Initialize .planning/ from a repo that already exists - PROJECT.md, REQUIREMENTS.md and a remaining-work ROADMAP.md derived from the code and the git history
Scanned 9/3/2026
Install to Claude Code
npx -y skills add crenshawdev/cadence --skill cad-adopt --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Cad Adopt?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/crenshawdev-cad-adopt)More formats (shields.io, HTML) on the badges page.
---
name: cad-adopt
description: "Initialize .planning/ from a repo that already exists - PROJECT.md, REQUIREMENTS.md and a remaining-work ROADMAP.md derived from the code and the git history"
argument-hint: ""
allowed-tools:
- Read
- Write
- Edit
- Bash
- Grep
- Glob
- AskUserQuestion
---
<objective>
The second front door. A project that already has code and history enters
Cadence as itself instead of as a blank page: the README, the manifests, the
tree and `git log` are read here, shipped capability lands in PROJECT.md as
Validated, the roadmap covers what is LEFT, and the only questions asked are
the ones the repo cannot answer. What it writes is the same `.planning/` shape
/cad-new-project writes, so every downstream command works unchanged.
</objective>
<execution_context>
@${CLAUDE_PLUGIN_ROOT}/cadence-core/workflows/adopt.md
</execution_context>
<process>
Execute end-to-end.
</process>
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...