Install command
Not provided
Time-tracking statusline showing elapsed session duration, tokens per minute rate, and estimated cost with productivity metrics
Open the source and read safety notes before installing.
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
Decision playbook
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
0
78
—
No baseline selected
No major trust-signal divergence detected in the current selection.
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Source provenance statusRequired
Marked as source-backed.
Metadata reviewed
Registry metadata indicates a reviewed listing.
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Trust level risk gateRequired
Trust level does not block evaluation.
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Package verification flag
No package verification flag provided.
Checksum metadata
No checksum provided for downloaded artifact.
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Baseline comparison available
No baseline peer selected yet.
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Copy-ready — paste the snippet to get started.
Install command
Not provided
Config snippet
Provided
Copy snippet
Provided
Prerequisites
6 to clear
Platforms
1 listed
Difficulty
4/100
Adoption plan
Current risk score 16/100. Use staged verification before broader rollout.
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Confirm metadata review state
Listing has review metadata.
Verify install payload
Install/config payload exists and can be inspected.
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Review privacy notesRequired
Privacy notes are present.
Verify package integrity metadata
No package verification/checksum metadata.
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Required evidence gates are covered (5/6 signals complete).
Source repository/provenance is listed.
Required in this preset
Review metadata is present.
Required in this preset
Safety notes are present.
Required in this preset
Privacy notes are present.
Optional in this preset
Package integrity metadata is missing.
Optional in this preset
Install payload is available.
Required in this preset
Required evidence gates are covered for this preset.
Decision timeline
5/6 steps complete with no blocking gaps for this preset.
triage
Source/provenance metadata is available.
triage
Review metadata is available.
verify
Safety notes are available.
verify
Privacy notes are available.
verify
Package integrity metadata is missing.
rollout
Install payload is available.
No required blockers for this timeline preset.
Prerequisite readiness
6 prerequisites to line up before setup.
Safety & privacy surface
1 safety and 1 privacy notes across 1 risk area. Review closely: credentials & tokens.
#!/usr/bin/env bash
# Session Timer Statusline for Claude Code
# Tracks session duration and productivity metrics
# Read JSON from stdin
read -r input
# Extract session data
model=$(echo "$input" | jq -r '.model // "unknown"' | sed 's/claude-//')
tokens=$(echo "$input" | jq -r '.session.totalTokens // 0')
cost=$(echo "$input" | jq -r '.session.estimatedCost // 0' | awk '{printf "%.3f", $0}')
session_start=$(echo "$input" | jq -r '.session.startTime // ""')
# Calculate session duration
if [ -n "$session_start" ]; then
start_epoch=$(date -j -f "%Y-%m-%dT%H:%M:%S" "${session_start%.*}" "+%s" 2>/dev/null || echo "0")
current_epoch=$(date +%s)
duration=$((current_epoch - start_epoch))
# Format duration as HH:MM:SS
hours=$((duration / 3600))
minutes=$(((duration % 3600) / 60))
seconds=$((duration % 60))
formatted_time=$(printf "%02d:%02d:%02d" $hours $minutes $seconds)
# Calculate tokens per minute
if [ $duration -gt 0 ]; then
tokens_per_min=$((tokens * 60 / duration))
# Productivity rating
if [ $tokens_per_min -gt 500 ]; then
