deepinit

Generate hierarchical AGENTS.md files with parent reference tags across repositories.

3|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/marcmunoz-uno/jailbreak --skill deepinit-marcmunoz-uno
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deepinit
Source: https://github.com/marcmunoz-uno/jailbreak/tree/main/skills/deepinit
Command: npx skills add https://github.com/marcmunoz-uno/jailbreak --skill deepinit-marcmunoz-uno

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Initializes an AI-friendly, navigable documentation layer so agents can quickly understand what exists in each directory and how to work there correctly.

Core Features & Use Cases

  • Hierarchical AGENTS.md Generation: Produces AGENTS.md files across the codebase and links them via parent reference tags for an explicit documentation tree.
  • Directory Mapping and Level-by-Level Planning: Scans directories recursively, plans work by depth, and generates parent-first to keep references valid.
  • Update and Preservation of Manual Notes: When AGENTS.md already exists, updates auto-generated sections while preserving content marked as manual.
  • Validation for Completeness and Parent Resolution: Checks that parent references resolve and that no orphaned or missing AGENTS.md files remain.

Quick Start

Ask the AI to run the deepinit skill to generate or update hierarchical AGENTS.md files across the repository, preserving any manual sections.

Frequently Asked Questions about deepinit

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

FAQPage Schema
How do I generate hierarchical AGENTS.md files across my codebase?

To generate hierarchical AGENTS.md files, the skill recursively scans directories, maps the hierarchy by depth, and creates parent-first documentation with resolvable reference tags for AI navigation. It plans work level-by-level to maintain valid links across the repository.

What is hierarchical AGENTS.md documentation used for?

Hierarchical AGENTS.md documentation provides an AI-friendly navigable layer so agents can quickly understand what exists in each directory and how to work there correctly. It links files via parent reference tags to create an explicit documentation tree across the codebase.

Can I update auto-generated AGENTS.md sections without losing manual notes?

Yes, updating AGENTS.md sections preserves manual notes by only modifying auto-generated content while keeping manual annotations intact. This merge preservation ensures your custom working instructions remain safe during ongoing documentation refreshes.

Does this approach work for large, multi-directory repository bootstrapping?

Yes, this approach is designed for large, multi-directory projects where agents need consistent context. It bootstraps the codebase by applying recursive directory mapping and level-ordered generation to build a complete documentation tree across the repository.

How does the validation check for completeness and orphaned AGENTS.md files?

Validation checks for completeness by verifying that parent references resolve correctly and ensuring no orphaned or missing AGENTS.md files remain in the directory hierarchy. This guarantees the navigable documentation layer stays fully intact.