lifi

lifi is a skill for Claude Code, Codex from Demerzels-lab/elsamultiskillagent. It costs 28 tokens per session (2,201 once invoked), scanned A, original, MIT.

A service for bridging and swapping tokens across more than 30 blockchain networks. It combines liquidity from decentralized exchanges and bridge protocols to find routes between chains.

In plain words
What is it for?
Use it to bridge tokens between supported blockchains, swap assets through aggregated decentralized exchanges, and optimize routes. Swaps include a disclosed 0.3% integrator fee.
Why use it?
It helps handle cross-chain transfers and swaps without arranging each bridge or exchange separately.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to bridge tokens between supported blockchains, swap assets through aggregated decentralized exchanges, and optimize routes. Swaps include a disclosed 0.3% integrator fee.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/demerzels-lab/elsamultiskillagent/lifi
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 Demerzels-lab/elsamultiskillagent --skill lifi
Clone the repo
git clone --depth 1 https://github.com/Demerzels-lab/elsamultiskillagent

Made for: Claude Code, Codex.

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 lifi

README.md
[![agentmods](https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/lifi/github.svg)](https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/lifi)
Your own site
<a href="https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/lifi"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/lifi/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 lifi

Your own site · 80×15
<a href="https://agentmods.dev/skills/demerzels-lab/elsamultiskillagent/lifi"><img src="https://agentmods.dev/badge/skills/demerzels-lab/elsamultiskillagent/lifi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,201 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00028 $0.02201
Opus 5 $0.00014 $0.01100
Sonnet 5 $0.00006 $0.00440
Haiku 4.5 $0.00003 $0.00220

Measured 12d ago against content hash d0626ce8be78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

lifi scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

metadata: {"clawdbot":{"emoji":"🌉","always":true,"requires":{"bins":["curl","jq"]}}}
public/skills/0xterrybit/lifi/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LI.FI 🌉

Multi-chain liquidity aggregation protocol. Bridge and swap tokens across 30+ blockchains.

Environment Variables

Variable Description Required
LIFI_API_KEY API key for higher rate limits No
LIFI_INTEGRATOR Integrator ID for analytics No

💎 Integrator Fee Configuration

This skill includes a small integrator fee (0.3%) on swaps to support development. The fee is transparently disclosed to users before each transaction.

Variable Value Description
INTEGRATOR_ID CyberPay Integrator identifier (registered at portal.li.fi)
INTEGRATOR_FEE 0.003 0.3% integrator fee
FEE_RECIPIENT 0x890CACd9dEC1E1409C6598Da18DC3d634e600b45 EVM wallet to receive fees

Fee Breakdown:

  • User pays: 0.3% of swap output
  • Integrator receives: 100% of fee (after LI.FI service fee)

💡 Fees are accumulated in the LI.FI contract and can be withdrawn via the LI.FI Portal or API.

Features

  • 🌉 Cross-Chain Bridges - 15+ bridge protocols
  • 🔄 DEX Aggregation - Best rates across DEXs
  • ⛓️ 30+ Chains - Ethereum, Arbitrum, Polygon, Solana, etc.
  • 🛡️ Route Optimization - Fastest, cheapest, or safest routes
  • 💰 Fee Estimation - Transparent gas and bridge fees

API Base URL

https://li.quest/v1

Get Supported Chains

curl -s "https://li.quest/v1/chains" | jq '.chains[] | {id: .id, name: .name, nativeToken: .nativeToken.symbol}'

Get Supported Tokens

# Get tokens for a specific chain
CHAIN_ID="1"  # Ethereum

curl -s "https://li.quest/v1/tokens?chains=${CHAIN_ID}" | jq ".tokens.\"${CHAIN_ID}\"[:10]"

Get Quote (Cross-Chain Swap)

FROM_CHAIN="1"        # Ethereum
TO_CHAIN="42161"      # Arbitrum
FROM_TOKEN="0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48"  # USDC on ETH
TO_TOKEN="0xaf88d065e77c8cC2239327C5EDb3A432268e5831"    # USDC on ARB
FROM_AMOUNT="100000000"  # 100 USDC (6 decimals)
FROM_ADDRESS="<YOUR_WALLET>"

# Integrator fee configuration
INTEGRATOR="CyberPay"
INTEGRATOR_FEE="0.003"  # 0.3%

curl -s "https://li.quest/v1/quote" \
  -G \
  --data-urlencode "fromChain=${FROM_CHAIN}" \
  --data-urlencode "toChain=${TO_CHAIN}" \
  --data-urlencode "fromToken=${FROM_TOKEN}" \
  --data-urlencode "toToken=${TO_TOKEN}" \
  --data-urlencode "fromAmount=${FROM_AMOUNT}" \
  --data-urlencode "fromAddress=${FROM_ADDRESS}" \
  --data-urlencode "integrator=${INTEGRATOR}" \
  --data-urlencode "fee=${INTEGRATOR_FEE}" | jq '{
    tool: .toolDetails.name,
    estimatedOutput: .estimate.toAmount,
    gasCost: .estimate.gasCosts,
    executionTime: .estimate.executionDuration,
    integratorFee: .estimate.feeCosts,
    route: .includedSteps
  }'

Read the full file on GitHub · 254 lines

Files

What ships with it

2 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. 12d ago First seen · 254 lines · 28 tokens per session scan A d0626ce8be78

Subscribe to this mod's changes

lifi is a skill published in the GitHub repository Demerzels-lab/elsamultiskillagent (10 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 2,201 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.