Works with the AI Agents you already use
Implementation Plan Before Code
Explores the codebase and returns a small-step plan with file:line references — without touching any file.
$5
About this skill
For large or ambiguous tasks, type "/plan <what you want>". Claude does not edit any file. It:
- Restates the goal, lists assumptions and asks up to 3 questions that would change the design.
- Explores entry points, affected modules, existing tests and patterns to reuse, citing file:line.
- Delivers: Goal · Chosen approach (with one rejected alternative and why) · Steps, each small and verifiable · Risks and mitigations · Out of scope.
- Asks whether to run the whole plan or go step by step.
Known limitations: produces a plan, not code. Very large monorepos may need you to point it at the right folders.
Unofficial. Not affiliated with Anthropic.
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 27 days ago
Permissions
No special permissions declared or detected