Initialize horizon — define the objective, target date, and 3-7 milestones

Store horizon — call mcp__claude-flow__memory_store with namespace horizons and key horizon-[name]:

{
  "objective": "...",
  "created": "2026-04-28",
  "targetDate": "2026-05-15",
  "milestones": [
    {"id": "m1", "name": "...", "criteria": "...", "status": "pending"},
    {"id": "m2", "name": "...", "criteria": "...", "status": "pending"}
  ],
  "currentMilestone": "m1",
  "sessions": []
}

Session check-in — at the start of each session:
- Recall horizon: mcp__claude-flow__memory_retrieve key horizon-[name] namespace horizons
- Review milestone status
- Assess drift (are we still on track?)
- Plan this session's contribution
Work and record — as work progresses:
- Update milestone status
- Record session summary
- Store intermediate findings
Session check-out — at the end of each session:
- Update horizon state in memory
- Record what was accomplished
- Note blockers or scope changes
- Estimate remaining effort
Milestone completion — when a milestone is done:
- Verify completion criteria met
- Store learned patterns via mcp__claude-flow__hooks_intelligence_pattern-store
- Advance to next milestone
Drift detection — flag when:
- Progress rate suggests target date will be missed
- Scope has grown beyond original definition
- Dependencies have changed
- Approach needs fundamental rethinking

Memory namespaces

horizons — active horizon definitions and state
horizon-sessions — per-session summaries keyed by [horizon]-[date]
horizon-learnings — patterns and insights discovered during the horizon

horizon-track

Horizon Track

When to use

Steps