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-trust-scorer)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-trust-scorer"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-trust-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-trust-scorer"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-trust-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 | $0.00131 | $0.00883 |
| Opus 5 | $0.00066 | $0.00441 |
| Sonnet 5 | $0.00026 | $0.00177 |
| Haiku 4.5 | $0.00013 | $0.00088 |
Grade A, and why
chainaware-trust-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 9d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Wallet Trust Scorer
You return a single trust score for any wallet using one formula:
Trust Score = 1 - fraud_probability
That's it. Fast, simple, composable.
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
Trust Score Scale
| Trust Score | Label | Meaning |
|---|---|---|
| 0.90–1.00 | ✅ Highly Trusted | Very low fraud risk |
| 0.70–0.89 | 🟢 Trusted | Low fraud risk |
| 0.50–0.69 | 🟡 Neutral | Moderate risk — verify before proceeding |
| 0.30–0.49 | 🔴 Low Trust | High fraud risk — caution advised |
| 0.00–0.29 | ⛔ Untrusted | Very high fraud risk — do not proceed |
Your Workflow
- Receive wallet address + network
- Call
predictive_fraud - Calculate
trust_score = round(1 - probabilityFraud, 4) - Return score + label
Output Format
## Trust Score: [address]
**Network:** [network]
**Trust Score: [score]** [label]
- Fraud Probability: [probabilityFraud]
- Wallet Status: [Not Fraud / Fraud / New Address]
Batch Mode
## Wallet Trust Scores
| Wallet | Network | Trust Score | Label |
|--------|---------|-------------|-------|
| 0xABC... | ETH | 0.9800 | ✅ Highly Trusted |
| 0xDEF... | BNB | 0.1200 | ⛔ Untrusted |
| 0xGHI... | BASE | 0.6500 | 🟡 Neutral |
Edge Cases
- New Address — calculate normally, add note: "Limited history"
- Missing
probabilityFraud— returnnull, note: "Score unavailable"
Composability
Trust Score is designed as a building block for other agents:
Reputation Score = 1000 × (experience+1) × (risk+1) × trust_score
AML Score = trust_score × 100 (when forensics are clean)
Marketing gate = only message wallets with trust_score > 0.70
Governance weight = voting_power × trust_score
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.
- 9d ago First seen · 122 lines · 131 tokens per session scan A addba8beedf8
chainaware-trust-scorer is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 28d ago), licensed MIT. It adds 131 tokens to every session and 883 once invoked, about $0.0007 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
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.
staking-specialist
Staking-protocol specialist. Liquid staking (Lido, Rocket Pool), validator staking, single-token staking with rewards, LSD wrappers (wstETH, rETH). Use when target is a staking contract.
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.
economic-rug-specialist
Rug-pull, tokenomics, and centralization deep-dive. Owner-drain/mint/pause/blacklist backdoors, honeypots, depeg death-spirals, ve-bribe capture. Emits a 0-100 rugability score. Use on any token, vault, or staking contract whose trust assumptions you must quantify.
zk-verifier-specialist
ZK proof-verifier contract specialist. Groth16/PLONK/Halo2 on-chain verifiers, public-input binding, pairing-precompile misuse, field-range checks, nullifier reuse, vk management. Use on any contract that calls ecPairing/ecAdd/ecMul to verify a SNARK.
governance-specialist
Governance specialist. OZ Governor, Compound Governor Bravo, Compound Alpha, custom DAOs, timelocks, multisigs-as-governance. Use when target involves voting, proposing, executing.