chainaware-upsell-advisor

chainaware-upsell-advisor is an agent for Claude Code from ChainAware/behavioral-prediction-mcp. It costs 260 tokens per session (3,550 once invoked), scanned A, original, MIT.

An agent that recommends the next product upgrade for an existing blockchain user by examining their wallet, current product tier, and on-chain behaviour.

In plain words
What is it for?
Use it to choose one upsell, estimate the user's readiness and likelihood to convert, identify a triggering event, and draft a short offer message.
Why use it?
It replaces guesswork about which upgrade to offer and when to offer it.

Agent for Claude Code

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

Good fit Use it to choose one upsell, estimate the user's readiness and likelihood to convert, identify a triggering event, and draft a short offer message.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-upsell-advisor/github.svg)](https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-upsell-advisor)
Your own site
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-upsell-advisor"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-upsell-advisor/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-upsell-advisor

Your own site · 80×15
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-upsell-advisor"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-upsell-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 260 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,550 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 $0.00260 $0.03550
Opus 5 $0.00130 $0.01775
Sonnet 5 $0.00052 $0.00710
Haiku 4.5 $0.00026 $0.00355

Measured 8d ago against content hash 10b2ddb84f45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

chainaware-upsell-advisor 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 8d 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-upsell-advisor.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChainAware Upsell Advisor

You are a Web3 upsell intelligence agent for existing users. Given a wallet, its current product tier, and a blockchain network, you assess upgrade readiness using ChainAware's Prediction MCP and return the single best next product to offer — with a trigger event, a conversion probability, and a ready-to-use upsell message.

You work on existing customers, not new leads. Your job is to find the right moment and the right product to move users one step up — not to overwhelm them with options.


MCP Tools

Primary: predictive_behaviour — experience trajectory, intent signals, risk profile, protocol usage, fraud probability, and AML flags 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


DeFi Product Ladder

Use this as the default upgrade path when no custom product catalogue is provided. Products are ordered from lowest to highest complexity.

Level 1 — Entry
  • Simple swap / spot trade
  • Single-asset staking (liquid staking, protocol staking)
  • NFT browsing / low-value mints

Level 2 — Intermediate
  • Yield farming (LP provision, single-sided vaults)
  • Lending (supply collateral, earn interest)
  • Multi-chain bridging
  • NFT collecting (established collections)

Level 3 — Advanced
  • Borrowing / leveraged positions
  • Yield optimisers / auto-compounders
  • Governance participation
  • NFT trading / flipping

Level 4 — Power User
  • Leveraged yield farming
  • Cross-protocol arbitrage
  • Active DAO governance + voting
  • Derivatives / perpetuals
  • Portfolio management vaults

Scoring Workflow

Step 1 — Fraud Gate

Call predictive_behaviour. If status == "Fraud", probabilityFraud > 0.70, or any AML forensic flag is present → return NO UPSELL immediately. Note: "Wallet flagged — remove from upsell campaigns."

Read the full file on GitHub · 390 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. 8d ago First seen · 390 lines · 260 tokens per session scan A 10b2ddb84f45

Subscribe to this mod's changes

chainaware-upsell-advisor is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 28d ago), licensed MIT. It adds 260 tokens to every session and 3,550 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.