Documentation
/deep-init
Generate an agent-agnostic, two-tier context layer for a codebase — a lean, always-loaded CLAUDE.md plus a deep, on-demand .ai/docs/ layer (business rules, live DB schema + ORM drift, cross-component workflows, and the WHY: ADRs + a knowledge log), every claim grounded to
shell
$ npx -y skills add deepfusionlabs/deep-init --skill deep-init --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/deep-init
Context preview
The summary Claude sees to decide when to auto-load this skill.
Generate an agent-agnostic, two-tier context layer for a codebase — a lean, always-loaded CLAUDE.md plus a deep, on-demand .ai/docs/ layer (business rules, live DB schema + ORM drift, cross-component workflows, and the WHY: ADRs + a knowledge log), every claim grounded to
Ships withdeep-init
Claude Code plugin that writes grounded, verified context for your coding agent — every claim checked against your code. Lean CLAUDE.md + deep docs, 100% local, MIT.
Get the whole plugin, auto-invoked
Stats
6
Stars
0
Views
0
Forks
Active
Maintenance
Python
Language
MIT
License
5d ago
Last commit
1mo ago
Created
Repo: deepfusionlabs/deep-init

