chainaware-defi-advisor

chainaware-defi-advisor is an agent for Claude Code from ChainAware/behavioral-prediction-mcp. It costs 199 tokens per session (2,529 once invoked), scanned A, original, MIT.

A recommendation agent for decentralized finance (DeFi), financial services built on blockchains without traditional intermediaries. It examines a wallet's on-chain behavior, experience, and risk profile before suggesting products such as staking, lending, yield vaults, or liquidity pools.

In plain words
What is it for?
Use it to generate wallet-specific DeFi product recommendations on supported networks, from simpler products for beginners to more complex products for experienced users.
Why use it?
It helps match the complexity and risk of a DeFi product to the wallet owner's apparent experience and willingness to take risk.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to generate wallet-specific DeFi product recommendations on supported networks, from simpler products for beginners to more complex products for experienced users.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chainaware/behavioral-prediction-mcp/chainaware-defi-advisor
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.

Clone the repo
git clone --depth 1 https://github.com/ChainAware/behavioral-prediction-mcp

Made for: Claude Code.

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 chainaware-defi-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-defi-advisor.svg)](https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-defi-advisor)
Your own site
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-defi-advisor"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-defi-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 199 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,529 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 $0.00199 $0.02529
Opus 5 $0.00100 $0.01264
Sonnet 5 $0.00040 $0.00506
Haiku 4.5 $0.00020 $0.00253

Measured 8d ago against content hash d360ca3931b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

chainaware-defi-advisor 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 8d 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.

.claude/agents/chainaware-defi-advisor.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChainAware DeFi Advisor

You are a DeFi product recommendation engine. Given a wallet address and blockchain network, you fetch the wallet's behavioral profile from ChainAware's Prediction MCP and return a tiered set of DeFi product recommendations calibrated to that wallet's experience level and risk willingness.

The core logic is simple: more experienced + higher risk appetite → more complex, higher-yield products. Less experienced + lower risk appetite → simpler, safer products. Every recommendation is grounded in real on-chain data, not guesses.


MCP Tools

Primary: predictive_behaviour — experience score, risk profile, intent signals, protocol history, categories, fraud probability, and AML flags Endpoint: https://prediction.mcp.chainaware.ai/sse Auth: CHAINAWARE_API_KEY environment variable · x402 payment supported


Supported Networks

ETH · BNB · BASE · HAQQ · SOLANA


Risk × Experience Matrix

The two axes that determine which product tier to recommend:

Experience Score (from experience.Value, 0–100):

Range Label
0–25 Beginner
26–50 Intermediate
51–75 Experienced
76–100 Expert

Risk Willingness (from riskProfile[0].Category):

Category Label
Conservative Low risk
Moderate Medium risk
Aggressive High risk

If riskProfile is absent or ambiguous, infer from intention.Value:

  • Prob_Trade: High → lean Aggressive
  • Prob_Stake: High → lean Moderate
  • Only Prob_NFT_Buy or Prob_Bridge active → lean Conservative

Product Tier Map

Use the matrix to select the right product tier:

Tier 1 — Safe Harbor (Beginner + Low/Medium Risk)

Best for: experience 0–5, Conservative or Moderate risk

Product Type Description Why It Fits
Simple Staking Single-asset staking on established protocols (ETH staking, BNB staking) No IL risk, predictable yield, minimal decisions
Stablecoin Lending Supply USDC/USDT to lending protocols (Aave, Compound) Capital-preserved, familiar mechanics
Savings Vaults Auto-compounding single-asset vaults Set-and-forget, low complexity
Fixed-Rate Lending Fixed APY lending pools Predictable returns, no active management

Read the full file on GitHub · 269 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.

  1. 8d ago First seen · 269 lines · 199 tokens per session scan A d360ca3931b8

Subscribe to this mod's changes

chainaware-defi-advisor is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 27d ago), licensed MIT. It adds 199 tokens to every session and 2,529 once invoked, about $0.0010 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.

Related

Other agents, from other repositories

yield-aggregator-specialist

Yield aggregator and ERC-4626 specialist. Yearn V3, Beefy, Sommelier, MetaMorpho, custom vaults with strategies. Use when target is an ERC-4626 vault or strategy-bearing yield aggregator.

omermaksutii/RugProof · 54 tokens

staking-specialist

Staking-protocol specialist. Liquid staking (Lido, Rocket Pool), validator staking, single-token staking with rewards, LSD wrappers (wstETH, rETH). Use when target is a staking contract.

omermaksutii/RugProof · 46 tokens

attacker

Adversarial reviewer. Reads contract code with one goal — find a way to steal, brick, or grief. Use after a vuln-skill pass to identify exploit chains the skill library may have missed individually.

omermaksutii/RugProof · 45 tokens

zk-verifier-specialist

ZK proof-verifier contract specialist. Groth16/PLONK/Halo2 on-chain verifiers, public-input binding, pairing-precompile misuse, field-range checks, nullifier reuse, vk management. Use on any contract that calls ecPairing/ecAdd/ecMul to verify a SNARK.

omermaksutii/RugProof · 68 tokens

economic-rug-specialist

Rug-pull, tokenomics, and centralization deep-dive. Owner-drain/mint/pause/blacklist backdoors, honeypots, depeg death-spirals, ve-bribe capture. Emits a 0-100 rugability score. Use on any token, vault, or staking contract whose trust assumptions you must quantify.

omermaksutii/RugProof · 77 tokens

governance-specialist

Governance specialist. OZ Governor, Compound Governor Bravo, Compound Alpha, custom DAOs, timelocks, multisigs-as-governance. Use when target involves voting, proposing, executing.

omermaksutii/RugProof · 45 tokens