agent-wallet-policy

agent-wallet-policy is a skill for Claude Code from circlefin/skills. It costs 118 tokens per session (1,605 once invoked), scanned A, original, Apache-2.0.

A spending-policy check for Circle agent wallets, which are wallets controlled through Circle’s command-line tool. It shows the USDC limits set for each payment or transfer.

In plain words
What is it for?
Inspect the current spending limits of a mainnet Circle agent wallet. Changing or resetting limits requires the user to confirm with a one-time password in their own terminal.
Why use it?
It helps you see whether a wallet has per-transaction, daily, weekly, or monthly spending caps before sending funds.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the circle plugin — 18 skills, 1 MCP server shipped together

Good fit Inspect the current spending limits of a mainnet Circle agent wallet. Changing or resetting limits requires the user to confirm with a one-time password in their own terminal.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/circlefin/skills/agent-wallet-policy
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add circlefin/skills --skill agent-wallet-policy
Clone the repo
git clone --depth 1 https://github.com/circlefin/skills

Made for: Claude Code.

Or install circle, the plugin that ships this one along with the rest of its 18 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-wallet-policy

README.md
[![agentmods](https://agentmods.dev/badge/skills/circlefin/skills/agent-wallet-policy/github.svg)](https://agentmods.dev/skills/circlefin/skills/agent-wallet-policy)
Your own site
<a href="https://agentmods.dev/skills/circlefin/skills/agent-wallet-policy"><img src="https://agentmods.dev/badge/skills/circlefin/skills/agent-wallet-policy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-wallet-policy

Your own site · 80×15
<a href="https://agentmods.dev/skills/circlefin/skills/agent-wallet-policy"><img src="https://agentmods.dev/badge/skills/circlefin/skills/agent-wallet-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,605 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 11 May 2026
  • Snyk warn 11 May 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 102
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00118 $0.01605
Opus 5 $0.00059 $0.00803
Sonnet 5 $0.00024 $0.00321
Haiku 4.5 $0.00012 $0.00161

Measured 9d ago against content hash f523dce272e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-wallet-policy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/circle/skills/agent-wallet-policy/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 BASE --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

# Confirm session is good
circle wallet status

# Get the wallet address
circle wallet list --chain BASE --type agent --output json

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 BASE --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.

Step 1 — Confirm values with the user

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

A typical conservative configuration:

Read the full file on GitHub · 136 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 136 lines · 118 tokens per session scan A f523dce272e2

Subscribe to this mod's changes

agent-wallet-policy is a skill published in the GitHub repository circlefin/skills (147 stars, last pushed 26d ago), licensed Apache-2.0. It adds 118 tokens to every session and 1,605 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories