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 agentmods add commands/trustwallet/tw-agent-skills/setupgit clone --depth 1 https://github.com/trustwallet/tw-agent-skillsWhat 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 | $0.00079 | $0.00509 |
| Opus 5 | $0.00039 | $0.00254 |
| Sonnet 5 | $0.00016 | $0.00102 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
setup 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 3d 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.
What it actually says
Setup — Authentication & Configuration
This is the foundation skill. Every other Trust Wallet API skill depends on it for auth headers, base URLs, and chain identifiers.
Quick Reference
| Base URL | Auth | Used By |
|---|---|---|
https://tws.trustwallet.com |
HMAC-SHA256 | Token prices, security, swap quotes, market listings, assets |
Asset ID Format
- Native coin:
c{coinId}— e.g.,c60(ETH),c714(BNB),c501(SOL) - Token:
c{coinId}_t{contractAddress}— e.g.,c60_t0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48(USDC on Ethereum)
The coinId follows the SLIP-44 standard.
Common Chain IDs
| Chain | Coin ID | Symbol |
|---|---|---|
| Ethereum | 60 | ETH |
| BNB Smart Chain | 714 | BNB |
| Solana | 501 | SOL |
| Bitcoin | 0 | BTC |
| Polygon | 966 | MATIC |
| Arbitrum | 10042221 | ETH |
| Optimism | 10000070 | ETH |
| Base | 10008453 | ETH |
| Tron | 195 | TRX |
| Avalanche | 10009000 | AVAX |
For the full list of 100+ supported chains and the complete HMAC-SHA256 signing algorithm with code examples (JS and Python), read the detailed reference:
Read skills/api/references/setup.md for:
- Full HMAC-SHA256 signing algorithm and pseudocode
- JavaScript and Python code examples for request signing
- Complete list of all supported EVM, UTXO, Cosmos, Solana, and other L1 chains
- Chain key vs chain ID mapping for swap endpoints
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.
- 3d ago First seen · 44 lines · 79 tokens per session scan A d444a3a9ce57
setup is a command published in the GitHub repository trustwallet/tw-agent-skills (94 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 509 once invoked, about $0.0004 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 commands, from other repositories
brainblast-firewall
Inspect a serialized Solana transaction before signing it — the AI-agent transaction firewall.
audit-strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Aggressively cuts false positives.
fix-btc-e2e-p6
Fix errors in BTC E2E test (Pattern 6: P2WSH 2-of-3 Multisig).
deploy-testnet
Guided testnet deploy for EVM chains (Base, ETH, Arb, Polygon).
maxia-stocks
Trade tokenized US stocks on MAXIA (AAPL, TSLA, NVDA, etc.).
setup-ci-cd
Setup CI/CD pipeline with automated security checks for Solana programs.