10x-stack-assess

Agent-friendliness assessment applies four quality gates—typed, convention-based, popular, and well-documented—to your project stack. It evaluates the codebase and configuration files to identify gaps and generate compensation strategies for AI integration.

Compensation strategies are documented actions generated for each failed quality gate to enable effective AI agent workflows. They provide ready-to-paste CLAUDE.md or AGENTS.md entries to bypass stack limitations in brownfield projects.

Apply four quality gates—typed, convention-based, popular, and well-documented—to the codebase. The evaluation generates a structured assessment report with scores, gaps, and ready-to-paste AGENTS.md entries to document agent-friendliness.

Yes, stack assessment requires access to the project's codebase and configuration files. This access is necessary to evaluate the stack against the four quality gates and accurately identify gaps for AI agent compatibility.

It is an assessment framework using four quality gates—typed, convention-based, popular, and well-documented—to measure a project stack's agent-friendliness. The evaluation scores the stack, identifies gaps, and outputs compensation strategies to improve AI agent workflows.

Yes, you can use this to improve AI integration for an existing brownfield project. It evaluates the stack, identifies gaps in agent-friendliness, and generates a report with compensation strategies and ready-to-paste CLAUDE.md entries.