prod_color="\033[32m" # Green - high productivity
prod_indicator="🔥"
elif [ $tokens_per_min -gt 200 ]; then
prod_color="\033[33m" # Yellow - medium productivity
prod_indicator="⚡"
else
prod_color="\033[36m" # Cyan - normal
prod_indicator="💭"
fi
else
tokens_per_min=0
prod_color="\033[36m"
prod_indicator="💭"
fi
# Calculate cost per hour
if [ $duration -gt 0 ]; then
cost_per_hour=$(echo "$cost * 3600 / $duration" | bc -l | awk '{printf "%.2f", $0}')
else
cost_per_hour="0.00"
fi
else
formatted_time="00:00:00"
tokens_per_min=0
cost_per_hour="0.00"
prod_indicator="💭"
fi
# Build statusline
echo -e "\033[35m⏱ ${formatted_time}\033[0m │ \033[36m${model}\033[0m │ ${prod_color}${prod_indicator} ${tokens_per_min}/min\033[0m │ \033[33m\$${cost_per_hour}/hr\033[0m"{
"statusLine": {
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/statuslines/session-timer-statusline.sh",
"refreshInterval": 1000
}
}{
"statusLine": {
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/statuslines/session-timer-statusline.sh",
"refreshInterval": 1000
}
}
Extended version showing session start time and elapsed duration
#!/usr/bin/env bash
# Enhanced Session Timer with Start Time Display
export LC_NUMERIC=C
read -r input
model=$(echo "$input" | jq -r '.model.id // .model.display_name // "unknown"' | sed 's/claude-//')
tokens=$(echo "$input" | jq -r '.cost.total_lines_added // .session.totalTokens // 0')
cost=$(echo "$input" | jq -r '.cost.total_cost_usd // .session.estimatedCost // 0')
session_start=$(echo "$input" | jq -r '.session.startTime // ""')
# Detect OS for date command
if [[ "$OSTYPE" == "darwin"* ]]; then
DATE_CMD="date -j"
DATE_FORMAT="-f"
else
DATE_CMD="date"
DATE_FORMAT="-d"
fi
# Calculate session duration
if [ -n "$session_start" ]; then
start_clean=$(echo "$session_start" | sed 's/\.\{0,1\}[0-9]\{0,3\}Z\{0,1\}$//' | sed 's/T/ /')
if [[ "$OSTYPE" == "darwin"* ]]; then
start_epoch=$(date -j -f "%Y-%m-%d %H:%M:%S" "$start_clean" "+%s" 2>/dev/null || echo "0")
start_formatted=$(date -j -f "%Y-%m-%d %H:%M:%S" "$start_clean" "+%H:%M" 2>/dev/null || echo "")
else
start_epoch=$(date -d "$start_clean" "+%s" 2>/dev/null || echo "0")
start_formatted=$(date -d "$start_clean" "+%H:%M" 2>/dev/null || echo "")
fi
current_epoch=$(date +%s 2>/dev/null || echo "0")
if [ "$start_epoch" != "0" ] && [ "$current_epoch" != "0" ]; then
duration=$((current_epoch - start_epoch))
if [ $duration -lt 0 ]; then
duration=0
fi
hours=$((duration / 3600))
minutes=$(((duration % 3600) / 60))
seconds=$((duration % 60))
formatted_time=$(printf "%02d:%02d:%02d" $hours $minutes $seconds)
if [ $duration -gt 0 ]; then
tokens_per_min=$((tokens * 60 / duration))
if [ $tokens_per_min -gt 500 ]; then
prod_color="\033[32m"
prod_indicator="🔥"
elif [ $tokens_per_min -gt 200 ]; then
prod_color="\033[33m"
prod_indicator="⚡"
else
prod_color="\033[36m"
prod_indicator="💭"
fi
else
tokens_per_min=0
prod_color="\033[36m"
prod_indicator="💭"
fi
if command -v bc > /dev/null 2>&1 && [ $duration -gt 0 ]; then
cost_per_hour=$(echo "scale=2; $cost * 3600 / $duration" | bc -l 2>/dev/null || echo "0.00")
elif command -v awk > /dev/null 2>&1 && [ $duration -gt 0 ]; then
cost_per_hour=$(awk "BEGIN {printf \"%.2f\", $cost * 3600 / $duration}" 2>/dev/null || echo "0.00")
else
cost_per_hour="0.00"
fi
else
formatted_time="00:00:00"
tokens_per_min=0
cost_per_hour="0.00"
prod_indicator="💭"
prod_color="\033[36m"
start_formatted=""
fi
else
formatted_time="00:00:00"
tokens_per_min=0
cost_per_hour="0.00"
prod_indicator="💭"
prod_color="\033[36m"
start_formatted=""
fi
RESET="\033[0m"
# Build statusline with start time
if [ -n "$start_formatted" ]; then
echo -e "\033[35m⏱ ${formatted_time}${RESET} (start: ${start_formatted}) │ \033[36m${model}${RESET} │ ${prod_color}${prod_indicator} ${tokens_per_min}/min${RESET} │ \033[33m\$${cost_per_hour}/hr${RESET}"
