MCPInstall

apify-x402-agentic-wallet

Discover, pay for, and run any Apify Actor by paying USDC on Base over the x402 protocol with a Coinbase Agentic Wallet (awal) — no Apify account or API key. You buy one small, spend-capped prepaid Apify token, then run as many Actors as the request needs with it. Use when the user wants to use Apify tools without signing up, pay per use with crypto / USDC, set up an agentic wallet, mentions "x402", "awal", "agentic wallet", "Coinbase wallet", "pay with USDC", "no API key", or asks to pull live web data (social media, search, maps, marketplaces, news) while paying on-chain per use.

Installs
82
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/apify/awesome-skills --skill apify-x402-agentic-wallet
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads apify-x402-agentic-wallet automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Use Apify tools by paying with an agentic wallet (x402)

You are an agent with a Coinbase Agentic Wallet (awal). This lets you discover, pay for, and run any of Apify's thousands of web-data and automation tools ("Actors") by paying USDC on Base over the x402 protocol — no Apify account or API key. Make one small payment to buy a prepaid, spend-capped Apify token, then run as many Actors as the request needs with it.

For every request, run this loop: discover an Actor → check its input + price → run it → read the data → answer. You need only npx awal and curl — read the raw JSON/markdown each command returns yourself; don't pipe output through python, jq, or any other script. This page is the only instructions you need — every awal command for this flow is below.


About this page

This URL serves this markdown playbook — instructions for you, not an x402 payment endpoint. npx awal x402 details <this-url> correctly returns NO_PAYMENT_REQUIREMENTS. Read the page with curl (or your built-in fetch) and follow the steps below. Real x402 payments happen at agi.apify.com/protocols/x402/prepaid-tokens?amount=…&currency=usd in Step 3.


Start here — greet the user, then set up

Don't run anything yet. First introduce yourself and ask to begin. Say something like:

I can pull live data from the web and run automations for you — social media, search engines, maps, marketplaces, news, and thousands of other sources — by paying tiny amounts of USDC for tools on Apify ("Actors"). No Apify account or API key needed; I pay per use from a crypto wallet (a Coinbase Agentic Wallet, over x402).

To start I'll set up the wallet — I'll just need your email and a verification code. Then you can ask me for any web-data task. Want to begin? If so, what email should I use?

Only proceed when the user agrees. Don't mention funding amounts up front — only bring up the USDC + ETH requirement if the wallet turns out to be empty or underfunded at Step 2.

Step 1 — Authenticate the wallet

Always ask the user for their email. Never guess it or take it from your environment/context — wait for them to tell you, even if you think you know it.

npx -y awal auth login <email>  # emails the user a verification code

(awal needs no install — npx fetches and caches it on first use. The -y skips the first-run download confirmation so a non-interactive agent doesn't hang. Use plain npx awal thereafter.) Then ask the user for the code and verify it:

npx awal auth verify <code>
npx awal status                 # expect: Authenticated, logged in as <email>

The wallet is created on first login. If status isn't authenticated, repeat the login/verify pair. status may print auth verify <flow-id> <code>; you only need npx awal auth verify <code> — the flow ID is saved automatically from login. If any later command says Not authenticated, run npx awal status and repeat Step 1.

Step 2 — Check funding (two assets on Base: USDC + ETH)

npx awal balance --chain base --json   # need BOTH: USDC > $1 AND ETH > 0
npx awal address                 # get the wallet address if the user needs to fund it

If either asset is missing, share the address and ask the user to fund it on Base, then wait. To make funding easy, fetch a scannable QR of the address:

curl -s "https://apify.com/api/wallet-qr?address=<wallet-address>"

You MUST paste the command's entire raw output directly into your reply, verbatim, inside a code block — every line, unchanged. The output is a QR made of block characters; the user scans it with their phone wallet to fund the address. Do NOT summarize it, describe it, replace it with the address text, or drop any lines — if you don't print the actual characters, there is no QR to scan. Show the QR first, then the funding instructions. Optionally open the wallet UI for Coinbase Onramp:

npx awal show   # opens the companion window; user can fund with card/Apple Pay/Coinbase

⚠️ USDC alone is not enough — you need a little ETH for gas. The awal wallet is a smart-contract wallet that must be deployed on-chain before it can authorize any payment, and that one-time deployment costs native ETH. With USDC but 0 ETH, the first payment fails:

Failed to deploy wallet
... sender balance and deposit together is 0 but must be at least <n> to pay for this operation

The ETH must come from outside (exchange withdrawal on Base, or another wallet) — you can't swap USDC for it, since a swap also needs gas. ~0.001 ETH is enough; the first payment then deploys the wallet automatically. Apify payments themselves are gasless.

