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 san-npm/skills-ws --skill wallet-integrationgit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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/san-npm/skills-ws/wallet-integration)<a href="https://agentmods.dev/skills/san-npm/skills-ws/wallet-integration"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/wallet-integration/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/san-npm/skills-ws/wallet-integration"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/wallet-integration.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 | $0.00072 | $0.01106 |
| Opus 5.5 | $0.00029 | $0.00442 |
| Sonnet 5.5 | $0.00014 | $0.00221 |
| Haiku 4.5 | $0.00007 | $0.00111 |
Grade A, and why
wallet-integration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web3 Wallet Integration
Stack: wagmi v2 + viem v2 + @tanstack/react-query v5. ethers-era patterns are out. RainbowKit and ConnectKit are wallet-UI layers on top of wagmi. Note: wagmi v3 is the latest major (it renames
useAccounttouseConnectionand hook action functions tomutate/mutateAsync, and makes connector SDKs optional peer deps), but RainbowKit and ConnectKit still peer-require wagmi 2.x, so this skill targets wagmi v2: installwagmi@2, not latest. For kit-free builds you can adopt wagmi v3 via https://wagmi.sh/react/guides/migrate-from-v2-to-v3 (the hooks below need the v3 renames applied).
Address typing rule (read first). wagmi/viem use the template-literal type
`0x${string}`for every address. A placeholder like'0xRecipient...'(with a literal...) is not assignable to that type — TypeScript will reject it and the example won't compile. Every address in this skill is a full 40-hex-char value. None of these are real or safe to use on mainnet — replace them with addresses you have verified for the correct chain. Centralize them so they're easy to swap:
// addresses.ts — verified per chain; replace before mainnet use.
import type { Address } from 'viem';
// USDC on Ethereum mainnet (chainId 1). USDC has a DIFFERENT address on every chain —
// never reuse an address across chains. Look up the canonical address per chain.
export const USDC_MAINNET: Address = '0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48';
// Obvious dummy recipients/contracts for examples. Do NOT send funds here.
export const RECIPIENT: Address = '0x70997970C51812dc3A010C7d01b50e0d17dc79C8'; // Anvil acct #1
export const EXAMPLE_CONTRACT: Address = '0x5FbDB2315678afecb367f032d93F642f64180aa3'; // Anvil deploy #0
export const ZERO_ADDRESS: Address = '0x0000000000000000000000000000000000000000';
Safety gate
Before executing commands or changing external systems, confirm scope, credentials, target environment, rollback, and required approval. Pin and verify third-party artifacts; never expose secrets to client code or logs.
What ships with it
14 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.
- agents/openai.yaml 181 B
- references/1-wagmi-v2-viem-setup.md 1.8 KB
- references/10-error-handling-patterns.md 1.2 KB
- references/11-mobile-wallet-deep-links.md 1.5 KB
- references/12-walletconnect-reown-project-id.md 992 B
- references/13-security-guardrails-money-moving-read-before-shipping.md 4.5 KB
- references/2-rainbowkit-quick-start.md 5.0 KB
- references/3-connectkit-alternative.md 1.1 KB
- references/4-contract-read-write-hooks.md 4.7 KB
- references/5-eip-712-typed-message-signing.md 1.9 KB
- references/6-chain-switching.md 661 B
- references/7-ens-resolution.md 683 B
- references/8-viem-client-non-react.md 1.5 KB
- references/9-typescript-contract-types.md 1.1 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.
- 2mo ago First seen · 46 lines · 72 tokens per session scan A 65c111cad9e4
wallet-integration is a skill published in the GitHub repository san-npm/skills-ws (4 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,106 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-07.
wallet-integration compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wallet-integrationsan-npm/skills-ws | Skill | 4 | 1mo ago | MIT | A | 72 | Codex |
| onchainkitalsk1992/CloddsBot | Skill | 3.1k | 1mo ago | MIT | A | 24 | Claude Code, Codex |
| devtools-event-clientTanStack/devtools | Skill | 510 | yesterday | MIT | A | 79 | Claude Code, Codex |
| walkeros-create-destinationelbwalker/walkerOS | Skill | 349 | 2d ago | MIT | A | 77 | Claude Code |
| walkeros-create-sourceelbwalker/walkerOS | Skill | 349 | 2d ago | MIT | A | 65 | Claude Code |
| implementing-mcp-toolsPostHog/posthog | Skill | 41k | yesterday | none | A | 58 | Claude Code, Codex |
| adding-personhog-rpcPostHog/posthog | Skill | 41k | yesterday | none | A | 88 | Claude Code, Codex |