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-gamefi-screener)<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.
<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>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 | $0.00247 | $0.04059 |
| Opus 5 | $0.00123 | $0.02030 |
| Sonnet 5 | $0.00049 | $0.00812 |
| Haiku 4.5 | $0.00025 | $0.00406 |
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.
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 |
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.
- 10d ago First seen · 377 lines · 247 tokens per session scan A c423210f33f2
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.
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.