Core

Hybrid Task System

Sprint Summary

!node -e "try{const p=require('./prd.json');const sp=p.sprints?p.sprints[p.sprints.length-1]:p;const s=Object.values(sp.stories||p.stories||{});const name=sp.id||sp.name||p.sprint||'unknown';const done=s.filter(x=>x.passes===true).length;const pending=s.filter(x=>x.passes===null||x.passes===false).length;const deferred=s.filter(x=>x.passes==='deferred').length;console.log('Sprint:',name,'| Done:',done,'| Pending:',pending,'| Deferred:',deferred,'| Total:',s.length)}catch(e){console.log('No prd.json')}"

Do not read the full prd.json into context. Use Grep to find specific stories or Read with offset/limit for targeted sections.

When to Sprint

• 5+ related tasks — create a sprint in prd.json
• < 5 tasks or single fixes — work directly, no sprint or stories needed
• Design/creative work — iterate freely, skip planning overhead
• Quick fixes — just fix, verify, done

Sprints are for tracking, not for ceremony. If the work is small, skip the overhead.

Two Layers

Work with native Tasks during session, batch-update prd.json at end.

prd.json Story Schema

{
  "id": "S26-001",
  "title": "Fix tooltip clipping",
  "priority": 1,
  "passes": null,
  "type": "fix",
  "category": "components",
  "notes": "",
  "resolution": ""
}

Resolution Learning

When completing bug fixes, document HOW:

[PATTERN]: [SPECIFIC FIX]

Examples:

• null-check: Added optional chaining at line 45
• missing-import: Added import for DateRange
• type-mismatch: Changed Record<string, T> to Partial<Record<K, T>>
• overflow: Added max-h + overflow-auto

Context Optimization

Archive Trigger

When 4+ total sprints exist, or prd.json > 500 lines, or prd.json > 50KB:

• Suggest archive before starting work
• Archive keeps only last 3 sprints active
• Completed stories move to .claude/archives/prd-archive-YYYY-MM.json