1inch-swap

1inch-swap is a skill for Claude Code from 1inch/1inch-ai. It costs 59 tokens per session (792 once invoked), scanned A, original, MIT.

A token-swap tool for exchanging digital tokens across supported blockchain networks. It can compare or use on-chain swaps, gasless orders, and cross-chain transfers.

In plain words
What is it for?
Getting swap quotes, comparing swap types, executing trades through a connected wallet, and creating unsigned transaction data for signing elsewhere.
Why use it?
It removes the need to manually find a route, build transaction data, and handle each approval step separately.

Skill for Claude Code

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

Part of the 1inch-mcp plugin — 9 skills, 1 MCP server shipped together

Good fit Getting swap quotes, comparing swap types, executing trades through a connected wallet, and creating unsigned transaction data for signing elsewhere.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/1inch/1inch-ai/1inch-swap
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 1inch/1inch-ai --skill 1inch-swap
Clone the repo
git clone --depth 1 https://github.com/1inch/1inch-ai

Made for: Claude Code.

Or install 1inch-mcp, the plugin that ships this one along with the rest of its 9 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 1inch-swap

README.md
[![agentmods](https://agentmods.dev/badge/skills/1inch/1inch-ai/1inch-swap/github.svg)](https://agentmods.dev/skills/1inch/1inch-ai/1inch-swap)
Your own site
<a href="https://agentmods.dev/skills/1inch/1inch-ai/1inch-swap"><img src="https://agentmods.dev/badge/skills/1inch/1inch-ai/1inch-swap/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 1inch-swap

Your own site · 80×15
<a href="https://agentmods.dev/skills/1inch/1inch-ai/1inch-swap"><img src="https://agentmods.dev/badge/skills/1inch/1inch-ai/1inch-swap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 792 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.
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 $0.00059 $0.00792
Opus 5 $0.00030 $0.00396
Sonnet 5 $0.00012 $0.00158
Haiku 4.5 $0.00006 $0.00079

Measured 10d ago against content hash bc157733b54f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

1inch-swap 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 10d 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.

skills/1inch-swap/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

1inch Swap

Use the authenticated MCP tool swap. Do not hand-build calldata for normal flows.

Unless the user explicitly wants to sign with their own tooling (private key, cast, viem), offer WalletConnect before executing: pair via the walletconnect tool (see the 1inch-walletconnect skill), then call swap. With an active session, execute defaults to true — the tool handles approve txs, EIP-712 signing, submission, and native escrow sends through the connected wallet, and the user simply approves each prompt in their wallet app. No key handling, no manual signing steps.

  • Set execute: false only when the user wants unsigned calldata / typed data to sign elsewhere.
  • Set execute: true explicitly to require a wallet session (errors if not connected).

Modes

  • Classic — on-chain via aggregation router; user pays gas. preferredType: "classic".
  • Fusion — gasless intent; resolvers fill. preferredType: "fusion".
  • Cross-chain — set dstChain; preferredType: "crosschain".

Approaches

  1. Wallet-first (recommended): connect via walletconnect, then call swap with src, dst, amount, chain, from (the connected wallet address). The user approves in their wallet.
  2. Shortcut: call swap directly. Omit preferredType to let the server recommend, or set it explicitly.
  3. Full flow: quoteOnly: true → compare quotes / recommended → execute with chosen preferredType.
  4. Manual Fusion/cross-chain submit (no wallet session): after signing typed data locally, call again with signedOrder + orderHash.

Flow guides (bundled references)

Load the reference for your flow before signing or broadcasting:

Flow Reference MCP resource fallback
Quote references/QUOTE.md file://1inch-mcp/guides/swap/quote
Classic references/CLASSIC.md file://1inch-mcp/guides/swap/classic
Fusion references/FUSION.md file://1inch-mcp/guides/swap/fusion
Cross-chain references/CROSSCHAIN.md file://1inch-mcp/guides/swap/crosschain

Read the full file on GitHub · 55 lines

Files

What ships with it

4 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.

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. 10d ago First seen · 55 lines · 59 tokens per session scan A bc157733b54f

Subscribe to this mod's changes

1inch-swap is a skill published in the GitHub repository 1inch/1inch-ai (2 stars, last pushed 13d ago), licensed MIT. It adds 59 tokens to every session and 792 once invoked, about $0.0003 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 2026-08-31.