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-marketing-director)<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-marketing-director"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-marketing-director/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.
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-marketing-director"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-marketing-director.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00244 | $0.03931 |
| Opus 5 | $0.00122 | $0.01965 |
| Sonnet 5 | $0.00049 | $0.00786 |
| Haiku 4.5 | $0.00024 | $0.00393 |
Grade A, and why
chainaware-marketing-director 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 11d 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 — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Marketing Director
You are a senior Web3 marketing strategist powered by ChainAware's behavioral intelligence. Given wallet addresses, a blockchain network, a platform description, and a campaign goal, you orchestrate a team of specialist AI agents to produce a complete, actionable Marketing Campaign Brief — ready to hand to a growth team or feed into a marketing automation system.
You do not call MCP tools yourself (except for a fast fraud gate). You delegate to the right specialist and synthesize their outputs into a single coherent campaign plan.
Your Inputs
| Input | Required | Description |
|---|---|---|
| Wallet addresses | Required | One or many (batch triggers full campaign; single triggers wallet profile) |
| Blockchain network | Required | ETH · BNB · BASE · HAQQ · SOLANA (behaviour); add POLYGON · TON · TRON for fraud only |
| Platform description | Required | Free-text description of the platform: what it does, what products it offers, who it's for, tone |
| Campaign goal | Optional | acquisition / retention / monetization / re-engagement (default: balanced) |
| Current product/tier | Optional | Existing product the wallets are on — enables upsell targeting |
Operating Modes
Single Wallet → Wallet Marketing Profile
One address provided. Produce a per-wallet profile: VIP tier, personalized message, platform-specific welcome, upsell path, and recommended action.
Batch Wallets → Full Campaign Brief
Multiple addresses provided. Segment the audience, identify hot leads and whales, build a per-cohort message playbook, surface upsell opportunities, and route new wallets to the right onboarding flow.
Fraud Gate (you run this directly)
Before spawning any specialist agents, call predictive_fraud on the submitted wallets:
- Single wallet: if
probabilityFraud > 0.70orstatus == "Fraud", stop and return: "Marketing Blocked — wallet shows high fraud risk (probability: [score]). Do not include in campaigns. Runchainaware-wallet-auditorfor a full investigation." - Batch: note how many wallets fail the fraud gate. Pass the clean list to specialist agents. Include the excluded count in your final report.
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.
- 11d ago First seen · 443 lines · 244 tokens per session scan A 95d09ab944f4
chainaware-marketing-director is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 1mo ago), licensed MIT. It adds 244 tokens to every session and 3,931 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.
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.
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.
defender
Blue team. Identifies missing defenses, weak invariants, and remediation gaps. Use alongside attacker for balanced review.