else
echo -e "\033[35m⏱ ${formatted_time}${RESET} │ \033[36m${model}${RESET} │ ${prod_color}${prod_indicator} ${tokens_per_min}/min${RESET} │ \033[33m\$${cost_per_hour}/hr${RESET}"
fi
Version with Pomodoro technique support (25-minute work intervals)
#!/usr/bin/env bash
# Session Timer with Pomodoro Alerts
export LC_NUMERIC=C
read -r input
model=$(echo "$input" | jq -r '.model.id // .model.display_name // "unknown"' | sed 's/claude-//')
tokens=$(echo "$input" | jq -r '.cost.total_lines_added // .session.totalTokens // 0')
cost=$(echo "$input" | jq -r '.cost.total_cost_usd // .session.estimatedCost // 0')
session_start=$(echo "$input" | jq -r '.session.startTime // ""')
# Pomodoro interval (25 minutes = 1500 seconds)
POMODORO_INTERVAL=${POMODORO_INTERVAL:-1500}
# Detect OS for date command
if [[ "$OSTYPE" == "darwin"* ]]; then
DATE_CMD="date -j"
else
DATE_CMD="date"
fi
# Calculate session duration
if [ -n "$session_start" ]; then
start_clean=$(echo "$session_start" | sed 's/\.\{0,1\}[0-9]\{0,3\}Z\{0,1\}$//' | sed 's/T/ /')
if [[ "$OSTYPE" == "darwin"* ]]; then
start_epoch=$(date -j -f "%Y-%m-%d %H:%M:%S" "$start_clean" "+%s" 2>/dev/null || echo "0")
else
start_epoch=$(date -d "$start_clean" "+%s" 2>/dev/null || echo "0")
fi
current_epoch=$(date +%s 2>/dev/null || echo "0")
if [ "$start_epoch" != "0" ] && [ "$current_epoch" != "0" ]; then
duration=$((current_epoch - start_epoch))
if [ $duration -lt 0 ]; then
duration=0
fi
# Check Pomodoro interval
pomodoro_count=$((duration / POMODORO_INTERVAL))
pomodoro_remaining=$((POMODORO_INTERVAL - (duration % POMODORO_INTERVAL)))
hours=$((duration / 3600))
minutes=$(((duration % 3600) / 60))
seconds=$((duration % 60))
formatted_time=$(printf "%02d:%02d:%02d" $hours $minutes $seconds)
if [ $duration -gt 0 ]; then
tokens_per_min=$((tokens * 60 / duration))
if [ $tokens_per_min -gt 500 ]; then
prod_color="\033[32m"
prod_indicator="🔥"
elif [ $tokens_per_min -gt 200 ]; then
prod_color="\033[33m"
prod_indicator="⚡"
else
prod_color="\033[36m"
prod_indicator="💭"
fi
else
tokens_per_min=0
prod_color="\033[36m"
prod_indicator="💭"
fi
if command -v bc > /dev/null 2>&1 && [ $duration -gt 0 ]; then
cost_per_hour=$(echo "scale=2; $cost * 3600 / $duration" | bc -l 2>/dev/null || echo "0.00")
elif command -v awk > /dev/null 2>&1 && [ $duration -gt 0 ]; then
cost_per_hour=$(awk "BEGIN {printf \"%.2f\", $cost * 3600 / $duration}" 2>/dev/null || echo "0.00")
else
cost_per_hour="0.00"
fi
# Pomodoro alert
if [ $pomodoro_remaining -le 60 ] && [ $pomodoro_remaining -gt 0 ]; then
pomodoro_alert="🍅 ${pomodoro_remaining}s"
pomodoro_color="\033[33m"
elif [ $pomodoro_count -gt 0 ]; then
pomodoro_alert="🍅 +${pomodoro_count}"
pomodoro_color="\033[32m"
else
pomodoro_alert=""
pomodoro_color=""
fi
else
formatted_time="00:00:00"
tokens_per_min=0
cost_per_hour="0.00"
prod_indicator="💭"
prod_color="\033[36m"
pomodoro_alert=""
pomodoro_color=""
fi
else
formatted_time="00:00:00"
tokens_per_min=0
cost_per_hour="0.00"
prod_indicator="💭"
prod_color="\033[36m"
pomodoro_alert=""
pomodoro_color=""
fi
RESET="\033[0m"
# Build statusline with Pomodoro alert
if [ -n "$pomodoro_alert" ]; then
echo -e "\033[35m⏱ ${formatted_time}${RESET} │ ${pomodoro_color}${pomodoro_alert}${RESET} │ \033[36m${model}${RESET} │ ${prod_color}${prod_indicator} ${tokens_per_min}/min${RESET} │ \033[33m\$${cost_per_hour}/hr${RESET}"
else
echo -e "\033[35m⏱ ${formatted_time}${RESET} │ \033[36m${model}${RESET} │ ${prod_color}${prod_indicator} ${tokens_per_min}/min${RESET} │ \033[33m\$${cost_per_hour}/hr${RESET}"
fi
Complete setup script with OS detection and date command verification
#!/bin/bash
# Installation script for Session Timer Statusline
# Check for jq (required for JSON parsing)
if ! command -v jq &> /dev/null; then
echo "Installing jq for JSON parsing..."
