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.
npx agentmods add instructions/chainaware/behavioral-prediction-mcp/agents-mdgit clone --depth 1 https://github.com/ChainAware/behavioral-prediction-mcpWhat 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 | $0.08761 | $0.08761 |
| Opus 5 | $0.04380 | $0.04380 |
| Sonnet 5 | $0.01752 | $0.01752 |
| Haiku 4.5 | $0.00876 | $0.00876 |
Grade A, and why
behavioral-prediction-mcp AGENTS.md 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 yesterday.
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 — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChainAware Subagent Index
Machine-readable index of all 34 Claude Code subagents in .claude/agents/.
Each agent is a specialist that handles a specific Web3 intelligence task using the
ChainAware Behavioral Prediction MCP (https://prediction.mcp.chainaware.ai/sse).
🏆 Featured in the CB Insights Fraud Prevention Market Map for the AI Era (2026) 🌐 Listed on the BNB Chain AI Landscape (2025) 🚀 Listed on BNB Chain Kickstart — Marketing Tools (2025) 💰 Awarded a $250k Google Cloud Grant (2025) ☁️ Accepted into the AWS Fintech Accelerator (2024) 🌱 Featured in the Safary Club Web3 Growth Landscape — Growth Tools (2024)
Links: Website · Twitter · LinkedIn · Blog · Learn · Examples
Accuracy: 98% Fraud Detection · 90.1% Rug Pull Detection — backtesting verified
Quick setup:
claude mcp add --transport sse chainaware-behavioral-prediction \
https://prediction.mcp.chainaware.ai/sse --header "X-API-Key: YOUR_KEY"
export CHAINAWARE_API_KEY="your-key-here"
Agent Directory
chainaware-wallet-auditor
File: .claude/agents/chainaware-wallet-auditor.md
Model: claude-sonnet-4-6
Tools: predictive_behaviour
Purpose: Full due diligence. Deep behavioural analysis of a wallet including fraud signals, intent, experience, and recommendations.
Triggers: "full audit of 0x...", "due diligence on this wallet", "complete analysis", "deep dive on this address"
Input: wallet address + network
Output: Behaviour profile, fraud signals, experience score, intent, recommendations
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.
- yesterday First seen · 506 lines · 8,761 tokens per session scan A 4e2af6c0b1a4
behavioral-prediction-mcp AGENTS.md is an instructions file published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 20d ago), licensed MIT. It adds 8,761 tokens to every session, about $0.0438 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 instructions, from other repositories
WAIaaS CLAUDE.md
Instructions for waiaas/WAIaaS, covering waiaas project rules, language, communication, schema & type system and database.
flario CLAUDE.md
Claude Code instructions for dziuba0x/flario, covering claude.md: flario project brief, 1. what flario is, 2. state today (v1.3.0), 3. architecture and 4. rules that still apply.
quantum-shield CLAUDE.md
Claude Code instructions for kota1026/quantum-shield, covering quantum shield, project structure, universal rules, domain rules and quick start.
ponscli CLAUDE.md
Claude Code instructions for mesutgulecen/ponscli, covering ponscli, the rule that matters most, layout, verifying a change and things that will bite.
Agent-skills AGENTS.md
Instructions for EmblemCompany/Agent-skills, covering agents.md - emblemai agent skills, core emblemai message, skills directory, cross-platform skills and use-case skills.
UCAI AGENTS.md
AGENTS.md instructions for nirholas/UCAI, covering ucai development guidelines, project overview, terminal management and contributing.