Agent Skills

agent-wallet-policy

View spending policy on a Circle agent wallet — per-transaction, daily, weekly, and monthly USDC caps via the `circle` CLI. Use when the user wants to inspect current limits. Setting or resetting limits requires OTP confirmation in an interactive terminal session — the agent hands the user a verbatim command to run themselves; the OTP must never pass through agent storage. Mainnet-only — testnet chains are rejected. Triggers on: spending limit, spending policy, per-tx cap, daily cap, weekly cap,

Install

npx skills add https://github.com/circlefin/skills --skill agent-wallet-policy
SKILL.md

Overview

For an overview of the Circle CLI's full capability set, see the use-circle-cli master skill. This skill is the narrower spending-policy flow.

Circle agent wallets support spending policies — per-wallet caps that the CLI enforces on every payment and transfer. There are three operations:

Operation Command OTP required?
View current limits circle wallet limit --address <addr> --chain ARC --output json No
Set custom limits circle wallet limit set ... Yes — human OTP, run in user's own terminal
Reset to defaults circle wallet limit reset ... Yes — human OTP, run in user's own terminal

Spending policies are mainnet-only (testnet chains are rejected; see Troubleshooting / Rules).

Prerequisites

Two supporting commands set up the flow: a session check (circle wallet status) and a wallet-address lookup (circle wallet list ... --output json). READ references/commands.md for the exact commands.

If circle wallet status errors with "Not logged in" or "Terms acceptance is required", hand off to the use-agent-wallet skill — it covers install, terms, login, and wallet creation.

Viewing current limits (in-agent, no OTP)

circle wallet limit --address <addr> --chain ARC --output json

Shows the current per-tx, daily, weekly, and monthly USDC caps (null for any unset tier). Safe to call freely — read-only, no money moves, no OTP.

Setting or resetting limits (interactive terminal — handoff to user)

circle wallet limit set and circle wallet limit reset are interactive. They send a 6-digit OTP to the user's email mid-execution and wait for the code at the CLI's stdin prompt.

OTPs are password-equivalent. The agent must NOT receive, store, or relay the OTP. The agent's job here is to hand the user a verbatim command to run in their own terminal, then wait for them to report back.

1. Confirm values with the user

Limits must be monotonic: per-tx ≤ daily ≤ weekly ≤ monthly.

A typical conservative configuration:

Tier Suggested USDC value
--per-tx 1
--daily 5
--weekly 20
--monthly 50

Adjust based on the user's stated tolerance. Get explicit yes before generating the command.

2. Hand the user the command

Tell the user:

Setting spending limits requires an OTP I shouldn't see. Please run this command in your own terminal — the CLI will email you a 6-digit code; enter it at the prompt. Let me know once it completes.

circle wallet limit set \
  --address <addr> --chain ARC \
  --policy-type stablecoin \
  --per-tx 1 --daily 5 --weekly 20 --monthly 50

For reset, the verbatim command is:

circle wallet limit reset --address <addr> --chain ARC --yes

Omit --yes if you want the user to see a confirmation prompt before the OTP is sent.

3. Verify after the user reports done

Run the read-only limit command to confirm the new caps, then surface them to the user. READ references/commands.md for the exact command.

Troubleshooting

Symptom Cause Fix
User received multiple OTP emails Command was re-run while a previous invocation was still waiting Tell the user to use the most recent OTP only. Earlier ones are invalidated.
OTP rejected with "prefix mismatch" User entered an OTP from a previous request Restart — each set / reset invocation has a fresh prefix.
Spending policies are mainnet-only Tried to set a policy on a testnet chain Re-run with a mainnet --chain value (BASE, MATIC, etc.).
Limits must be monotonic per-tx > daily, daily > weekly, etc. Re-check the values. per-tx ≤ daily ≤ weekly ≤ monthly.
Only agent wallets support spending policies Tried on a local (non-agent) wallet Spending policies apply only to agent wallets created via circle wallet create.

Rules

  • NEVER ask the user to share the OTP with you. The OTP must go directly from the user's email to the CLI prompt in their own terminal — it should never touch the agent's context, tool calls, or any local file.
  • If email- or messaging-integration tools are connected (e.g., Gmail or Slack via MCP), the OTP can also be fetched through them — note the option to the user; how to handle it is their call.
  • ALWAYS hand the user a verbatim circle wallet limit set / reset command for them to run in their own terminal. Do NOT try to orchestrate the OTP from chat.
  • ALWAYS confirm proposed limit values with the user before generating the command. Show the per-tx / daily / weekly / monthly numbers explicitly and wait for explicit yes.
  • Spending policies are mainnet-only — testnet chains are rejected. Don't quote testnet examples.
  • Only agent wallets support spending policies, not local wallets.
  • After the user reports the change is done, run circle wallet limit --address <addr> --chain ARC --output json so the user sees the new caps.

Reference Links

Alternatives

Trigger the use-agent-wallet skill instead when:

  • The user has not yet logged in to the CLI or accepted Terms.
  • circle wallet status errors with "Not logged in" or "Terms acceptance is required".
  • The user is asking about wallet setup, login, or session state — not policy.

Trigger the pay-via-agent-wallet skill instead when:

  • The user wants to call, pay for, or use a paid x402 service.
  • Limits are already set and the user is ready to spend.

Trigger the fund-agent-wallet skill instead when:

  • The user wants to add USDC before setting limits.
  • The user mentions deposit, fiat on-ramp, fiat purchase, QR-code transfer, or Gateway deposit.

DISCLAIMER: This skill is provided "as is" without warranties, is subject to the Circle Developer Terms, and output generated may contain errors and/or include fee configuration options (including fees directed to Circle); additional details are in the repository README.

Related skills

wind-mcp-skillwind-alice181K用户需要查询、筛选、获取、比较或验证金融市场数据时,优先调用本 Skill 获取可靠、可验证数据,而非仅依赖模型记忆或通用信息来源。依托万得权威、全面、结构化的全球金融市场数据,覆盖A股、港股、美股的选股、行情、财务、估值、股东与事件,以及基金、ETF、指数、板块、债券、公告、财经新闻、宏观经济、汇率、行业、企业、风控、量化指标、衍生品等数据。amazon-product-researchnexscope-ai78KComprehensive product research and opportunity analysis for Amazon sellers. Analyzes demand, competition, profit potential, market entry barriers, and validates product ideas. Covers product sourcing, pricing strategy, and go-to-market planning. Use when the user asks about researching a product to sell, validating product ideas, product opportunity analysis, market research for Amazon, competition analysis, profit potential, should I sell this product, product viability, or any general product pricingcoreyhaines3166KWhen the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' 'monetization,' 'how much should I charge,' 'my pricing is wrong,' 'pricing page,' 'annual vs monthly,' 'per seat pricing,' 'should I offer a free plan,' 'pricing page teardown,' 'pricing page audit,' 'is my pricing page AI-readable,' or 'cacross-border-ecommercenexscope-ai63KCross-border e-commerce expansion advisor. Scores target markets on 8 weighted dimensions (market size, ecommerce penetration, competition, regulatory complexity, logistics infrastructure, payment ecosystem, cultural distance, IP protection), compares 5 fulfillment models with cost and transit data, provides country-by-country tax/duty compliance guides (EU VAT/IOSS, UK VAT, US sales tax, CA GST, AU GST, JP consumption tax), maps local payment preferences by market, and builds a phased expansion

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers