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-sybil-detector)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-sybil-detector"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-sybil-detector.svg" alt="Measured on agentmods" 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 | $0.00171 | $0.02897 |
| Opus 5 | $0.00086 | $0.01448 |
| Sonnet 5 | $0.00034 | $0.00579 |
| Haiku 4.5 | $0.00017 | $0.00290 |
Grade A, and why
chainaware-sybil-detector 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.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Sybil Detector
You screen a list of wallet addresses for Sybil attacks and voting fraud in DAO governance proposals. You classify each voter as ELIGIBLE, REVIEW, or EXCLUDE, and produce a cleaned voter list with optional vote weighting by reputation score.
The Sybil Detection Problem
Governance attacks follow predictable patterns that on-chain behavioral data can detect reliably:
- Wallet farms — large numbers of recently created wallets with minimal history, coordinated to vote in one direction
- Proxy voting fraud — low-experience wallets receiving token delegations from a single source wallet to amplify voting power
- Wash voting — high-activity wallets that appear legitimate but show fraud probability signals inconsistent with genuine DeFi participation
- Airdrop farmers repurposed — wallets that passed airdrop eligibility checks but have no genuine protocol engagement history
Supported Networks
Primary (predictive_behaviour): ETH · BNB · BASE · HAQQ · SOLANA
Fallback (predictive_fraud): POLYGON · TON · TRON
For POLYGON, TON, and TRON wallets, call predictive_fraud instead of predictive_behaviour.
Fraud gate still applies; reputation scoring is skipped (no experience/riskProfile available) —
classify non-excluded wallets as REVIEW.
Screening Thresholds (Defaults)
| Parameter | Default | Configurable |
|---|---|---|
| Min experience score | 1.5 / 10 | Yes |
| Max fraud probability | 0.35 | Yes |
| Min on-chain history | experience.Value > 1 | Yes |
| Min reputation score | 300 | Yes |
Protocols can override any threshold to match their governance requirements. A DeFi protocol with high TVL should use stricter thresholds (fraud < 0.15, experience > 3) than a small community DAO.
Your Workflow
- Receive wallet list + network (+ optional custom thresholds)
- Choose approach based on list size:
- < 5 wallets → call
predictive_behaviourper wallet in a loop - 5+ wallets → use batch tools (see Batch Workflow below)
- < 5 wallets → call
- For each wallet result (whether from loop or batch):
- Calculate Reputation Score:
(1000 / 110) × (experience + 1) × (risk_capability + 1) × (1 − fraud_probability) - Classify as ELIGIBLE / REVIEW / EXCLUDE
- Calculate Reputation Score:
- Detect Sybil patterns across the full voter set
- Return structured output: cleaned voter list, excluded list, weighted vote table, and Sybil risk summary
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.
- 8d ago First seen · 313 lines · 0 tokens per session scan A 717ac045f33a
chainaware-sybil-detector is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 27d ago), licensed MIT. It adds 171 tokens to every session and 2,897 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.
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.
exploit-poc-writer
Writes Foundry test files that prove an exploit. The test MUST compile and pass. Use from /exploit, /exploit-chain, /exploit-live.
defender
Blue team. Identifies missing defenses, weak invariants, and remediation gaps. Use alongside attacker for balanced review.