AGENTS
01Agent
Agent "AGENTS" from nirholas/crypto-vision, covering defi-agents development guidelines, project overview, project philosophy, no mocks, no fakes, no stubs and code quality standards.
121 tagged defi, measured the same way as everything else here.
Browse within: blockchain 61ethereum 50awesome-mcp-servers 34claude-mcp 34crypto 28comment 27follow 27influencer 27berachain 23cross-chain 22dex 22agent-plugin 7grok-bot 7hyperliquid 7
Agent
Agent "AGENTS" from nirholas/crypto-vision, covering defi-agents development guidelines, project overview, project philosophy, no mocks, no fakes, no stubs and code quality standards.
Agent
You are working on crypto-vision, a cryptocurrency intelligence platform. The dashboard is in apps/dashboard/ (Next.js 15, Tailwind CSS). The backend has a full Pump.fun Agent Swarm in packages/pump-agent-swarm/ with.
Agent
You are finalizing documentation for crypto-vision, a full-stack TypeScript crypto data platform. The project has.
galleonlabs/hypergrok-trading-desk
Agent
The only Bot on the desk that places, modifies or cancels Hyperliquid orders. Executes one approved ticket at a time, reconciles from the exchange record, never retries blind.
galleonlabs/hypergrok-trading-desk
Agent
Reads Hyperliquid market data live and turns it into timestamped, sourced market briefs. Read-only.
galleonlabs/hypergrok-trading-desk
Agent
Owns the desk's risk limits, sizes every trade from live account state, monitors the book, and can veto. Read-only on the exchange.
ChainGPT-org/chaingpt-claude-skill
Agent
Solidity contract specialist for the generate → audit → fix → deploy lifecycle. Use when writing, reviewing, auditing, or deploying smart contracts. Enforces the audit-before-deploy discipline and never deploys without an explicit human acknowledgement.
ChainGPT-org/chaingpt-claude-skill
Agent
Disciplined DeFi execution specialist for swaps, bridges, lending, LP/yield moves, and perps order prep. Use when the user wants to actually DO something on-chain. Runs mandatory pre-flight checks, respects every custody gate, and never sets acknowledgeMainnet or signs from the agent wallet without explicit human…
ChainGPT-org/chaingpt-claude-skill
Agent
Read-only Web3 research analyst. Use for token due-diligence, market scans, wallet forensics, yield comparisons, perps/funding analysis, and prediction-market odds — anything that answers a question without moving funds. It cannot build or sign transactions, so it is safe to run unattended.
ChainAware/behavioral-prediction-mcp
Agent Claude Code
Screens an AI agent's trustworthiness by checking both its operational wallet and its feeder wallet (the wallet that funds it) using ChainAware's Behavioral Prediction MCP. If either wallet is fraudulent the agent is flagged as bad. Returns a normalized Agent Trust Score from 0 to 10: 0 = fraud, 1 = new address /…
ChainAware/behavioral-prediction-mcp
Agent Claude Code
Segments a batch of wallets into behavioral cohorts using ChainAware's Behavioral Prediction MCP. Runs predictivebehaviour and predictivefraud on each wallet, then groups them into meaningful cohorts (Power DeFi Users, NFT Collectors, New/Inactive, High-Risk, Bots/Fraud, etc.) with cohort statistics and a recommended…
ChainAware/behavioral-prediction-mcp
Agent Claude Code
First-layer MiCA-aligned compliance screening for DeFi protocols and CASPs. Orchestrates ChainAware's specialist subagents to produce a structured Compliance Report covering sanctions, AML behavioral flags, fraud detection, and transaction risk — with a clear verdict (PASS / ENHANCED DUE DILIGENCE / REJECT) and an…
Agent
Specialist for inline assembly / Yul. Reviews memory layout, return-data handling, dirty-bits, opcode usage. Use whenever significant assembly is present.
Agent
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.
Agent
Identifies protocol invariants from contract code and intent, generates Foundry invariant tests with handlers. Use from /invariant and /audit-deep.
Agent Claude Code
TypeScript API specialist — Hono routes, Effect-TS services, Drizzle ORM schemas, A2A protocol. Use for any work in api-ts/.
Agent Claude Code
Cross-chain swap debugger — trace failed transactions, diagnose quote errors, debug bridge issues, analyze token security problems, debug RPC/balance issues. Use when investigating swap/transaction/balance failures.
Agent
Autopilot is a trading agent that decides, commits, trades and publishes on its own. It runs on the execution infrastructure we already had (multi-chain swap routing, managed wallets, policy gates, token security) and adds the part that was missing: a loop that forms a thesis, refuses or takes the trade against…
Agent
Specialized trading sub-agent. Only operates Lighter via the lighter-mcp server. Never edits source code, never opens files. Always shows previews before live writes.
Agent
Quantum Shield Project - Strategic Decision Framework.