plan-with-agent

Organizes ideas and requirements, converting them into executable tasks in Plans.md.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "plan-with-agent" with this command: npx skills add chachamaru127/claude-code-harness/chachamaru127-claude-code-harness-plan-with-agent

Planning Skill

Organizes ideas and requirements, converting them into executable tasks in Plans.md.

Quick Reference

  • "Create a plan" → this skill

  • "Turn what we talked about into a plan" → extract from conversation

  • "Want to organize what to build" → start with hearing

  • "Plan with TDD" → force TDD adoption

  • "CI/benchmark" → --ci mode

Deliverables

  • Plans.md - Task list executable with /work (required)

  • Feature priority matrix - Required/Recommended/Optional classification

Usage

/plan-with-agent # Interactive planning /plan-with-agent --ci # CI mode (non-interactive)

Mode-specific Usage

Mode Command Description

Solo mode /plan-with-agent

Claude Code alone: plan → execute → review

2-agent mode /plan-with-cc (Cursor) Plan with Cursor → Execute with Claude Code

Feature Details

Feature Reference

Execution Flow See references/execution-flow.md

TDD Adoption See references/tdd-adoption.md

Priority Matrix See references/priority-matrix.md

Execution Flow Overview

  • Step 0: Check conversation context (extract from previous conversation or start fresh)

  • Step 1: Hearing what to build

  • Step 2: Increase resolution (max 3 questions)

  • Step 3: Technical research (WebSearch)

  • Step 4: Extract feature list

  • Step 5: Create priority matrix (Required/Recommended/Optional)

  • Step 5.5: TDD adoption judgment and test design

  • Step 6: Effort estimation (reference)

  • Step 7: Generate Plans.md with quality markers

  • Step 8: Guide next actions

Auto-invoke Skills

Skill When to Call

setup

Call first (executes adaptive setup)

vibecoder-guide

When user is non-technical

Quality Markers (Auto-assigned)

Task Content Marker Effect

Auth/login feature [feature:security]

Security checklist

UI component [feature:a11y]

a11y check

Business logic [feature:tdd]

TDD recommended

API endpoint [feature:security]

Input validation

Bug fix [bugfix:reproduce-first]

Reproduction test first

Next Actions

After planning:

  • Start implementation with /work

  • Or say "start from Phase 1"

  • Adjust with "add {{feature}}" or "postpone {{feature}}"

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

auth

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

agent-browser

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

generate-video

No summary provided by upstream source.

Repository SourceNeeds Review