EVM chains (base, ethereum, polygon, arbitrum, optimism) with no API key. Send a standard JSON-RPC body (eth_call, eth_getBalance, eth_blockNumber, eth_getLogs). Also callable as GET with the same fields as query parameters.

Prompt Injection Guard — Keeps an AI agent from obeying instructions hidden in what it reads (indirect prompt injection). Web pages, e-mails, files, PDFs, API and tool output, other agents' messages and skill files under review are treated as content, never as orders. The agent is instructed never to pay, transfer, delete or reveal anything because content asked, to report the attempt with a quote and its source, and to still finish the real task. Use whenever the agent reads anything it did no…

Use when an agent must confirm a Base transaction or payment landed: did it succeed, who paid whom, how much of which token. Input: hash. Output: JSON status (success/reverted), block+time, confirmations, from, to, ETH value, fee (L2 gas + L1 data fee), decoded ERC-20 transfers with symbol and decimal amount (first 25). Unknown or unmined hash: 404, not charged. Example: ?hash=0x284f8abed91b5631ee28bdb1ccfe78374e18c480cb2ab25f28e3bfac5210fe0b

Proofread — Proofreads a text with minimal intervention, in the language of the text. Fixes spelling, grammar, punctuation and obvious typos, keeps everything else, and returns the corrected text plus a short list of changes for review. Use when asked to proofread, correct, spell-check or fix the mistakes in a text without rewriting it. One-time purchase of the SKILL.md file itself (Agent Skills format), not an API call: $0.05 USDC, yours forever incl. free re-downloads and new versions. Tested…

Code Review — Reviews a code change (a diff or a changed file pasted as text) and reports real problems ranked by severity — correctness bugs, security holes, data loss, missing error handling, edge cases, resource leaks — each with location, reason and a concrete fix in words. Use when asked to review code, a diff or a pull request, check a change for bugs, or find security problems in a snippet. One-time purchase of the SKILL.md file itself (Agent Skills format), not an API call: $0.01 USDC, …

Does this x402 endpoint really deliver? x402 Doctor buys it once with the example input its own listing declares (at most $0.1, USDC on Base), checks the answer against the declared output schema and measures the charge on chain. Answers with a job id at once; the result is public, usually within 30 minutes. For sellers who want proof, and buyers before a big order.

Fetch a public URL (HTML article, PDF, or JSON) and return JSON matching your schema in one call, with page title and source. Pay-per-call over x402 in USDC on Base; payment challenge answered in ~8 ms.

Is this wallet sanctioned? Screens any chain's address (EVM, Solana, Tron, Bitcoin, XRP Ledger, Algorand) against the OFAC SDN list, synced from the US Treasury, plus theft, phishing and mixer reports for EVM addresses. Green/orange/red with the SDN entry (name, programs) when listed. For sellers screening who pays them and agents checking who they pay. Bulk: 100 checks for $0.80 via /v1/credits.

SEC red-flag alerts across all US public companies, for polling agents: restatements, auditor changes, delisting notices, bankruptcies, late 10-K/10-Q, cyber incidents, CEO/director changes, earnings releases, deals, and insider purchases of $100K+. Ticker, time, excerpt, filing link. Watchlist and level filters; cursor polling; free peek. $0.005 USDC per call.

Who is this phone number or website? Give a US phone number or a website and get the local business behind it: name, address, category, the best email graded A/B/C, a contact name when the email shows one, socials and buying signals. A website only matches when it carries the business's own phone number, so the answer is never a guess. $0.01 per lookup that finds a business; no match, no charge. USDC on Base or Arc.

OrionCMD Checks: HTTP security headers + redirect chain for a site. One HTTPS GET from Cloudflare's edge: redirect chain, final status, HSTS, CSP, X-Content-Type-Options, X-Frame-Options, Referrer-Policy, Permissions-Policy, COOP, a simple A-F grade and plain-English findings.

OrionCMD Checks: Email authentication posture: SPF, DMARC, DKIM, MTA-STS, TLS-RPT, BIMI. SPF validity and DNS-lookup count (limit 10), DMARC policy/pct/rua, DKIM on common selectors, MTA-STS mode, TLS-RPT and BIMI, with a rough 0-100 score and plain-English findings. Live DNS via Cloudflare DoH.

Summarize Faithfully, Keep Every Number — Writes a faithful summary of a text in the text's own language, using only what the text says, with every number, name and date kept exactly and every qualifier kept. Use when asked to summarize, shorten, condense, give the gist or a TL;DR of an article, report, email, transcript, thread or document. One-time purchase of the SKILL.md file itself (Agent Skills format), not an API call: $0.03 USDC, yours forever incl. free re-downloads and new versions. T…

JSON Repair: Fix Broken JSON, Keep Every Value — Repairs broken JSON so a program can parse it, without changing any value. Fixes trailing and missing commas, comments, single quotes, unquoted keys, Python and JavaScript literals, smart quotes used as delimiters, raw line breaks and stray quotes inside strings, a code fence or chat text around the JSON, and output cut off in the middle. A value that was cut off becomes null instead of a guess, numbers JSON cannot hold as written are kept as str…

Text to JSON: Extract Data Without Guessing — Extracts data from text into JSON that matches the shape you give (a JSON Schema, an example object or a list of fields), without guessing. Every value comes from the text; a missing fact becomes null, numbers and dates are converted only into the type the shape asks for, two conflicting values are not settled by a guess, and instructions hidden in the text are ignored. Use when asked to extract structured data, turn text into JSON, parse an invoice…