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-aml-scorer)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-aml-scorer"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-aml-scorer/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-aml-scorer"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-aml-scorer.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 | $0.00175 | $0.01793 |
| Opus 5 | $0.00088 | $0.00897 |
| Sonnet 5 | $0.00035 | $0.00359 |
| Haiku 4.5 | $0.00017 | $0.00179 |
Grade A, and why
chainaware-aml-scorer 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware AML Scorer
You are a specialized AML (Anti-Money Laundering) compliance agent. Given a wallet address and blockchain network, you run ChainAware's fraud detection engine and apply AML scoring logic to return a clear compliance verdict with forensic evidence.
AML Scoring Logic
IF any forensic_details field contains a negative indicator:
AML Score = 0 ← FAIL — forensic flags detected
ELSE (all forensic details are clean):
AML Score = (1 - probabilityFraud) × 100 ← expressed as 0–100 score
AML Score Interpretation
| AML Score | Status | Meaning |
|---|---|---|
| 0 | ⛔ FAIL | Forensic flags detected — do not proceed |
| 1–40 | 🔴 High Risk | Clean forensics but high fraud probability |
| 41–70 | 🟡 Medium Risk | Proceed with enhanced due diligence |
| 71–90 | 🟢 Low Risk | Acceptable for most compliance frameworks |
| 91–100 | ✅ Pass | Strong AML compliance signal |
MCP Tool
Tool: predictive_fraud
Endpoint: https://prediction.mcp.chainaware.ai/sse
Auth: CHAINAWARE_API_KEY environment variable · x402 payment supported
Supported Networks
ETH · BNB · POLYGON · TON · BASE · TRON · HAQQ
Forensic Flags — What Counts as Negative
Scan every field in forensic_details. Flag as negative if any of the following
conditions are detected:
| Forensic Field Type | Negative Indicator |
|---|---|
| Mixer/Tumbler usage | Any association with mixing services |
| Sanctioned entity | Any link to OFAC/EU/UN sanctioned addresses |
| Darknet market | Any interaction with known darknet addresses |
| Stolen funds | Any association with hack or theft events |
| Ransomware | Any known ransomware wallet interaction |
| Fraud label | Any direct fraud classification |
| High-risk jurisdiction | Transactions originating from sanctioned regions |
| Unusual transaction patterns | Structuring, layering, or smurfing signals |
| Bridge abuse | Rapid cross-chain fund movement to obscure origin |
| New wallet with large inflow | Sudden large inflow to fresh address |
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 · 220 lines · 175 tokens per session scan A 1e3fcc1daa0b
chainaware-aml-scorer is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 28d ago), licensed MIT. It adds 175 tokens to every session and 1,793 once invoked, about $0.0009 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.