- Home
- Skills
- Agents & Orchestration
- Scaffold Kit: A Clear Plan Before Your AI Builds
More screenshots
Works with the AI Agents you already use
Scaffold Kit: A Clear Plan Before Your AI Builds
Turn an idea into a clear plan and a focused build brief, with the important choices explained and your approval before code is built.
$19
About this skill
Know what your AI is going to build before it starts.
Scaffold Kit helps you turn an idea, an existing project or your next feature into a plan you can review. It asks the useful questions, explains tradeoffs in language that fits your experience, and keeps open choices visible.
Optional bundle: Get both skills for $39 one-time. Each skill also works independently.
What you get
- An Architecture Document explaining how the parts fit together.
- An Engineering Document recording requirements, risks and checks.
- A Decision Log keeping choices, alternatives and revisit triggers together.
- One focused Slice Brief: the next piece of work, what is excluded, how it will be checked and its approval state.
Small changes use a compact brief. Choose plain language, balanced explanations or developer shorthand. The evidence and approval rules stay the same.
You stay in control
Planning writes documents. You review the specific build brief before implementation begins. Open decisions stay visible until you resolve them. The optional auditor checks document structure and consistency; your project's functional tests remain separate.
Works independently
Use Scaffold Kit with your project files and existing checks. Anti-Dark-Code is an optional companion for mapping existing code and supplying verification evidence.
Getting started
Use a compatible AI agent that can read supporting files and work with your project documents. The planning instructions need no Python. The optional standard-library auditor needs Python 3.9 or newer and can run separately from your project's Python. Your AI account and model/API usage are separate.
Delivery and example
Agensi handles checkout, access and delivery. The images show excerpts of a fictional client-tracker plan: choices are Proposed and build approval is pending. No app was built.
Source and license
Packaged from stable Scaffold Kit 0.4.5. Review the publicly available source and included FSL-1.1-MIT terms: https://github.com/LynxTWO/scaffold-kit/releases/tag/v0.4.5
Plans and writes documents; implementation needs your approval of the specific brief. The document auditor checks structure and consistency, while functional behavior needs project checks. Supporting-file access and execution depend on your host.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 25 days ago
Permissions
Reads the supporting skill files and authorized project files; writes planning documents only. Terminal access is optional for the Python document auditor. The auditor has no network client. Product code, installs, schema changes and deployment are outside the planning interview. Anti-dark-code is optional.