if [[ "$OSTYPE" == "darwin"* ]]; then
brew install jq
elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
sudo apt-get install -y jq || sudo yum install -y jq
else
echo "Please install jq manually: https://stedolan.github.io/jq/"
fi
fi
# Check for bc (optional, for cost calculations)
if ! command -v bc &> /dev/null; then
echo "Installing bc calculator (optional, for cost calculations)..."
if [[ "$OSTYPE" == "darwin"* ]]; then
brew install bc
elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
sudo apt-get install -y bc || sudo yum install -y bc
else
echo "Note: bc is optional - script will use awk as fallback"
fi
fi
# Check for awk (usually pre-installed)
if ! command -v awk &> /dev/null; then
echo "Warning: awk command not found - cost calculations may not work"
echo "Install awk: macOS (pre-installed), Linux (sudo apt-get install gawk or sudo yum install gawk)"
else
echo "awk command available"
fi
# Test date command for OS compatibility
if [[ "$OSTYPE" == "darwin"* ]]; then
if date -j -f "%Y-%m-%d %H:%M:%S" "2024-01-01 12:00:00" "+%s" &> /dev/null; then
echo "macOS date command working: $(date -j -f '%Y-%m-%d %H:%M:%S' '2024-01-01 12:00:00' '+%s')"
else
echo "Warning: macOS date command test failed"
fi
else
if date -d "2024-01-01 12:00:00" "+%s" &> /dev/null; then
echo "Linux date command working: $(date -d '2024-01-01 12:00:00' '+%s')"
else
echo "Warning: Linux date command test failed"
fi
fi
# Test bc calculator (if available)
if command -v bc &> /dev/null; then
if echo "scale=2; 0.05 * 3600 / 1800" | bc -l 2>/dev/null | grep -q "0.10"; then
echo "bc calculator working: $(echo 'scale=2; 0.05 * 3600 / 1800' | bc -l)"
else
echo "Warning: bc calculator test failed"
fi
fi
# Test awk for cost calculation
if command -v awk > /dev/null 2>&1; then
test_cost=$(awk "BEGIN {printf \"%.2f\", 0.05 * 3600 / 1800}" 2>/dev/null)
if [ "$test_cost" = "0.10" ]; then
echo "awk cost calculation working: $test_cost"
else
echo "Warning: awk cost calculation test failed"
fi
fi
# Test emoji support
if echo -e '⏱ 🔥 ⚡ 💭 🍅' &> /dev/null; then
echo "Emoji characters supported: ⏱ 🔥 ⚡ 💭 🍅"
else
echo "Warning: Emoji characters may not display correctly"
fi
# Create statuslines directory
mkdir -p .claude/statuslines
cat > .claude/statuslines/session-timer-statusline.sh << 'SCRIPT_EOF'
#!/usr/bin/env bash
# Session Timer Statusline for Claude Code
# Tracks session duration and productivity metrics
export LC_NUMERIC=C
read -r input
model=$(echo "$input" | jq -r '.model.id // .model.display_name // "unknown"' | sed 's/claude-//')
tokens=$(echo "$input" | jq -r '.cost.total_lines_added // .session.totalTokens // 0')
cost=$(echo "$input" | jq -r '.cost.total_cost_usd // .session.estimatedCost // 0')
session_start=$(echo "$input" | jq -r '.session.startTime // ""')
if [[ "$OSTYPE" == "darwin"* ]]; then
DATE_CMD="date -j"
else
DATE_CMD="date"
fi
if [ -n "$session_start" ]; then
start_clean=$(echo "$session_start" | sed 's/\.\{0,1\}[0-9]\{0,3\}Z\{0,1\}$//' | sed 's/T/ /')
