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 ChainGPT-org/chaingpt-claude-skill --skill defigit clone --depth 1 https://github.com/ChainGPT-org/chaingpt-claude-skillWrote 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/chaingpt-org/chaingpt-claude-skill/defi)<a href="https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/defi"><img src="https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/defi/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/chaingpt-org/chaingpt-claude-skill/defi"><img src="https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/defi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00186 | $0.01694 |
| Opus 5 | $0.00093 | $0.00847 |
| Sonnet 5 | $0.00037 | $0.00339 |
| Haiku 4.5 | $0.00019 | $0.00169 |
Grade A, and why
defi 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainGPT DeFi Skill
You manage real DeFi positions on mainnet. The plugin is custody-free — it returns unsigned transactions; the user signs externally via MetaMask, Rabby, hardware wallet, ERC-4337 smart account, or WalletConnect.
Protocols supported
| Protocol | What | Chains |
|---|---|---|
| Aave V3 | Lending market (supply / borrow / repay / withdraw + health) | ethereum, base, arbitrum, optimism, polygon, bsc, avalanche |
| Lido | stETH liquid staking | Ethereum mainnet |
| EigenLayer | Restake LSTs (stETH / rETH / cbETH / …) | Ethereum mainnet |
| Pendle (read) | Yield-trading markets — split assets into PT (fixed) + YT (floating) | ethereum, arbitrum, optimism, bsc, base, mantle |
| Morpho Blue (read) | Isolated lending markets + MetaMorpho curated vaults | ethereum, base |
Hard rules for mainnet
- Before borrowing or withdrawing from Aave, ALWAYS call
chaingpt_defi_aave_healthand surface the health factor. Borrowing or withdrawing collateral lowers HF; if it drops below 1.0 the position is liquidated. Refuse the action and tell the user to top up if HF would drop below 1.2 after the requested operation. - Before supplying, repaying, or depositing, verify the user has approved the pool / strategy manager. ERC-20 approval is a separate signed transaction. Use
chaingpt_dex_approve_tx token=<asset> spender=<aave-pool-or-strategy-manager> acknowledgeMainnet=truefirst if not done (the ack gate applies to approvals too). - Echo the USD-equivalent values before asking for confirmation. Pull the asset price from
chaingpt_research_tokenif not obvious. - For Lido stake, note that stETH rebases — the balance grows daily. Don't store the staked amount as the "stETH balance"; it will diverge.
- For EigenLayer, note the 7-day withdrawal queue. Deposits are functionally illiquid for a week. Surface this fact before asking for confirmation.
The "supply on Aave" pipeline
chaingpt_research_token # confirm the asset (price, contract)
chaingpt_defi_aave_health # current position state (if any)
chaingpt_dex_approve_tx # approve the Aave Pool to spend the asset (acknowledgeMainnet=true)
spender=<AAVE_POOL_ADDRESS> # surface this from the build_tx output
chaingpt_defi_aave_supply_tx # REFUSES mainnet unless acknowledgeMainnet=true
│
▼
[user signs + broadcasts]
│
▼
chaingpt_defi_aave_health # confirm the supply landed in the position
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 · 119 lines · 186 tokens per session scan A fa71b69aadfb
defi is a skill published in the GitHub repository ChainGPT-org/chaingpt-claude-skill (16 stars, last pushed 10d ago), licensed MIT. It adds 186 tokens to every session and 1,694 once invoked, about $0.0009 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
perp-cli
Multi-DEX perpetual futures trading via the perp-cli command-line tool. Use when user asks to: trade perps, check funding rates, scan/execute arbitrage (perp-perp or spot-perp), run delta-neutral strategies, bridge USDC across chains, manage positions/orders/leverage, deposit/withdraw, hedge spot+perp, trade HIP-3…
propfund
Trade on PropFund, the decentralized on-chain prop firm for AI agents. Use this skill to get funded with the liquidity pool's capital and trade without risking your own bankroll — pass a transparent evaluation, then place leveraged long/short trades with mandatory stop-loss/take-profit and on-chain risk limits, and…
suwappu
Build with the Suwappu REST API: cross-chain quotes, simulation, self-custody or managed swaps, managed-wallet portfolio/prices, Polymarket research and orders, Hyperliquid market research, and Morpho lending-market research.
suwappu-dex
Use Suwappu's hosted MCP server for cross-chain quotes, swap simulation and unsigned transaction preparation, managed-wallet portfolio reads, prices, prediction-market research, Hyperliquid research, and Morpho market data.
ethereum-defi
Ethereum DeFi skill — query balances, get Chainlink prices, estimate gas, resolve ENS names, call smart contracts, ABI-encode functions, interact with ERC-8004 agent registry, query EAS attestations.
defi-protocols
DeFi protocol authority — flashloans, AMM design, lending markets, concentrated liquidity, MEV, triangular and cross-DEX arbitrage, stablecoin depeg dynamics, and on-chain capital routing across Uniswap V3, Aerodrome, Balancer, Curve, and Aave V3 on Ethereum, Base, Arbitrum, Optimism, and Polygon.