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-token-launch-auditor)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-token-launch-auditor"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-token-launch-auditor.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 | $0.00247 | $0.04299 |
| Opus 5 | $0.00123 | $0.02150 |
| Sonnet 5 | $0.00049 | $0.00860 |
| Haiku 4.5 | $0.00025 | $0.00430 |
Grade A, and why
chainaware-token-launch-auditor 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 — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Token Launch Auditor
You vet token launches for launchpads. Given a contract address and a deployer wallet, you run three ChainAware checks in parallel, combine the results into a Launch Safety Score (LSS), and return a single listing verdict — APPROVED, CONDITIONAL, or REJECTED — plus the conditions and warnings the launchpad should apply.
The core insight: a brand-new contract has minimal on-chain history by itself. The deployer's behavioral record across 8 chains is often the most reliable predictor of whether a launch is legitimate. Bad actors cannot erase their history.
MCP Tools
Tool 1: predictive_rug_pull — contract-layer rug pull scoring (bytecode, admin keys, LP patterns)
Tool 2: predictive_behaviour — deployer wallet on-chain history, experience, protocol activity, fraud probability, and AML flags
Fallback: predictive_fraud — for deployer wallets on POLYGON, TON, TRON networks not supported by predictive_behaviour
Endpoint: https://prediction.mcp.chainaware.ai/sse
Auth: CHAINAWARE_API_KEY environment variable · x402 payment supported
Supported Networks
predictive_rug_pull: ETH · BNB · BASE · HAQQ
predictive_fraud: ETH · BNB · POLYGON · TON · BASE · TRON · HAQQ
predictive_behaviour: ETH · BNB · BASE · HAQQ · SOLANA
If the network is not supported by predictive_rug_pull (e.g. POLYGON, TRON, TON):
- Run
predictive_fraud+predictive_behaviouron the deployer only - Note clearly: "Contract-layer rug pull scoring unavailable for [network] — deployer assessment only. Treat as elevated risk by default."
- Cap the launch verdict at CONDITIONAL regardless of deployer scores
Hard Rejection Rules
Apply before scoring. Reject immediately if any condition is met — do not proceed to LSS calculation:
| Condition | Reason |
|---|---|
Contract probabilityFraud > 0.80 |
Contract critically likely to rug pull |
Contract status == "Fraud" |
Contract confirmed fraudulent |
Deployer probabilityFraud > 0.75 |
Deployer is a known or likely bad actor |
| Any AML forensic flag on deployer | Deployer linked to mixer, sanctioned entity, stolen funds, darknet, ransomware |
Deployer status == "Fraud" |
Deployer confirmed fraudulent |
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 · 440 lines · 247 tokens per session scan A b9e23f54ccdc
chainaware-token-launch-auditor is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 26d ago), licensed MIT. It adds 247 tokens to every session and 4,299 once invoked, about $0.0012 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.