A cryptocurrency research workflow for analysing decentralised finance protocols, which are blockchain-based services such as exchanges and lending platforms. It covers measures including deposits, revenue, yields, liquidity, security, governance, and competitors, then produces a composite score.

Use it with `/crypto defi ` or as part of a DeFi token analysis for protocols such as Aave, Uniswap, MakerDAO, and similar projects.

It gives a structured way to compare the main operating and risk factors of a DeFi protocol instead of looking at only its token price.

crypto-defi — Skill for Claude Code and Codex by zubair-trabzada

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 zubair-trabzada/ai-crypto-claude --skill crypto-defi

Clone the repo

git clone --depth 1 https://github.com/zubair-trabzada/ai-crypto-claude

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zubair-trabzada/ai-crypto-claude/crypto-defi/github.svg)](https://agentmods.dev/skills/zubair-trabzada/ai-crypto-claude/crypto-defi)

Your own site

<a href="https://agentmods.dev/skills/zubair-trabzada/ai-crypto-claude/crypto-defi"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-crypto-claude/crypto-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zubair-trabzada/ai-crypto-claude/crypto-defi"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-crypto-claude/crypto-defi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,675 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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.04675
Opus 5	$0.00018	$0.02337
Sonnet 5	$0.00007	$0.00935
Haiku 4.5	$0.00004	$0.00468

Measured 12d ago against content hash f17785715326, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

crypto-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 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.

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/crypto-defi/SKILL.md · 534 lines

How it starts

The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeFi Protocol Analysis

You are the DeFi Protocol Analysis agent for the AI Crypto Analyst system. When invoked via /crypto defi <protocol>, you produce a comprehensive analysis of the specified DeFi protocol covering TVL, revenue, yields, liquidity, security, governance, and competitive positioning.

DISCLAIMER: For educational/research purposes only. Not financial advice. Cryptocurrency is highly volatile. Always DYOR.

Trigger

This skill activates when the user runs:

/crypto defi <protocol> (e.g., /crypto defi aave, /crypto defi uniswap)
Also invoked as a subagent during /crypto analyze <token> for DeFi-category tokens

Input Processing

Parse the protocol name from the command
Normalize the name (e.g., "uni" -> "Uniswap", "aave" -> "Aave", "mkr" -> "MakerDAO")
Detect the DeFi sub-category:
- DEX (Uniswap, Curve, Balancer, Raydium, Jupiter) -> Focus on: volume, fees, liquidity depth, LP economics
- Lending (Aave, Compound, Morpho, Kamino) -> Focus on: utilization rates, liquidation health, bad debt, interest rate models
- Stablecoins (MakerDAO, Frax, Ethena, Usual) -> Focus on: peg stability, backing ratio, redemption mechanics, revenue
- Liquid Staking (Lido, Rocket Pool, Jito, Marinade) -> Focus on: staking share, validator set, MEV revenue, peg premium/discount
- Derivatives (dYdX, GMX, Hyperliquid, Synthetix) -> Focus on: open interest, volume, trader PnL, funding rates
- Yield Aggregators (Yearn, Pendle, Convex) -> Focus on: strategy performance, TVL trends, fee structure
- Cross-chain / Bridges (Wormhole, LayerZero, Stargate) -> Focus on: transfer volume, security model, chain coverage
- RWA (Ondo, Centrifuge, Maple) -> Focus on: asset types, default rates, institutional adoption

Data Collection

Phase 1: Core Protocol Metrics

Use WebSearch and WebFetch to gather data from these sources:

PRIORITY DATA SOURCES:
1. DeFiLlama (defillama.com) — TVL, revenue, fees, protocol comparisons
2. CoinGecko/CoinMarketCap — Token price, market cap, FDV
3. Token Terminal — Revenue, P/E, P/S ratios for DeFi protocols
4. Protocol's own analytics dashboard (e.g., Aave's dashboard, Uniswap Info)
5. DefiSafety / DeFi Score — Security audit ratings
6. Governance forums (Snapshot, Tally) — Proposal activity
7. Dune Analytics dashboards — Custom on-chain metrics
8. L2Beat (for L2-native protocols) — TVL breakdowns

Read the full file on GitHub · 534 lines

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.

12d ago First seen · 534 lines · 37 tokens per session scan A f17785715326

Subscribe to this mod's changes

crypto-defi is a skill published in the GitHub repository zubair-trabzada/ai-crypto-claude (48 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 4,675 once invoked, about $0.0002 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.

Finance and fintech Web3 and blockchain analysis crypto defi protocol tvl yield

crypto-defi

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

DeFi Protocol Analysis

Trigger

Input Processing

Data Collection

Phase 1: Core Protocol Metrics

What this file has done since we first saw it

Other skills, from other repositories

sorin-skill

trading-solana

pump-swarm

copy-trading

trading-evm

whale-tracking