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.
npx skills add circlefin/skills --skill agent-wallet-policygit clone --depth 1 https://github.com/circlefin/skillsWrote 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.
[](https://agentmods.dev/skills/circlefin/skills/agent-wallet-policy)<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.
<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>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
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.
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.
| Model | Per session | Once 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 |
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.
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:
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.
- 9d ago First seen · 136 lines · 118 tokens per session scan A f523dce272e2
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.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.