if [[ "$OSTYPE" == "darwin"* ]]; then
start_epoch=$(date -j -f "%Y-%m-%d %H:%M:%S" "$start_clean" "+%s" 2>/dev/null || echo "0")
else
start_epoch=$(date -d "$start_clean" "+%s" 2>/dev/null || echo "0")
fi
current_epoch=$(date +%s 2>/dev/null || echo "0")
if [ "$start_epoch" != "0" ] && [ "$current_epoch" != "0" ]; then
duration=$((current_epoch - start_epoch))
if [ $duration -lt 0 ]; then
duration=0
fi
hours=$((duration / 3600))
minutes=$(((duration % 3600) / 60))
seconds=$((duration % 60))
formatted_time=$(printf "%02d:%02d:%02d" $hours $minutes $seconds)
if [ $duration -gt 0 ]; then
tokens_per_min=$((tokens * 60 / duration))
if [ $tokens_per_min -gt 500 ]; then
prod_color="\033[32m"
prod_indicator="🔥"
elif [ $tokens_per_min -gt 200 ]; then
prod_color="\033[33m"
prod_indicator="⚡"
else
prod_color="\033[36m"
prod_indicator="💭"
fi
else
tokens_per_min=0
prod_color="\033[36m"
prod_indicator="💭"
fi
if command -v bc > /dev/null 2>&1 && [ $duration -gt 0 ]; then
cost_per_hour=$(echo "scale=2; $cost * 3600 / $duration" | bc -l 2>/dev/null || echo "0.00")
elif command -v awk > /dev/null 2>&1 && [ $duration -gt 0 ]; then
cost_per_hour=$(awk "BEGIN {printf \"%.2f\", $cost * 3600 / $duration}" 2>/dev/null || echo "0.00")
else
cost_per_hour="0.00"
fi
else
formatted_time="00:00:00"
tokens_per_min=0
cost_per_hour="0.00"
prod_indicator="💭"
prod_color="\033[36m"
fi
else
formatted_time="00:00:00"
tokens_per_min=0
cost_per_hour="0.00"
prod_indicator="💭"
prod_color="\033[36m"
fi
RESET="\033[0m"
echo -e "\033[35m⏱ ${formatted_time}${RESET} │ \033[36m${model}${RESET} │ ${prod_color}${prod_indicator} ${tokens_per_min}/min${RESET} │ \033[33m\$${cost_per_hour}/hr${RESET}"
SCRIPT_EOF
chmod +x .claude/statuslines/session-timer-statusline.sh
# Add to settings.json
if [ ! -f .claude/settings.json ]; then
echo '{"statusLine":{"type":"command","command":"$CLAUDE_PROJECT_DIR/.claude/statuslines/session-timer-statusline.sh","refreshInterval":1000}}' > .claude/settings.json
else
jq '.statusLine = {"type":"command","command":"$CLAUDE_PROJECT_DIR/.claude/statuslines/session-timer-statusline.sh","refreshInterval":1000}' .claude/settings.json > .claude/settings.json.tmp
mv .claude/settings.json.tmp .claude/settings.json
fi
echo "Session Timer Statusline installed successfully!"
echo "Note: Ensure LC_NUMERIC=C is set for correct decimal formatting"
echo "Note: Script detects OS automatically (macOS uses 'date -j', Linux uses 'date -d')"
echo "Test timer: Verify session.startTime is provided by Claude Code in JSON input"
Ensure Claude Code is providing session.startTime in JSON. Check with: echo '$input' | jq '.session.startTime'. May require Claude Code update. Verify date command works: macOS (date -j -f '%Y-%m-%d %H:%M:%S' '2024-01-01 12:00:00' '+%s'), Linux (date -d '2024-01-01 12:00:00' '+%s'). Test timestamp parsing: start_clean=$(echo '$session_start' | sed 's/.{0,1}[0-9]{0,3}Z{0,1}$//' | sed 's/T/ /'). Check epoch calculation: current_epoch=$(date +%s) (should return current Unix timestamp).