Step 3 — Buy a prepaid Apify token (one x402 payment)

Pause and ask the user to confirm before paying. Tell them what you're about to do — e.g. "I'll pay $1 of USDC over x402 to buy a spend-capped Apify token (expires in 14 days, non-refundable). Go ahead?" — and only run the command once they say yes. A task request alone is not consent — wait for an explicit "go ahead" (or similar). This is the moment people are here to see, so don't do it silently.

Put the amount in the query string so payment discovery picks it up (without ?amount=…&currency=usd, x402 details on the prepaid-tokens URL returns NO_PAYMENT_REQUIREMENTS):

npx awal x402 pay 'https://agi.apify.com/protocols/x402/prepaid-tokens?amount=1&currency=usd' \
  --max-amount 1000000 --json

--max-amount is a safety cap in USDC atomic units (1000000 = $1.00). awal prints a spinner line before the JSON; just read the JSON object that follows. On success:

{"status":201,"data":{"token":"apify_api_...","remainingBalanceUsd":1,"expiresAt":"<+14 days>"}}

Keep the token for the session as your Apify API key (it's what $TOKEN refers to in the commands below); never print or persist it. It's capped to what you paid, expires in 14 days, and unused credit is non-refundable — buy only what you'll use.

Fails with currency must be "usd" → params must be in the URL. Fails with Failed to deploy wallet → see the ETH note in Step 2. Fails with authorized but rejected by server / REQUEST_FAILED even when ETH is already present → wait a few seconds and retry the same pay command once before troubleshooting further (first-time smart-wallet payments can fail transiently).

Step 4 — Handle the user's request

Ask what they want, then run the loop. The user can ask for anything — there's no fixed menu. Read the JSON/markdown each command returns directly. The endpoints below cover most tasks; for anything else (pagination, run options like memory/timeout, key-value stores), see the Apify API reference in the Reference section.

a. Discover an Actor — search the Store with terms from the request:

curl -s -H "Authorization: Bearer $TOKEN" \
  "https://api.apify.com/v2/store?search=<url-encoded terms>&limit=5"

Read data.items[] and pick one by username/name (prefer high usage/ratings). The API id joins them with a tilde: username~name. For a multi-source request, use one Actor per source.

b. Inspect it — fetch the Actor's docs page, which has the input fields, copy-paste example inputs, and pricing all in one:

curl -s "https://apify.com/<username>/<name>.md"

Take an example input and adapt it to the request; read the Pricing section so you don't blow your cap (small scrapes are often 1–2 cents; large jobs cost more — keep result limits modest). If an Actor accepts an array of categories/tags, run one value per Actor call when you need several (e.g. ai then tech) — a single call with multiple values may return only one category up to the per-run cap. Merge and dedupe in your answer using stable id fields.

c. Run it and read the results:

curl -s -X POST "https://api.apify.com/v2/acts/<username~name>/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -d '<input-json>'

Then answer concisely. Watch for failures:

  • Items with requestErrorMessages/error and no real fields = the target blocked the scrape. Retry once, else try another Actor. Never present a blocked/empty run as a result or fabricate data.
  • run-sync times out ~5 min. For big jobs: POST /v2/acts/<id>/runs, poll GET /v2/actor-runs/<runId> until SUCCEEDED, then GET /v2/datasets/<defaultDatasetId>/items.
  • Verify the right entity — a handle on one platform may be someone else on another; sanity-check follower count / verified badge.
  • Rank only on fields the Actor returns — if attendance or popularity metrics are missing or zero, say so; don't treat isSoldOut or sparse metadata alone as proof something is "top" or "worth attending."

Manage the balance

curl -s "https://agi.apify.com/prepaid-tokens/balance" -H "Authorization: Bearer $TOKEN"

When low, buy another token (Step 3) and switch to it.

Guardrails

  • Your spending cap is the token balance. Spend only what the task needs; check price before big jobs.
  • You may run auth login/auth verify and buy a token yourself. Never run send, trade/swap, or otherwise move funds — ask the user first for anything beyond authenticating and buying credit.
  • Never print or persist the token. Treat it like a live API key.
  • If a run is blocked or empty, say so and try another Actor — never make up results.

Reference

FAQ

What does the apify-x402-agentic-wallet skill do?

