$ show buildermethods/agent-os
Agent OS is a framework for AI coding assistants to establish, discover, and inject project standards and shape specifications. It provides a set of markdown commands (commands/agent-os/) that define workflows for common tasks like discovering codebase patterns, maintaining an index of standards, injecting relevant standards into context, planning product vision, and shaping feature specs. These commands are designed to be consumed by tools like Claude Code and Cursor. The repository also includes bash scripts for installing Agent OS into a project, syncing standards back to a base profile, and shared utility functions. The core value is not executable code but a methodology encoded in instructions and shell scripts that enforce a disciplined approach to spec-driven development with AI agents. The codebase is lean, well-structured, and focused on solving the problem of keeping AI agents aligned with team conventions without heavy tooling overhead.
The LLM identified 2 files worth highlighting for reuse:
A self-contained collection of reusable bash functions for colored output, simple YAML value extraction, profile inheritance chain resolution with circular dependency detection, and file operations (ensure_dir, copy_file, copy_standards). It can be sourced by any bash script and provides a clean API for logging, parsing, and filesystem tasks, making it straightforward to extract into another project.
A detailed markdown command that instructs an AI agent how to interactively discover and document tribal knowledge from a codebase. It demonstrates a rigorous pattern of analyzing code structure, presenting findings, asking clarifying questions, and saving concise standards. The procedure is reusable as a template for any agent-driven documentation workflow.