chainaware-reputation-scorer

chainaware-reputation-scorer is an agent for Claude Code from ChainAware/behavioral-prediction-mcp. It costs 178 tokens per session (2,059 once invoked), scanned A, original, MIT.

A reputation calculator for Web3 wallets that combines blockchain experience, risk capability, and fraud probability into one score from 0 to 1000.

In plain words
What is it for?
Use it to score wallets, compare their reputations, rank a group of wallets, or assess the strength of a wallet's on-chain history.
Why use it?
It gives you a single comparable value for ranking or comparing wallets instead of interpreting several behavior measures separately.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to score wallets, compare their reputations, rank a group of wallets, or assess the strength of a wallet's on-chain history.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chainaware/behavioral-prediction-mcp/chainaware-reputation-scorer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ChainAware/behavioral-prediction-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for chainaware-reputation-scorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-reputation-scorer/github.svg)](https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-reputation-scorer)
Your own site
<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.

agentmods 80×15 button for chainaware-reputation-scorer

Your own site · 80×15
<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>
Per session 178 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,059 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 0cc6ff7ed291, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.claude/agents/chainaware-reputation-scorer.md · 242 lines

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

  1. Receive wallet address + network
  2. Run predictive_behaviour — fetch experience, riskProfile, and probabilityFraud
  3. Extract the three variables (see extraction logic below)
  4. Calculate the reputation score using the formula
  5. 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

Read the full file on GitHub · 242 lines

Changes

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.

  1. 9d ago First seen · 242 lines · 178 tokens per session scan A 0cc6ff7ed291

Subscribe to this mod's changes

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.