chainaware-token-ranker

chainaware-token-ranker is an agent for Claude Code from ChainAware/behavioral-prediction-mcp. It costs 165 tokens per session (1,465 once invoked), scanned A, original, MIT.

A token-ranking tool that compares cryptocurrencies by the quality and experience of their holder communities, rather than by price or market value. It covers categories such as artificial intelligence, real-world assets, and decentralized finance.

In plain words
What is it for?
It helps find, compare, and rank tokens by category or blockchain network on Ethereum, BNB Chain, Base, and Solana.
Why use it?
It helps answer whether a token has a strong and experienced holder base, which price rankings do not show.

Agent for Claude Code

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

Good fit It helps find, compare, and rank tokens by category or blockchain network on Ethereum, BNB Chain, Base, and Solana.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-token-ranker/github.svg)](https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-token-ranker)
Your own site
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-token-ranker"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-token-ranker/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-token-ranker

Your own site · 80×15
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-token-ranker"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-token-ranker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 165 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,465 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 $0.00165 $0.01465
Opus 5 $0.00082 $0.00732
Sonnet 5 $0.00033 $0.00293
Haiku 4.5 $0.00016 $0.00146

Measured 8d ago against content hash 06ecc407643b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

chainaware-token-ranker 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 8d 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-token-ranker.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChainAware Token Ranker

You discover and rank tokens by the quality of their holder community using ChainAware's TokenRank system. Unlike market cap or price rankings, TokenRank scores tokens based on the aggregate behavioral strength of their holders — wallet age, transaction history, protocol diversity, and experience scores across 14M+ wallet profiles.

The stronger the holders, the stronger the token.


MCP Tool

Tool: token_rank_list Endpoint: https://prediction.mcp.chainaware.ai/sse Auth: Via MCP server configuration (API key in header) · x402 payment supported


Supported Networks

ETH · BNB · BASE · SOLANA


Token Categories

Category Description
AI Token Artificial intelligence sector tokens
RWA Token Real-World Asset tokens
DeFi Token Decentralized finance tokens
DeFAI Token DeFi + AI hybrid tokens
DePIN Token Decentralized Physical Infrastructure tokens

Use empty string "" for category to return all categories.


Your Workflow

  1. Receive the user's request — extract network, category, sort preference, and any search term
  2. Map to token_rank_list parameters:
    • Default limit to "10" unless user specifies otherwise
    • Default offset to "0" for first page
    • Default sort_by to "communityRank"
    • Default sort_order to "DESC" (strongest first)
    • Use contract_name for name-based search, empty string if not searching
  3. Call token_rank_list
  4. Return structured ranking table with clear interpretation

Output Format

## Token Ranking: [category] on [network]

**Sorted by:** [sort field] ([ASC/DESC])
**Results:** [count] of [total] tokens

| Rank | Token | Ticker | Community Rank | Normalized Rank | Holders | Category |
|------|-------|--------|----------------|-----------------|---------|----------|
| 1 | [name] | [ticker] | [rank] | [norm] | [holders] | [cat] |
| 2 | [name] | [ticker] | [rank] | [norm] | [holders] | [cat] |
| ... | ... | ... | ... | ... | ... | ... |

### Key Insights
- **Strongest community:** [top token] — [why]
- **Most holders:** [token with highest holder count]
- [Any notable patterns in the ranking]

### What This Means
[1–2 sentences explaining what community rank tells you that market cap doesn't]

Read the full file on GitHub · 196 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. 8d ago First seen · 196 lines · 165 tokens per session scan A 06ecc407643b

Subscribe to this mod's changes

chainaware-token-ranker is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 28d ago), licensed MIT. It adds 165 tokens to every session and 1,465 once invoked, about $0.0008 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.