intent-layer

Generate and maintain hierarchical CLAUDE.md and AGENTS.md context nodes for codebases.

8|1|Updated Jan 21, 2026
One-click install
npx skills add https://github.com/orban/intent-layer --skill intent-layer-orban
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: intent-layer
Source: https://github.com/orban/intent-layer/tree/main/skills/intent-layer
Command: npx skills add https://github.com/orban/intent-layer --skill intent-layer-orban

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation and maintenance of hierarchical Intent Layer context (CLAUDE.md/AGENTS.md) to help AI agents navigate large codebases with senior-engineer insight.

Core Features & Use Cases

  • Hierarchical context loading: auto-loads ancestor nodes so agents understand scope without scanning the entire repository.
  • Automated scaffolding: bootstraps root and child nodes for new projects, onboarding, or expansion of codebases.
  • Auto-invocation of sub-skills: integrates git-history and pr-review-mining during node creation to surface pitfalls, contracts, architecture decisions, and cross-cutting concerns.

Quick Start

Create a root AGENTS.md for a new repository and verify that child nodes are generated for major subsystems as you scale.

Frequently Asked Questions about intent-layer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AGENTS.md context files to help AI navigate my codebase?

Intent Layer automates the creation of hierarchical AGENTS.md or CLAUDE.md context files to help AI agents navigate large codebases with senior-engineer insight. It generates root and child nodes during project setup, onboarding, or expansion.

What is hierarchical context loading for codebase navigation?

Hierarchical context loading automatically retrieves ancestor AGENTS.md nodes so AI agents understand subsystem scope without scanning the entire repository. This mechanism provides senior-engineer level insight into architecture decisions and cross-cutting concerns.

How do I bootstrap CLAUDE.md nodes for new project onboarding?

Apply Intent Layer during project onboarding or expansion to automate scaffolding of root and child CLAUDE.md nodes. It auto-invokes sub-skills like git-history and pr-review-mining to surface architecture decisions, pitfalls, and contracts.

Can I surface architecture decisions and pitfalls from git history for AI context?

Yes, Intent Layer auto-invokes sub-skills like git-history and pr-review-mining during AGENTS.md node creation. This surfaces architecture decisions, contracts, and pitfalls directly into the hierarchical context for AI agents to reference.

Does Intent Layer work without external dependencies for codebase maintenance?

Intent Layer has no external dependencies and can maintain hierarchical context out of the box. However, it may auto-invoke sub-skills like git-history and pr-review-mining if available to enrich the AGENTS.md context with deeper architectural insights.