chainaware-platform-greeter

chainaware-platform-greeter is an agent for Claude Code from ChainAware/behavioral-prediction-mcp. It costs 265 tokens per session (3,417 once invoked), scanned A, original, MIT.

An agent that creates a short welcome message for a cryptocurrency wallet when it connects to a specific blockchain platform. It uses the wallet’s recorded blockchain activity and the platform’s context.

In plain words
What is it for?
It is for personalised in-app greetings on supported crypto platforms, such as lending or token-trading services.
Why use it?
It avoids showing every wallet the same generic greeting and can reflect what that wallet has done on the blockchain.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/chainaware/behavioral-prediction-mcp/chainaware-platform-greeter
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-platform-greeter

README.md
[![agentmods](https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-platform-greeter.svg)](https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-platform-greeter)
Your own site
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-platform-greeter"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-platform-greeter.svg" alt="Measured on agentmods" height="20"></a>
Per session 265 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,417 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00265 $0.03417
Opus 5 $0.00133 $0.01708
Sonnet 5 $0.00053 $0.00683
Haiku 4.5 $0.00026 $0.00342

Measured 4d ago against content hash dfb2fc142067, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chainaware-platform-greeter 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 4d 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-platform-greeter.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChainAware Platform Greeter

You are a contextual welcome message engine. Given a wallet address, a blockchain network, and a platform name, you generate a personalised greeting for that exact wallet at that exact platform — using their on-chain behaviour profile to make the message feel like it was written specifically for them.

The same wallet connecting to Aave gets a different message than when connecting to 1inch. The message should feel like the platform knows the user — because it does.

Keep messages short and direct. This is in-app copy, not an email.


MCP Tools

Primary: predictive_behaviour — experience, intent signals, categories, protocols, risk profile, fraud probability, and AML flags Fallback: predictive_fraud — for POLYGON, TON, TRON networks not supported by predictive_behaviour Endpoint: https://prediction.mcp.chainaware.ai/sse Auth: CHAINAWARE_API_KEY environment variable · x402 payment supported


Supported Networks

predictive_behaviour: ETH · BNB · BASE · HAQQ · SOLANA predictive_fraud: ETH · BNB · POLYGON · TON · BASE · TRON · HAQQ


Platform Type Map

Identify the platform type from its name. Use this to determine which wallet signals are most relevant for the message.

Platform Type Examples Primary wallet signals
DEX / Swap Uniswap, 1inch, Curve, Jupiter, Balancer, Orca Prob_Trade, Active Trader category, protocols count
Lending / Borrowing Aave, Compound, Morpho, Kamino, Venus Prob_Stake + Prob_Trade, DeFi Lender category, experience
Yield / Staking Lido, Rocket Pool, Pendle, Yearn, Beefy Prob_Stake, Yield Farmer category, risk profile
Bridge Stargate, Across, LayerZero, Hop, Wormhole Prob_Bridge, Bridge User category, multi-chain activity
NFT OpenSea, Blur, Magic Eden, Tensor Prob_NFT_Buy, NFT Collector category, experience
Derivatives / Perps dYdX, GMX, Hyperliquid, Drift Prob_Trade, risk profile (Aggressive+), experience
Portfolio / Analytics DeBank, Zerion, Zapper All categories, experience, protocol breadth
Launchpad / IDO Various experience, risk profile, Prob_Trade
Governance / DAO Snapshot, Tally, Compound Gov experience, governance category, protocols
Unknown / Custom Any other platform Use dominant intent signal + experience

Read the full file on GitHub · 327 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. 4d ago First seen · 327 lines · 265 tokens per session scan A dfb2fc142067

Subscribe to this mod's changes

chainaware-platform-greeter is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 24d ago), licensed MIT. It adds 265 tokens to every session and 3,417 once invoked, about $0.0013 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.