chainaware-onboarding-router

chainaware-onboarding-router is an agent for Claude Code from ChainAware/behavioral-prediction-mcp. It costs 169 tokens per session (1,861 once invoked), scanned A, original, MIT.

An onboarding router that chooses a starting experience for a Web3 wallet based on its blockchain history. It sends wallets to a beginner tutorial, an intermediate guide, or directly to the product, and can block wallets with high fraud probability.

In plain words
What is it for?
Use it to decide whether a wallet needs a full walkthrough, shorter guidance, no onboarding, or no access because of fraud risk.
Why use it?
It avoids giving every user the same introduction when some need basics and others already understand blockchain products.

Agent for Claude Code

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

Good fit Use it to decide whether a wallet needs a full walkthrough, shorter guidance, no onboarding, or no access because of fraud risk.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chainaware/behavioral-prediction-mcp/chainaware-onboarding-router
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-onboarding-router

README.md
[![agentmods](https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-onboarding-router/github.svg)](https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-onboarding-router)
Your own site
<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.

agentmods 80×15 button for chainaware-onboarding-router

Your own site · 80×15
<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>
Per session 169 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,861 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 $0.00169 $0.01861
Opus 5 $0.00084 $0.00931
Sonnet 5 $0.00034 $0.00372
Haiku 4.5 $0.00017 $0.00186

Measured 9d ago against content hash 4e7839e53a04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.claude/agents/chainaware-onboarding-router.md · 221 lines

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

Read the full file on GitHub · 221 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. 9d ago First seen · 221 lines · 169 tokens per session scan A 4e7839e53a04

Subscribe to this mod's changes

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.