auto-plan

Work Plan - Create Implementation Plan

Analyze open issues and create a sequenced implementation plan.

Workflow Mode

WORKFLOW_MODE: planning

---

Instructions

You are now the Implementation Planner. Your job is to:

1. Read all open issues from GitHub
2. Analyze dependencies and priorities
3. Create an implementation-plan.md document
4. Present to user for approval

---

Phase 0.5: Detect Existing Plan Files

Before gathering issues, check for prior plan runs:

ls implementation-plan.md implementation-plan-*.md 2>/dev/null

• If none exist → this is the first run, will create implementation-plan.md
• If some exist → find the highest number and create implementation-plan-{N+1}.md
  • implementation-plan.md counts as run 1
  • implementation-plan-2.md is run 2, etc.
• Read ALL existing plan files for context — understand the current dependency graph and what's already been sequenced

---

Phase 1: Gather Issues

Read All Discovery Files

ls discovery.md discovery-*.md 2>/dev/null

Read all discovery files (glob discovery*.md) for full requirements context.

List All Open Issues

gh issue list --state open --json number,title,labels,milestone,body --jq '.[] | "### #\(.number): \(.title)\nMilestone: \(.milestone.title // "None")\nLabels: \(.labels | map(.name) | join(", "))\n"'

Check Milestones

gh api repos/{owner}/{repo}/milestones --jq '.[] | "#\(.number): \(.title) - \(.open_issues) open, \(.closed_issues) closed"'

---

Phase 2: Analyze Dependencies

For each issue, extract dependencies:

# Get issue body and find dependencies
gh issue view {number} --json body --jq '.body' | grep -oE 'Depends on #[0-9]+'

Build a dependency graph:

• Which issues have no dependencies? (Can start immediately)
• Which issues are blocked by others?
• Which issues unblock the most other work?

---

Phase 3: Design Language & Style Guide

Before implementation begins, spawn the Designer agent to establish the visual foundation: