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 trustwallet/tw-agent-skills --skill walletgit clone --depth 1 https://github.com/trustwallet/tw-agent-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/trustwallet/tw-agent-skills/wallet)<a href="https://agentmods.dev/skills/trustwallet/tw-agent-skills/wallet"><img src="https://agentmods.dev/badge/skills/trustwallet/tw-agent-skills/wallet/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/trustwallet/tw-agent-skills/wallet"><img src="https://agentmods.dev/badge/skills/trustwallet/tw-agent-skills/wallet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00132 | $0.01138 |
| Opus 5 | $0.00066 | $0.00569 |
| Sonnet 5 | $0.00026 | $0.00228 |
| Haiku 4.5 | $0.00013 | $0.00114 |
Grade A, and why
trust-wallet-cli 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trust Wallet CLI (twak)
Command-line interface for multichain crypto wallet operations. Install with npm install -g @trustwallet/cli.
Quick Start
Read references/setup.md for installation and authentication.
Reference Guide
Read the reference that matches the user's task:
| Task | Reference | When to read |
|---|---|---|
| Install, auth, env vars | references/setup.md |
First time setup, "install twak", "configure API keys" |
| List supported chains, chain keys | references/setup.md |
"what chains are supported", "list chains", "show chain keys", "what is the chain key for X" |
| Create wallet, keychain, sign, register | references/wallet.md |
"create wallet", "keychain", "sign message", "wallet status", "register wallet with backend" |
| Balance, holdings, portfolio | references/balance.md |
"check balance", "portfolio", "token holdings" |
| Send tokens, ENS transfers | references/send.md |
"send ETH", "transfer to", "vitalik.eth" |
| Swap tokens, cross-chain | references/swap.md |
"swap ETH for USDC", "bridge", "cross-chain swap" |
| Buy/sell crypto with fiat | references/onramp.md |
"buy ETH with USD", "onramp", "offramp", "fiat", "sell crypto for cash" |
| Prices, trending, DApps | references/market.md |
"price of", "trending tokens", "dapps" |
| Transaction history | references/history.md |
"tx history", "transaction details" |
| Price alerts | references/alerts.md |
"alert when ETH", "price alert", "notify me" |
| DCA & limit orders | references/automations.md |
"DCA", "dollar cost average", "limit order", "recurring swap", "buy when price" |
| ERC-20 approve/revoke | references/erc20.md |
"approve spender", "check allowance", "revoke" |
| Token risk checks | references/token-risk.md |
"is this token safe", "honeypot check", "audit status" |
| x402 micropayments | references/x402.md |
"x402", "micropayment", "payment-gated API", "preview payment", "quote endpoint cost", "how much does this API charge" |
| BNB Hack competition register/status | references/compete.md |
"register for the competition", "BNB hack", "AI trading agent edition", "compete", "registration status" |
| Register/manage ERC-8004 agent identities | references/erc8004.md |
"register agent identity", "erc8004", "agent NFT", "agentURI", "agent metadata", "identity registry", "mint agent" |
| Agent job escrows (ERC-8183 Agentic Commerce) | references/erc8183.md |
"erc8183", "agentic commerce", "job escrow", "create job", "fund job", "submit deliverable", "settle job", "dispute policy", "policy-info", "agent payment escrow", "evaluator router" |
| Run MCP / REST server for AI agents | MCP server section below | "MCP server", "twak serve", "connect an agent", "REST API" |
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/alerts.md 3.1 KB
- references/automations.md 5.5 KB
- references/balance.md 3.9 KB
- references/compete.md 2.5 KB
- references/erc20.md 5.6 KB
- references/erc8004.md 6.3 KB
- references/erc8183.md 10 KB
- references/history.md 2.5 KB
- references/market.md 3.5 KB
- references/onramp.md 7.1 KB
- references/send.md 7.2 KB
- references/setup.md 5.0 KB
- references/swap.md 5.5 KB
- references/token-risk.md 1.5 KB
- references/wallet.md 3.3 KB
- references/x402.md 14 KB
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 · 53 lines · 132 tokens per session scan A 79db4c71dff3
trust-wallet-cli is a skill published in the GitHub repository trustwallet/tw-agent-skills (97 stars, last pushed 2mo ago), licensed MIT. It adds 132 tokens to every session and 1,138 once invoked, about $0.0007 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
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
cobie-cycle-filter
Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).