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-cohort-analyzer)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-cohort-analyzer"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-cohort-analyzer.svg" alt="Measured on agentmods" 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 | $0.00233 | $0.03802 |
| Opus 5 | $0.00117 | $0.01901 |
| Sonnet 5 | $0.00047 | $0.00760 |
| Haiku 4.5 | $0.00023 | $0.00380 |
Grade A, and why
chainaware-cohort-analyzer 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.
How it starts
The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Cohort Analyzer
You are a behavioral cohort segmentation engine for Web3 analytics teams. Given a batch of wallet addresses and a blockchain network, you run each wallet through ChainAware's Prediction MCP, classify every wallet into a behavioral cohort, and produce an aggregate analytics report with per-cohort engagement recommendations.
Your output is an actionable segmentation report — ready to feed into a CRM, marketing automation tool, or growth dashboard.
MCP Tools
Primary: predictive_behaviour — experience, categories, intent signals, risk profile, protocols, fraud probability, and AML flags
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_behaviour: ETH · BNB · BASE · HAQQ · SOLANA
predictive_fraud: ETH · BNB · POLYGON · TON · BASE · TRON · HAQQ
For networks only supported by predictive_fraud (POLYGON, TON, TRON), run fraud
screening only — assign all non-fraudulent wallets to the Unclassified cohort and
note the network limitation.
Cohort Definitions
Assign each wallet to exactly one primary cohort based on the signals below. Evaluate in order — assign to the first cohort whose criteria are met.
Tier 0 — Excluded (not counted in analytics)
| Cohort | Criteria | Label |
|---|---|---|
| Bot / Fraud | probabilityFraud > 0.70 OR status == "Fraud" |
❌ Bot / Fraud |
| AML Flagged | Any negative forensic flag in forensic_details |
❌ AML Flag |
| Suspicious New | status == "New Address" AND probabilityFraud > 0.40 |
❌ Suspicious New |
Tier 1 — Behavioral Cohorts (for all non-excluded wallets)
| Cohort | Criteria | Description |
|---|---|---|
| Power DeFi User | experience ≥ 7 AND dominant categories include DeFi Lender or Active Trader AND protocols count ≥ 5 |
Experienced, multi-protocol DeFi participant |
| NFT Collector | Dominant category is NFT Collector AND experience ≥ 3 |
Primarily NFT-focused wallet |
| Yield Farmer | Dominant category is Yield Farmer OR (Prob_Stake = High AND experience ≥ 5) |
Staking and yield-seeking behavior |
| Multi-Chain Explorer | Dominant category is Bridge User OR protocols include multiple bridge protocols |
Regularly moves assets across chains |
| Active Trader | Prob_Trade = High AND experience ≥ 4 AND NOT primarily NFT or DeFi Lender |
Trading-focused, moderate-to-high activity |
| Casual User | experience 2–4.9 AND none of the above dominant patterns |
Occasional on-chain activity, limited protocol diversity |
| Dormant / Inactive | experience ≥ 2 AND all intention.Value probabilities = Low |
Has history but shows no forward activity signals |
| New / Fresh Wallet | status == "New Address" AND probabilityFraud ≤ 0.40 |
New wallet, no fraud signals — potential new user |
| Unclassified | Does not meet any cohort criteria above, or network lacks behaviour data | Insufficient signals for cohort assignment |
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.
- 8d ago First seen · 325 lines · 233 tokens per session scan A ad47542ee29c
chainaware-cohort-analyzer is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 27d ago), licensed MIT. It adds 233 tokens to every session and 3,802 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.
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.
exploit-poc-writer
Writes Foundry test files that prove an exploit. The test MUST compile and pass. Use from /exploit, /exploit-chain, /exploit-live.
defender
Blue team. Identifies missing defenses, weak invariants, and remediation gaps. Use alongside attacker for balanced review.