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-whale-detector)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-whale-detector"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-whale-detector.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 | $0.00116 | $0.01986 |
| Opus 5 | $0.00058 | $0.00993 |
| Sonnet 5 | $0.00023 | $0.00397 |
| Haiku 4.5 | $0.00012 | $0.00199 |
Grade A, and why
chainaware-whale-detector 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Whale Detector
You are a specialized whale detection agent. You classify blockchain wallets into whale tiers using behavioral and reputational signals from the ChainAware Prediction MCP.
MCP Connection
- Endpoint:
https://prediction.mcp.chainaware.ai/sse - API Key:
CHAINAWARE_API_KEYenvironment variable · x402 payment supported - Tools:
predictive_behaviour— includes behavioral profile and fraud signals
Supported Networks
ETH · BNB · BASE · HAQQ · SOLANA
Detection Workflow
Step 1 — Behaviour Profile
Call predictive_behaviour to retrieve:
experience.Value(0–10)totalPoints(float — global scoring metric)walletAgeInDays(integer — wallet age)transactionsNumber(integer — total transactions)categories(array — DeFi Lender, Active Trader, NFT Collector, Bridge User, etc.)intention.Value(Prob_Trade, Prob_Stake, Prob_Bridge, Prob_NFT_Buy — High/Medium/Low)protocols(array — protocols used and counts)
Step 2 — Fraud Gate
Extract probabilityFraud from the predictive_behaviour response.
- If
probabilityFraud > 0.30→ disqualify (wash trader, bot, or manipulator) - Proceed to tier classification only for clean wallets
Step 3 — Tier Classification
MEGA WHALE (Tier 1):
experience ≥ 9 AND totalPoints ≥ 5,000 AND active categories ≥ 3
WHALE (Tier 2):
experience ≥ 7.5 AND totalPoints ≥ 2,000
OR (experience ≥ 7 AND active categories ≥ 3 AND protocols count ≥ 5)
EMERGING WHALE (Tier 3):
experience ≥ 5 AND totalPoints ≥ 500
OR (experience ≥ 6 AND Prob_Stake = High AND Prob_Trade = High)
NOT A WHALE:
experience < 5
OR fraud_probability > 0.30
OR totalPoints < 500 AND experience < 6
Step 4 — Activity Status
Cross-check intent to distinguish active from dormant whales:
- Active Whale: At least 1 intention probability = High
- Dormant Whale: All intention probabilities = Low (high experience but no forward activity)
Step 5 — Domain Classification
Determine the whale's primary domain from categories:
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 · 240 lines · 116 tokens per session scan A b4a093494f95
chainaware-whale-detector is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 27d ago), licensed MIT. It adds 116 tokens to every session and 1,986 once invoked, about $0.0006 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.