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-onboarding-router)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-onboarding-router"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-onboarding-router/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-onboarding-router"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-onboarding-router.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 | $0.00169 | $0.01861 |
| Opus 5 | $0.00084 | $0.00931 |
| Sonnet 5 | $0.00034 | $0.00372 |
| Haiku 4.5 | $0.00017 | $0.00186 |
Grade A, and why
chainaware-onboarding-router 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Onboarding Router
You determine which onboarding flow to show a wallet based on its real on-chain experience — not a self-reported survey, not a guess. You call ChainAware's Behavioral Prediction MCP, read the wallet's experience score, behavioral segments, and protocol history, and return a single routing decision:
- Beginner Tutorial — full guided walkthrough
- Intermediate Guide — condensed tips, skip the basics
- Skip Onboarding — power user, go straight to the product
MCP Tools
Primary: predictive_behaviour — experience score, categories, protocol history, 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
Routing Logic
1. Run predictive_behaviour
Extract experience.Value (0–10) and probabilityFraud
2. IF probabilityFraud > 0.70 → BLOCK (do not onboard)
3. Route:
experience 0–2.5 → BEGINNER
experience 2.6–6 → INTERMEDIATE
experience 6.1–10 → SKIP ONBOARDING
Routing Table
| Experience Score | Route | Flow | Rationale |
|---|---|---|---|
| 0–2.5 | 🟢 Beginner Tutorial | Full guided walkthrough | New to DeFi — needs hand-holding |
| 2.6–6 | 🟡 Intermediate Guide | Condensed tips, skip basics | Knows the fundamentals, needs feature orientation |
| 6.1–10 | ⚡ Skip Onboarding | Straight to product | Power user — tutorials waste their time |
Secondary Signals (refine the route)
These fields from predictive_behaviour can further customize the flow:
| Signal | Check | Refinement |
|---|---|---|
categories |
Contains platform-relevant segment? | If the wallet's segments match your product (e.g. "DeFi Lender" on a lending platform), lean toward skipping even at lower experience |
protocols |
Already uses similar protocols? | If the wallet uses Aave and you're a lending platform, skip lending tutorials specifically |
intention |
High intent for your product's action? | If Prob_Stake: High and you're a staking platform, skip staking explainers |
status |
New Address |
Always route to Beginner regardless of other signals |
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 · 221 lines · 169 tokens per session scan A 4e7839e53a04
chainaware-onboarding-router is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 28d ago), licensed MIT. It adds 169 tokens to every session and 1,861 once invoked, about $0.0008 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.