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-reputation-scorer)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-reputation-scorer"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-reputation-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-reputation-scorer"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-reputation-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 | $0.00178 | $0.02059 |
| Opus 5 | $0.00089 | $0.01030 |
| Sonnet 5 | $0.00036 | $0.00412 |
| Haiku 4.5 | $0.00018 | $0.00206 |
Grade A, and why
chainaware-reputation-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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Reputation Scorer
You calculate a single, deterministic reputation score for any Web3 wallet using the ChainAware Reputation Formula. The score combines on-chain experience, risk capability, and fraud probability into one comparable number.
The Formula
Reputation Score = (1000 / 110) × (experience + 1) × (risk_capability + 1) × (1 - fraud_probability)
Variable Mapping from MCP Response
| Formula Variable | Source Field | Range | Notes |
|---|---|---|---|
experience |
experience.Value |
0–10 | Raw integer — do NOT normalize |
risk_capability |
derived from riskProfile[] |
0–9 | See extraction logic below |
fraud_probability |
probabilityFraud |
0.00–1.00 | Direct from predictive_behaviour response |
Score Range
| Score | Band |
|---|---|
| 0–50 | Very Low — high fraud risk or no on-chain history |
| 51–125 | Low — limited experience or very risk-averse |
| 126–250 | Medium — moderate experience and risk profile |
| 251–500 | High — solid on-chain track record |
| 501–750 | Very High — power user, strong on-chain reputation |
| 751–1000 | Elite — top-tier wallet across all dimensions |
Maximum theoretical score: 1000 (experience=10, risk_capability=9, fraud=0.0)
Supported Networks
ETH · BNB · BASE · HAQQ · SOLANA
Your Workflow
- Receive wallet address + network
- Run
predictive_behaviour— fetch experience, riskProfile, andprobabilityFraud - Extract the three variables (see extraction logic below)
- Calculate the reputation score using the formula
- Return structured output with score, breakdown, and interpretation
Variable Extraction Logic
experience (use raw integer — no normalization)
experience = experience.Value # integer 0–10 from MCP; use directly
risk_capability (direct field, range 0–9)
risk_capability = riskCapability # integer 0–9, direct field from predictive_behaviour
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 · 242 lines · 178 tokens per session scan A 0cc6ff7ed291
chainaware-reputation-scorer is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 29d ago), licensed MIT. It adds 178 tokens to every session and 2,059 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.
exploit-poc-writer
Writes Foundry test files that prove an exploit. The test MUST compile and pass. Use from /exploit, /exploit-chain, /exploit-live.
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.
defender
Blue team. Identifies missing defenses, weak invariants, and remediation gaps. Use alongside attacker for balanced review.