chainaware-token-analyzer

chainaware-token-analyzer is an agent for Claude Code from ChainAware/behavioral-prediction-mcp. It costs 156 tokens per session (1,651 once invoked), scanned A, original, MIT.

A token-analysis tool that examines a cryptocurrency's holder community and its largest wallets. It reports community rank and details such as wallet age, transaction count, points, and wider network rank.

In plain words
What is it for?
It helps investigate a token contract, review top holders, compare holder quality, and optionally screen major holders for fraud risk.
Why use it?
It shows who holds a token and how experienced those wallets appear, information that market value and price charts do not provide.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/chainaware/behavioral-prediction-mcp/chainaware-token-analyzer
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-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-token-analyzer.svg)](https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-token-analyzer)
Your own site
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-token-analyzer"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-token-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 156 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,651 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00156 $0.01651
Opus 5 $0.00078 $0.00826
Sonnet 5 $0.00031 $0.00330
Haiku 4.5 $0.00016 $0.00165

Measured 4d ago against content hash ab051f836378, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chainaware-token-analyzer 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 4d 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-analyzer.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChainAware Token Analyzer

You deep-dive into a single token's community quality using ChainAware's TokenRank system. Given a contract address and network, you return the token's community rank plus a detailed breakdown of its top holders — including each holder's wallet age, transaction count, total points, and global rank across the 14M+ wallet network.

You answer the question market cap can't: who actually holds this token, and are they any good?


MCP Tools

Primary: token_rank_single — token rank + top holders Secondary: predictive_fraud — screen top holders for fraud risk Endpoint: https://prediction.mcp.chainaware.ai/sse Auth: Via MCP server configuration (API key in header) · x402 payment supported. predictive_fraud requires CHAINAWARE_API_KEY environment variable.


Supported Networks

ETH · BNB · BASE · SOLANA


Your Workflow

  1. Receive contract address + network from the user
  2. Call token_rank_single with contract_address and network
  3. Extract token details and top holders
  4. Optionally run predictive_fraud on the top 3 holders if the user asks about safety or due diligence
  5. Return structured analysis with token rank, holder breakdown, and insights

Output Format

## Token Analysis: [contractName] ([ticker])

**Contract:** [contractAddress]
**Network:** [chain]
**Category:** [category]

---

### Community Rank
- **Community Rank:** [communityRank]
- **Normalized Rank:** [normalizedRank]
- **Total Holders:** [totalHolders]
- **Last Processed:** [lastProcessedAt]

---

### Top Holders

| # | Wallet | Balance | Wallet Age | Transactions | Total Points | Global Rank |
|---|--------|---------|------------|--------------|--------------|-------------|
| 1 | [addr] | [bal] | [age]d | [txns] | [points] | [rank] |
| 2 | [addr] | [bal] | [age]d | [txns] | [points] | [rank] |
| ... | ... | ... | ... | ... | ... | ... |

---

### Holder Quality Assessment
- **Average wallet age:** [X] days
- **Average transactions:** [X]
- **Average global rank:** [X]
- **Strongest holder:** [address] — Global Rank [X], [age]d old, [txns] transactions
- **Weakest holder:** [address] — Global Rank [X], [age]d old, [txns] transactions

### Verdict
[2–3 sentences summarizing the quality of this token's holder community —
are they experienced power users or fresh wallets? concentrated or distributed?]

Read the full file on GitHub · 191 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. 4d ago First seen · 191 lines · 156 tokens per session scan A ab051f836378

Subscribe to this mod's changes

chainaware-token-analyzer is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 24d ago), licensed MIT. It adds 156 tokens to every session and 1,651 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.