/install agent-store
Agent Store Skill
When to use this skill
Use this skill when the user wants to buy, purchase, order, pay for, or top up API keys or API credits.
intent word:
- buy
- order
- purchase
- pay for
- get
- top up
product word:
- api key
- api keys
- api credit
- api credits
Examples:
- I want to buy API keys
- Help me order API credits
- Purchase more API credits
- Get an API key
- Top up my API credits
Execution requirement
Use scripts/store.py as the only entry point:
python3 apps/agent-store-skill/scripts/store.py \x3Cproduct_type> \x3Clog_file>
Run the bundled Python script and use its log file as the execution report, and report user in "How to report result" section.
DO NOT create other scripts, wrappers, curl flows, or debugging helpers for this task.
DO NOT extend scripts/store.py to perform that follow-up automatically. The script ends once it returns the final delivery JSON.
DO NOT investigate or debug the underlying API or wallet flow in chat.
Arguments:
-
product_type:api_credits,api_key, orvps_instance -
log_file: plain-text log file path for step-by-step reporting, in your workspace's logs folder -
X402_BASE_RPC_URLdefaults tohttps://mainnet.base.orgfor EIP-2612 nonce reads on Base -
the API-side facilitator config now lives in
apps/facilitator/config/x402.config.jsonwith the facilitator signer key inapps/facilitator/config/x402.secrets.env; committed examples live next to them -
the bundled Python client bypasses proxies automatically for loopback
API_HOSTand loopback x402 RPC endpoints -
awp-walletmust be installed and onPATH -
awp-wallet allowancesmust be available for Permit2-only assets -
awp-wallet approvemust be available for Permit2-only assets -
awp-wallet sign-typed-datamust be available
What the script does:
- finds the first active product for the requested
product_type - chooses one supported payment asset for that product, preferring
awp, thenusdc, thenusdt - creates an order request on
POST /orderswithpayment_asset - handles the
402 PAYMENT-REQUIREDx402 challenge - with the committed facilitator defaults,
awpis permit-capable andusdc/usdtremain Permit2 assets until the server config says otherwise - sends explicit
Accept,Content-Type, andUser-Agentheaders on x402 RPC requests - if the server advertises
extensions.eip2612GasSponsoring, signs both the Permit2 witness payload and the EIP-2612 permit extension and skipsapprove - otherwise ensures Permit2 approval with
awp-wallet allowancesandawp-wallet approve - retries the same
POST /orderscall withPAYMENT-SIGNATURE - uses the successful signed retry response as the order summary and polls
GET /orders/{order_id}/deliveryfor the detailed delivery result - tolerates a short
404 order_not_foundrace while the delivery record becomes visible - keeps an in-progress sidecar at
\x3Clog_file>.attempt.jsonso restarted runs reuse the same order idempotency key until the flow reaches a terminal state - writes step logs to
log_file - prints the final order-delivery JSON to stdout
Before running an api_key purchase:
- Detect if the active model provider is
agent-store. If so, inform the user that no purchase is needed, can purchaseapi_creditsinstead.
Before running an api_credits purchase:
- use the standard purchase flow directly; the API credits workflow now always performs a real top-up through the API service
After a successful api_credits purchase:
- reply with a short summary that includes the remain_credits, payment asset, and transaction hash, do not convert remain_credits to tokens, use original number.
After a successful api_key purchase:
- inspect
delivery_result.base_url,delivery_result.key, anddelivery_result.supported_models - open your runtime configuration file and check whether
models.providers.agent-storeexists; if not, create it - set the provider base URL to
delivery_result.base_url - set the provider API key to
delivery_result.key - set the provider API to
openai-completions - replace the provider models with the returned
supported_models; use each model key as the model name - update only your own active model selection to the first model in
supported_models; do not change other agents' model selections in the same config file - send one minimal verification request through the updated
agent-storeprovider with the first model to confirm the gateway works - reply with a short summary that includes the result, order amount, payment asset, transaction hash, and the verified model you will use next
- start a new session with that verified model
- do not restart the gateway
Failure handling:
- if the script succeeds, use its stdout and
log_fileas the result - if the script fails, do not build alternate flows or debug further
- report the failure from
log_file
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent-store - After installation, invoke the skill by name or use
/agent-store - Provide required inputs per the skill's parameter spec and get structured output
What is Agent Store?
Use when the user wants to buy, purchase, order, pay for, or top up API keys or API credits. It is an AI Agent Skill for Claude Code / OpenClaw, with 82 downloads so far.
How do I install Agent Store?
Run "/install agent-store" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agent Store free?
Yes, Agent Store is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Agent Store support?
Agent Store is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agent Store?
It is built and maintained by levey (@levey); the current version is v1.0.2.