What problem does it solve? Teams adopting AI coding agents often lack the documentation, tests, linting, and structure agents need to work effectively, and have no systematic way to measure or close those gaps. ## Core Features & Use Cases - 16-Principle Audit: Scores a codebase 0-2 on each of 16 principles across three pillars (Codebase Memory, Implementation Feedbacks, Mapping the Context) with evidence-based findings and a total out of 32. - Guided Setup Mode: Runs the audit first, then proposes concrete fixes such as ADR templates, AGENTS.md generation, linter configs, and CI checks, creating files only after user approval. - Stack-Adaptive Checks: Detects Node/TypeScript, Python, Rust, Go, and other stacks, then maps principles to ecosystem tooling like ESLint, ruff, clippy, or golangci-lint. - Use Case: Before onboarding an AI agent to a legacy repository, run the audit to get a prioritized gap report, then use setup mode to generate an AGENTS.md entry point and ADR structure from actual codebase analysis. ## Quick Start Ask the agent to audit this repository against the 16 agentic codebase principles and produce a scored report with prioritized improvement actions.
