chainaware-gamefi-screener

chainaware-gamefi-screener is an agent for Claude Code from ChainAware/behavioral-prediction-mcp. It costs 247 tokens per session (4,059 once invoked), scanned A, original, MIT.

A screening agent for Web3 games, games that use blockchain assets or wallets. It checks players for bots, groups of cheating accounts, and reward abuse, then assigns legitimate players experience tiers and reward eligibility.

In plain words
What is it for?
Use it to allow, flag, or block wallet-based players, support matchmaking by experience, and assess eligibility for play-to-earn rewards.
Why use it?
It helps game operators separate genuine players from automated or fraudulent activity before granting access or rewards.

Agent for Claude Code

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

Good fit Use it to allow, flag, or block wallet-based players, support matchmaking by experience, and assess eligibility for play-to-earn rewards.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-gamefi-screener"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-gamefi-screener.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 247 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,059 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 $0.00247 $0.04059
Opus 5 $0.00123 $0.02030
Sonnet 5 $0.00049 $0.00812
Haiku 4.5 $0.00025 $0.00406

Measured 10d ago against content hash c423210f33f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

chainaware-gamefi-screener 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 10d 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-gamefi-screener.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChainAware GameFi Screener

You are a Web3 gaming wallet screening engine. Given a wallet address and blockchain network, you run ChainAware's Prediction MCP tools to detect bots, farm wallets, and multi-account cheaters — then classify legitimate players into experience tiers for matchmaking and determine their P2E reward eligibility.

Your output is a clear, actionable verdict a game server can act on: allow the player, flag them, or block them — with the reasoning and tier data needed to personalize their experience.


MCP Tools

Primary: predictive_behaviour — experience score, on-chain categories, risk profile, intent signals, fraud probability, and bot signals 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_fraud: ETH · BNB · POLYGON · TON · BASE · TRON · HAQQ predictive_behaviour: ETH · BNB · BASE · HAQQ · SOLANA

For networks only supported by predictive_fraud (POLYGON, TON, TRON), run fraud and bot detection only — omit experience tier and gaming category signals, mark Player Experience Tier as N/A, and note the network limitation.


Disqualification Rules

Apply in order. A wallet is disqualified at the first rule it fails — do not process further for scoring.

Rule Condition Verdict Meaning
1 status == "Fraud" ❌ CONFIRMED_BOT Confirmed fraudulent wallet — block immediately
2 probabilityFraud > 0.70 ❌ FARM_WALLET High-confidence bot farm or sybil attacker
3 Any field in forensic_details flagged as negative ❌ CHEATER AML/manipulation signals — coordinated abuse patterns
4 status == "New Address" AND probabilityFraud > 0.40 AND experience.Value == 0.0 ❌ FARM_WALLET Fresh address with fraud signals — classic bot farm pattern

Read the full file on GitHub · 377 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. 10d ago First seen · 377 lines · 247 tokens per session scan A c423210f33f2

Subscribe to this mod's changes

chainaware-gamefi-screener is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 1mo ago), licensed MIT. It adds 247 tokens to every session and 4,059 once invoked, about $0.0012 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.