# Session Health Score

Claude Code session health aggregator providing A-F grade based on cost efficiency, latency performance, productivity velocity, and cache utilization with actionable recommendations.

---


## Metadata

**Title:** Session Health Score
**Category:** statuslines
**Author:** JSONbored
**Added:** October 2025
**Tags:** health-score, session-grade, performance-aggregator, quality-metrics, optimization-recommendations
**URL:** https://claudepro.directory/statuslines/session-health-score

## Overview

Claude Code session health aggregator providing A-F grade based on cost efficiency, latency performance, productivity velocity, and cache utilization with actionable recommendations.

## Content

#!/usr/bin/env bash
SESSION HEALTH SCORE FOR CLAUDE CODE
AGGREGATES MULTIPLE METRICS INTO OVERALL HEALTH GRADE (A-F)
READ JSON FROM STDIN
read -r input
EXTRACT METRICS
totalcost=$(echo "$input" | jq -r '.cost.totalcost_usd // 0')
totaldurationms=$(echo "$input" | jq -r '.cost.totaldurationms // 1')
apidurationms=$(echo "$input" | jq -r '.cost.totalapiduration_ms // 0')
linesadded=$(echo "$input" | jq -r '.cost.totallines_added // 0')
linesremoved=$(echo "$input" | jq -r '.cost.totallines_removed // 0')
cachereadtokens=$(echo "$input" | jq -r '.cost.cachereadinput_tokens // 0')
cachecreatetokens=$(echo "$input" | jq -r '.cost.cachecreationinput_tokens // 0')
regularinputtokens=$(echo "$input" | jq -r '.cost.input_tokens // 0')
CONVERT DURATION TO MINUTES
if [ "$totaldurationms" -gt 0 ]; then
 durationminutes=$(echo "scale=2; $totalduration_ms / " | bc)
else
 duration_minutes=
fi
METRIC 1: COST EFFICIENCY (25 POINTS)
TARGET: $ = POOR
if (( $(echo "$duration_minutes > 0" | bc -l) )); then
 costperminute=$(echo "scale=4; $totalcost / $durationminutes" | bc)
else
 costperminute=0
fi
if (( $(echo "$costperminute 3s = poor
networktime=$((totaldurationms - apiduration_ms))
networkseconds=$(echo "scale=2; $networktime / " | bc)
if (( $(echo "$network_seconds 30 lines/min = excellent, = good, 0" | bc -l) )); then
 linesperminute=$(echo "scale=1; $totalchanged / $durationminutes" | bc)
else
 linesperminute=0
fi
if (( $(echo "$linesperminute > 30" | bc -l) )); then
 productivity_score=25
elif (( $(echo "$linesperminute > 15" | bc -l) )); then
 productivity_score=18
elif (( $(echo "$linesperminute > 5" | bc -l) )); then
 productivity_score=12
else
 productivity_score=5
fi
METRIC 4: CACHE UTILIZATION (25 POINTS)
TARGET: >40% HIT RATE = EXCELLENT, % = GOOD, 30 L/MIN
? Cache utilization metric (25 points): hit rate vs target >40%
? Actionable recommendations identifying weakest metric with optimization tips
? Metric breakdown display showing individual scores (C:25 L:18 P:12 K:25)
? Color-coded grading (green A, blue B, yellow C, orange D, red F)
CONFIGURATION
Format: bash
Refresh Interval: 2000ms
Position: left
USE CASES
? Quick session quality assessment at a glance
? Identifying performance bottlenecks across multiple dimensions
? Comparing session health across different projects/workflows
? Optimizing Claude Code usage based on weakest metric feedback
? Team performance benchmarking with standardized grading
? Historical session quality tracking for improvement trends
TROUBLESHOOTING
1) Health score always showing F grade despite good session
 Solution: Verify all JSON fields exist: cost.totalcostusd, cost.totaldurationms, cost.totalapidurationms, cost.totallinesadded, cost.totallinesremoved, cost.cachereadinputtokens. Missing fields default to 0, causing low scores. Check: echo '$input' | jq .cost. Ensure Claude Code version exposes all required metrics.
2) Individual metric scores seem incorrect
 Solution: Check thresholds: Cost (30 L/min = 25pt, >15 = 18pt), Cache (>40% hit = 25pt, >20% = 18pt). Verify calculations: costperminute = totalcost / durationminutes. Test each metric independently.
3) Recommendation not showing despite low grade
 Solution: Recommendations only display for grades C (), D (), or F ( latency > productivity > cache).
5) Cache score always showing 5 despite caching enabled
 Solution: Cache score requires cachereadinputtokens field. Verify: echo '$input' | jq .cost.cachereadinputtokens. If missing/null, defaults to 0 giving minimum score (5pt). Check that prompt caching is properly configured and Claude Code version supports cache metrics. Zero cachereadtokens = no cache benefit detected.
6) Metric breakdown abbreviations confusing
 Solution: Abbreviations: C = Cost efficiency, L = Latency performance, P = Productivity velocity, K = Cache utilization (K for Kache to avoid confusion with C). Each shows score out of 25 points. Add legend to documentation or customize METRICS string for clarity.
TECHNICAL DETAILS
Documentation: https://docs.claude.com/en/docs/claude-code/statusline
PREVIEW
✓ Health: B (82/) | GOOD | C:25 L:18 P:22 K:17


---

Source: Claude Pro Directory
Website: https://claudepro.directory
URL: https://claudepro.directory/statuslines/session-health-score

This content is optimized for Large Language Models (LLMs).
For full formatting and interactive features, visit the website.