Discover, pay for, and run any Apify Actor by paying USDC on Base over the x402 protocol with a Coinbase Agentic Wallet (awal) — no Apify account or API key. You buy one small, spend-capped prepaid Apify token, then run as many Actors as the request needs with it. Use when the user wants to use Apify tools without signing up, pay per use with crypto / USDC, set up an agentic wallet, mentions "x402", "awal", "agentic wallet", "Coinbase wallet", "pay with USDC", "no API key", or asks to pull live web data (social media, search, maps, marketplaces, news) while paying on-chain per use.

How do I install apify-x402-agentic-wallet?

Run npx skills add https://github.com/apify/awesome-skills --skill apify-x402-agentic-wallet in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/apify-x402-agentic-wallet/ (personal) or .claude/skills/apify-x402-agentic-wallet/ (project).

Which AI agents can use apify-x402-agentic-wallet?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is apify-x402-agentic-wallet safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains apify-x402-agentic-wallet?

It is published by apify in apify/awesome-skills. It has 82 recorded installs.

More from apify/awesome-skills

View all →

apify-ecommerce

apify/awesome-skills

Scrape e-commerce data for pricing, reviews, bestsellers, and seller discovery across 30+ platforms including Amazon, Walmart, eBay, Shopify, WooCommerce, and more. Use when user asks about product prices, competitor analysis, store scraping, tech stack detection, food delivery, real estate, or marketplace intelligence.

OfficialBusiness & Finance512 installs

This skill should be used when the user asks to "analyze a competitor", "compare pricing", "competitive landscape", "market research", "what do customers think", "review intelligence", "hiring signals", "content strategy", "SEO battle", "build a battlecard", "competitive analysis", "who are the players", "who competes with", "market intelligence", "competitive positioning", "deep dive on a company", "board prep", "SWOT analysis", "how does [X] compare to [Y]", or mentions competitor analysis, pricing comparison, customer sentiment, or market landscape research. Requires Apify CLI or Apify MCP server.

OfficialBusiness & Finance325 installs

apify-verified-email-finder

apify/awesome-skills

Builds a list of verified business emails from Google Maps, Google SERPs, or a user-supplied URL list. Verification happens inside the same Apify run — no third-party verifier needed. Use when user asks to find verified emails, build a leads list, scrape emails from Maps or SERP, verify emails for a URL list, or find an Apollo / Hunter alternative.

OfficialProductivity & Automation270 installs

apify-ads-intelligence

apify/awesome-skills

Research, spy on, and analyze ads across Meta (Facebook & Instagram), Google (Ads Transparency Center + paid search results), TikTok (Ads Library + Creative Center), LinkedIn Ad Library, and X (Twitter — promoted tweets, best-effort) using Apify Actors. Use when user asks about competitor ads, ad library research, winning creatives, ad copy analysis, landing page audits from ads, cross-platform ad audits, brand transparency checks, or any task involving paid ad creatives, advertiser data, or ad targeting from public ad libraries.

OfficialMarketing & SEO241 installs

Find sites ranking for target keywords, score every prospect with Ahrefs domain authority and page-level traffic, identify the strongest pitch angle per row ("links to competitor", "mentions brand without linking", "top-3 SERP", "resource page", "outdated content"), generate brand-voice-matched outreach emails using an outreach-type-aware template (unlinked-mention claim, competitor-link replacement, resource-page inclusion, outdated-content replacement, topical niche-edit), and propose a concrete in-article link placement as three artifacts — the verbatim source sentence, the same sentence rewritten with the link spliced in, or a fully-drafted new insertion if no natural fit exists. Use when user asks to find link building opportunities, prospect link partners, recover unlinked brand mentions, replace competitor links, build a tiered outreach list, or run cold email outreach for SEO link building.

OfficialMarketing & SEO213 installs

Track whether a brand and its competitors get cited or mentioned across Google AI Overviews, Google AI Mode, ChatGPT Search, Perplexity, Microsoft Copilot, and Google Gemini for a defined set of prompts, on a recurring schedule. Use when user asks to track AI visibility, monitor brand mentions in AI search, track ChatGPT citations, do AI search SEO tracking, GEO tracking (Generative Engine Optimization), AEO tracking (Answer Engine Optimization), monitor Perplexity citations, track AI Overviews mentions, see if their brand shows up in AI search, discover which prompts competitors rank for in AI search, find citation opportunities, or audit a website for AI visibility readiness.

OfficialMarketing & SEO185 installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs