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 agentmods add agents/chainaware/behavioral-prediction-mcp/chainaware-platform-greetergit clone --depth 1 https://github.com/ChainAware/behavioral-prediction-mcpWrote 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/agents/chainaware/behavioral-prediction-mcp/chainaware-platform-greeter)<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>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 | $0.00265 | $0.03417 |
| Opus 5 | $0.00133 | $0.01708 |
| Sonnet 5 | $0.00053 | $0.00683 |
| Haiku 4.5 | $0.00026 | $0.00342 |
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.
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 |
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.
- 4d ago First seen · 327 lines · 265 tokens per session scan A dfb2fc142067
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.
Other agents, from other repositories
invariant-writer
Identifies protocol invariants from contract code and intent, generates Foundry invariant tests with handlers. Use from /invariant and /audit-deep.
exploit-poc-writer
Writes Foundry test files that prove an exploit. The test MUST compile and pass. Use from /exploit, /exploit-chain, /exploit-live.
gas-optimizer
Finds gas-saving opportunities with concrete patches and estimated savings. Use from /gas.
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.
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.
defender
Blue team. Identifies missing defenses, weak invariants, and remediation gaps. Use alongside attacker for balanced review.