productivity-score

1# Productivity Score
2 
3Calculate a productivity scorecard from the Agent Monitor's real data.
4 
5## Input
6 
7The user provides: **$ARGUMENTS**
8 
9Options: "today", "this week", "last 30 days", a session ID, or "compare" for period comparison.
10 
11## Data Sources
12 
13| Endpoint | Returns |
14|----------|---------|
15| `GET /api/analytics` | Token totals (`total_input`, `total_output`, `total_cache_read`, `total_cache_write` — baselines pre-summed), tool_usage top 20, daily_events/sessions, event_types, sessions_by_status, agents_by_status, avg_events_per_session, total_subagents |
16| `GET /api/sessions?limit=100` | Sessions with metadata JSON: `thinking_blocks`, `turn_count`, `total_turn_duration_ms`, `usage_extras` (service_tier, speed, inference_geo) |
17| `GET /api/pricing/cost` | Total cost with per-model breakdown |
18| `GET /api/workflows/{sessionId}` | 11 workflow datasets: stats, orchestration, toolFlow, effectiveness, patterns, modelDelegation, errorPropagation, concurrency, complexity, compaction, cooccurrence |
19 
20## Score Components (each 0–100)
21 
22### 1. Completion Rate (20% weight)
23From `sessions_by_status`:
24- `completed / (completed + error + abandoned) × 100`
25- Bonus for high completed-to-active ratio
26- Penalty for abandoned sessions (wasted work)
27 
28### 2. Token Efficiency (20% weight)
29From analytics `tokens` (baselines are pre-summed into totals):
30- **Cache hit rate**: `total_cache_read / (total_cache_read + total_input) × 100`
31  - Above 60% = excellent, below 30% = poor
32…