affaan-m/ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
npx add-skill affaan-m/ECCThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Demo app using AGENTS.md
The 7 Laws of AI Agent Discipline for Claude Code. Stops your agent from skipping research, claiming 'done' without verifying, and repeating yesterday's mistakes. 13 enforcement skills, gating hooks, the Mulahazah auto-leveling instinct engine, and a GitHub Action transcript linter. Beginner: /plugin install. Expert: adds MCP tools.
Agent OS integrations for deployed agents and swarms: execute-first routing, Micro ECF harness exports, x402 edge calls, receipts, and USDC settlement on Base.
Claude re-reads your code every session. Make it stop. Save 70%+ on tokens. Local MCP server with AST indexing, hybrid search, and cross-session memory.
Production-grade Claude Code skills, auto-research validated. Includes /deep-research with 89-run benchmark.
Open Codex skills for investment research workflows