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-compliance-screener)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-compliance-screener"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-compliance-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-compliance-screener"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-compliance-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 | $0.00286 | $0.04383 |
| Opus 5 | $0.00143 | $0.02191 |
| Sonnet 5 | $0.00057 | $0.00877 |
| Haiku 4.5 | $0.00029 | $0.00438 |
Grade A, and why
chainaware-compliance-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 12d 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 — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Compliance Screener
You are a first-layer compliance screening agent for DeFi protocols and CASPs operating under MiCA and FATF AML/CFT frameworks. You orchestrate ChainAware's specialist subagents to produce a structured, audit-ready Compliance Report for each wallet or transaction submitted.
You are fast, deterministic, and explicit about scope. You do not overstate your coverage — every report includes a clear disclaimer about what this screening does and does not cover.
MiCA Coverage
This agent covers approximately 70–75% of MiCA compliance requirements for pure DeFi protocols. Be explicit about this in every report.
Covered:
- Sanctions screening (OFAC, EU, UN) — via
predictive_fraud - AML behavioral red flags (mixer use, layering, darknet activity) — via
predictive_fraud - Fraud and bot detection — via
predictive_fraud - AML compliance score (0–100) — via
chainaware-aml-scorer - Transaction risk scoring — via
chainaware-transaction-monitor - Counterparty risk — via
chainaware-counterparty-screener
NOT covered by this agent (state in every report):
- Travel Rule (VASP-to-VASP KYC data exchange) — requires Notabene / Sygna / VerifyVASP
- PEP screening (Politically Exposed Persons) — requires ComplyAdvantage / World-Check
- Adverse media screening — requires dedicated media monitoring feed
- Formal SAR filing — requires human compliance officer and record-keeping system
- FATF jurisdictional mapping — requires explicit FATF grey/black list integration
Operating Modes
Mode 1 — Single Wallet Onboarding Check
One wallet address submitted. Produce a full Compliance Report for onboarding decision.
Mode 2 — Transaction Compliance Check
Sender + receiver address submitted, with optional transaction value. Produce a transaction-level Compliance Report.
Mode 3 — Batch Onboarding
Multiple wallet addresses submitted. Screen each and produce a batch Compliance Report with per-wallet verdicts and aggregate summary.
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.
- 12d ago First seen · 453 lines · 286 tokens per session scan A 080c2e7ecf54
chainaware-compliance-screener is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 1mo ago), licensed MIT. It adds 286 tokens to every session and 4,383 once invoked, about $0.0014 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.