happier-plan

Authors user-requested implementation plans as executable contracts for the Happier repository.

1.6k|141|Updated Dec 16, 2025
One-click install
npx skills add https://github.com/happier-dev/happier --skill happier-plan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: happier-plan
Source: https://github.com/happier-dev/happier/tree/main/skills/happier-plan
Command: npx skills add https://github.com/happier-dev/happier --skill happier-plan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents agents from creating unrequested or unverifiable plans by enforcing explicit user authorization, evidence-based design, and approval-gated execution contracts for Happier repository work.

Core Features & Use Cases

  • Authorization-gated planning: Classifies requests as CREATE, REFINE, REPLACE, or AMEND and refuses to author plans without an explicit user request.
  • Evidence-driven design: Requires investigation of canonical owners, entry points, compatibility seams, and failure points before selecting the smallest coherent target design.
  • Self-contained execution contracts: Produces plans with intent, current-state evidence, target state, decisions, execution units, QA, completion criteria, and amendment workflows.
  • Use Case: When a user asks to plan a cross-device sync feature, the skill investigates the current system, drafts a DRAFT plan with deciding checks, and waits for explicit approval before any implementation begins.

Quick Start

Ask the agent to create a Happier repository implementation plan for the specific feature or change you want, and it will draft an approval-gated plan under .project/plans/.

Frequently Asked Questions about happier-plan

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an implementation plan for the Happier repository?

Explicitly ask the agent to create a plan for your feature or change. The skill classifies the request, investigates the current system, drafts a DRAFT plan under .project/plans/, and waits for your approval before any implementation starts.

When should I use the happier-plan skill?

Use it only when you explicitly want to create, materially refine, replace, or amend a Happier repository plan. It is not for implementing existing plans, updating execution status, reviewing completed work, or making internal checklists.

Does creating a plan also start the implementation?

No. Plan authoring does not authorize implementation. The draft is presented for approval first, and execution is handed off to the separate happier-implement-plan skill only when you explicitly ask to execute the approved plan.

What happens if implementation evidence contradicts an approved plan?

The agent pauses the affected work, records the evidence, proposes the smallest coherent amendment, and asks you to approve, reject, or redirect it. Work resumes only after approval, with the amendment history preserved.

How does the skill decide a plan or phase is complete?

Completion requires observable evidence at the outermost contract surface, including required removals, behavior-change test evidence, and live QA where runnable. File existence, compilation, or agent claims of done never count as completion.