# Init

> Bootstrap ADR Kit in a project, including instructions, an architecture audit, initial ADR proposals, and the pre-commit gate.

- Skill: `rvdbreemen/init-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rvdbreemen/init-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rvdbreemen/init-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- License: MIT
- Author: rvdbreemen (https://skillmd.com/u/rvdbreemen)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rvdbreemen/init-2

---


<!-- Generated by scripts/build-client-adapters.py from clients/workflows.json; schema v1; client codex-cli. -->
# Initialize ADR Kit (the adopt mode of setup)

Invoke explicitly with `$adr-kit:init` when needed.
Resolve `<plugin-root>` from this installed skill. Use only bundled,
local ADR Kit tools and follow this canonical workflow:

1. Run the setup workflow, preview legacy ADR migration, and audit the workspace.
2. Create selected reconstruction candidates as Proposed and present them in small batches.
3. Use a compact confirmation grill only when the chosen decision, rationale, alternatives, and consequences have direct cited evidence; otherwise use the full grill and confirm each ADR separately.
4. Install the ADR Kit-owned pre-commit gate, then state plainly that the declarative gate is free and always on while the LLM pass is on by default and costs one model call per `llm_judge: true` ADR on every commit touching its scope, linear in their number and nothing at all until an author opts one in.
5. Record the host backend with `adr-judge --set-backend host --host-client <this client's id>` rather than by writing JSON (the host model is the only backend, ADR-036; operators can override per run with ADR_KIT_LLM_CMD), never prompt for or store an API key, and add docs/adr/.adr-kit.local.json to .gitignore.
6. Finish with `adr-doctor --fix-index docs/adr/`.

Do not contact another model or mutate user-owned instructions.