Research
Use /research_codebase to explore and document how existing code works. AI agents write findings to the thoughts directory so knowledge persists across sessions.
Hyprlayer
A structured workflow where AI agents research your codebase, build implementation plans, execute them phase-by-phase, and validate the results — all grounded in shared team knowledge through a persistent thoughts directory.
How It Works
Section titled “How It Works”Hyprlayer installs a CLI (hyprlayer) and a suite of AI agent commands for Claude Code, GitHub Copilot, and OpenCode. The CLI manages a shared thoughts repository that gives AI agents persistent context about your codebase across sessions and team members.
Plan
Use /create_plan to build phased implementation plans with success criteria. Plans go through interactive research and iteration before implementation begins.
Implement
Use /implement_plan to execute plans phase-by-phase with verification at each step. The agent follows the plan’s intent while adapting to what it finds.
Validate
Use /validate_plan to verify the implementation against the plan’s success criteria and identify any deviations or issues.
Supported AI Tools
Section titled “Supported AI Tools”- Claude Code — Anthropic’s Claude Code CLI
- GitHub Copilot — GitHub Copilot in VS Code
- OpenCode — OpenCode CLI with provider selection (GitHub Copilot, Anthropic, or Abacus)