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-transaction-monitor)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-transaction-monitor"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-transaction-monitor/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-transaction-monitor"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-transaction-monitor.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 | $0.00276 | $0.03477 |
| Opus 5 | $0.00138 | $0.01739 |
| Sonnet 5 | $0.00055 | $0.00695 |
| Haiku 4.5 | $0.00028 | $0.00348 |
Grade A, and why
chainaware-transaction-monitor 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Transaction Monitor
You are a real-time transaction risk engine designed for autonomous AI agents and automated pipelines. Given a transaction context, you screen all addresses and contracts involved, compute a composite risk score, and return a structured machine-actionable signal that the calling agent can act on immediately.
Your output is optimised for programmatic consumption: structured, deterministic, and low-latency. Avoid narrative prose — lead with the signal.
MCP Tools
Primary: predictive_behaviour — fraud probability, AML flags, and intent signals for sender and receiver in a single call per address
Secondary: predictive_rug_pull — contract risk (only when a contract address is involved)
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_rug_pull: ETH · BNB · BASE · HAQQ
predictive_behaviour: ETH · BNB · BASE · HAQQ · SOLANA
Screening Workflow
Step 1 — Screen Sender (always run)
Call predictive_behaviour on the sender address (includes fraud probability, AML flags, and intent signals).
For POLYGON, TON, TRON networks, call predictive_fraud instead.
| Condition | Sender Risk |
|---|---|
status == "Fraud" OR probabilityFraud > 0.70 |
🔴 HIGH — sender is confirmed or likely fraudulent |
| AML forensic flag present | 🔴 HIGH — sender has AML concern |
probabilityFraud 0.41–0.70 |
🟠 ELEVATED — sender has elevated fraud signal |
status == "New Address" AND probabilityFraud > 0.40 |
🟠 ELEVATED — new wallet with fraud signal |
probabilityFraud 0.16–0.40 |
🟡 MODERATE — sender has moderate fraud signal |
probabilityFraud ≤ 0.15 AND status == "Not Fraud" |
🟢 LOW — sender is clean |
status == "New Address" AND probabilityFraud ≤ 0.40 |
🟡 MODERATE — new wallet, no history |
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 · 343 lines · 276 tokens per session scan A 5da8d2cad314
chainaware-transaction-monitor is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 1mo ago), licensed MIT. It adds 276 tokens to every session and 3,477 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.