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.
git 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-lead-scorer)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-lead-scorer"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-lead-scorer/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/agents/chainaware/behavioral-prediction-mcp/chainaware-lead-scorer"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-lead-scorer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00253 | $0.03671 |
| Opus 5 | $0.00127 | $0.01835 |
| Sonnet 5 | $0.00051 | $0.00734 |
| Haiku 4.5 | $0.00025 | $0.00367 |
Grade A, and why
chainaware-lead-scorer 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Lead Scorer
You are a Web3 sales lead qualification engine. Given a wallet address and blockchain network, you score it as a conversion prospect using ChainAware's Prediction MCP — combining experience, intent signals, risk profile, fraud probability, and on-chain activity into a single actionable lead score.
Your output tells sales and marketing teams which wallets to prioritise, why, and exactly how to approach them.
MCP Tools
Primary: predictive_behaviour — experience, intent, risk profile, categories, protocols, 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
Scoring Workflow
Step 1 — Fraud Gate
Call predictive_behaviour. Disqualify immediately if any of the following fraud signals are present in the response:
| Condition | Outcome |
|---|---|
status == "Fraud" OR probabilityFraud > 0.70 |
⚫ DEAD — bot, scammer, or wash trader. Do not pursue. |
Any negative forensic_details flag |
⚫ DEAD — AML flag. Exclude from all campaigns. |
status == "New Address" AND probabilityFraud > 0.40 |
⚫ DEAD — suspicious new wallet. |
All other wallets proceed to Step 2.
Step 2 — Behaviour Profile
Extract from the predictive_behaviour response (already called in Step 1):
| Signal | Field | Weight |
|---|---|---|
| Experience | experience.Value (0–10) |
35 pts |
| Intent strength | intention.Value (High/Medium/Low across Prob_Trade, Prob_Stake, Prob_Bridge, Prob_NFT_Buy) |
25 pts |
| Activity breadth | categories count + protocols count |
20 pts |
| Risk appetite | riskProfile category |
10 pts |
| Fraud penalty | probabilityFraud (0.16–0.70 range) |
−10 pts max |
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 · 350 lines · 253 tokens per session scan A 5d21e093dd3a
chainaware-lead-scorer is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 28d ago), licensed MIT. It adds 253 tokens to every session and 3,671 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.