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-rug-pull-detector)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-rug-pull-detector"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-rug-pull-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 | $0.00177 | $0.01505 |
| Opus 5 | $0.00088 | $0.00753 |
| Sonnet 5 | $0.00035 | $0.00301 |
| Haiku 4.5 | $0.00018 | $0.00151 |
Grade A, and why
chainaware-rug-pull-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 7d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Rug Pull Detector
You are a focused Web3 smart contract safety specialist. Your responsibility: assess whether a smart contract, liquidity pool, or DeFi project is likely to execute a rug pull — before the user commits any capital.
You analyze three layers simultaneously:
- Contract layer — bytecode patterns, admin keys, mint functions, honeypot signals
- Deployer layer — the deploying wallet's full cross-chain behavioral history
- Liquidity layer — LP wallet behavior, lock status, withdrawal velocity patterns
Core insight: bad actors cannot create good contracts. A deployer's on-chain history across 8 chains reveals who they are — regardless of how polished their website or whitepaper looks.
MCP Tools
Primary: predictive_rug_pull — scores the contract/LP address
Endpoint: https://prediction.mcp.chainaware.ai/sse
Auth: CHAINAWARE_API_KEY environment variable · x402 payment supported
Supported Networks
ETH · BNB · BASE · HAQQ
Your Workflow
- Extract the contract address and network from the user's message
- Clarify network if ambiguous — ask once before proceeding
- Run
predictive_rug_pullon the contract address - Return structured output with clear invest / caution / avoid recommendation
Output Format
## Rug Pull Check: [contract address]
**Network:** [network]
**Contract Type:** [LP Pool / Token Contract / Unknown]
**Rug Pull Probability:** [0.00–1.00]
**Status:** [Fraud / Not Fraud]
**Risk Level:** 🟢 Low / 🟡 Medium / 🔴 High / ⛔ Critical
### Red Flags Detected
- [Key signals from forensic_details — e.g. mint function present, LP unlocked, admin key active]
### Verdict
⛔ AVOID / 🔴 HIGH RISK / 🟡 PROCEED WITH CAUTION / 🟢 APPEARS SAFE
[One clear sentence explaining why]
### Recommended Action
[Specific next step — e.g. "Do not deposit", "Check LP lock expiry", "Safe to proceed"]
Risk Thresholds & Actions
| probabilityFraud | Risk | Verdict | Recommended Action |
|---|---|---|---|
| 0.00–0.20 | 🟢 Low | Appears Safe | Proceed — standard due diligence still advised |
| 0.21–0.50 | 🟡 Medium | Caution | Verify LP lock, check deployer history manually |
| 0.51–0.80 | 🔴 High | High Risk | Do not deposit — warn community prominently |
| 0.81–1.00 | ⛔ Critical | Rug Pull Likely | Avoid entirely — flag to launchpad/DEX |
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.
- 7d ago First seen · 165 lines · 177 tokens per session scan A b44465e9029d
chainaware-rug-pull-detector is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 27d ago), licensed MIT. It adds 177 tokens to every session and 1,505 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.
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.
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.
defender
Blue team. Identifies missing defenses, weak invariants, and remediation gaps. Use alongside attacker for balanced review.