macOS uses 'date -j -f', Linux uses 'date -d'. Script detects OS automatically using OSTYPE. For macOS: date -j -f '%Y-%m-%d %H:%M:%S' '2024-01-01 12:00:00' '+%s'. For Linux: date -d '2024-01-01 12:00:00' '+%s'. Verify OS detection: echo $OSTYPE (should be 'darwin*' for macOS, 'linux-gnu*' for Linux). Check timestamp format: session.startTime should be ISO 8601 (e.g., '2024-01-01T12:00:00' or '2024-01-01T12:00:00.123Z'). Script cleans timestamp: removes milliseconds and 'Z' suffix, replaces 'T' with space.
Install bc calculator: macOS (brew install bc), Linux (sudo apt-get install bc or sudo yum install bc). Verify installation: command -v bc (should return path). Test bc: echo 'scale=2; 0.05 * 3600 / 1800' | bc -l (should return 0.10). Script has awk fallback: If bc unavailable, script uses awk for cost per hour calculation. Verify awk: command -v awk (should return path). Check both: Script tries bc first, then awk as fallback. Both methods should produce same result.
This is normal at session start. Metric stabilizes after 2-3 minutes of usage. Very high values indicate batch processing. Calculation: tokensper_min = tokens * 60 / duration. If duration is very small (< 60 seconds), tokensper_min can be very high. Wait for session to run longer (2-3 minutes) for accurate rate. Check tokens value: echo '$input' | jq '.cost.total_lines_added' (should return number). Check duration: echo $duration (should be seconds since session start). Verify calculation: tokens_per_min=$((tokens * 60 / duration)).
Check cost value: echo '$input' | jq '.cost.total_cost_usd' (should return decimal like 0.05). If zero, check alternative field: echo '$input' | jq '.session.estimatedCost'. Verify duration is greater than 0: echo $duration (should be > 0). Check calculation: cost*per_hour = cost * 3600 / duration. Test with bc: echo 'scale=2; 0.05 _ 3600 / 1800' | bc -l (should return 0.10). Test with awk: awk 'BEGIN {printf "%.2f", 0.05 * 3600 / 1800}' (should return 0.10). If both fail, check that bc or awk is installed.
Verify tokens_per_min calculation: echo $tokens_per_min (should be number). Check thresholds: > 500 (🔥 green), > 200 (⚡ yellow), else (💭 cyan). Test comparison: if [ 600 -gt 500 ]; then echo "High productivity"; fi (should output). Verify color codes: Green (\033[32m), Yellow (\033[33m), Cyan (\033[36m). Test color: echo -e '\033[32mGreen\033[0m' (should display green text). Check RESET code: echo -e '\033[0m' (should reset colors). If colors not working, terminal may not support ANSI colors.
Check epoch calculation: start_epoch and current_epoch should be valid Unix timestamps. Verify: date +%s (should return current timestamp). Check timestamp parsing: start_clean should be valid date string. Test: if [["$OSTYPE" == "darwin"*]]; then date -j -f '%Y-%m-%d %H:%M:%S' '2024-01-01 12:00:00' '+%s'; else date -d '2024-01-01 12:00:00' '+%s'; fi. Script has protection: if [ $duration -lt 0 ]; then duration=0; fi. If still negative, check system clock: date (should show correct time). Verify session.startTime is not in future: Compare with current time.
Check model extraction: echo '$input' | jq '.model.id' (should return model ID like 'claude-opus-4-1'). Check alternative: echo '$input' | jq '.model.display_name' (should return display name like 'Opus'). Script uses: model=$(echo '$input' | jq -r '.model.id // .model.display_name // "unknown"'). Verify sed replacement: echo 'claude-opus-4-1' | sed 's/claude-//' (should return 'opus-4-1'). If model is 'unknown', check JSON structure: echo '$input' | jq .model (should show model object with id or display_name).
Session Timer side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Time-tracking statusline showing elapsed session duration, tokens per minute rate, and estimated cost with productivity metrics Open dossier | Claude 5-hour conversation block tracker with visual countdown, expiration warnings, and color-coded indicators to prevent unexpected session terminations. Open dossier | Real-time AI cost tracking statusline with per-session spend analytics, model pricing, and budget alerts Open dossier | Multi-provider AI performance dashboard with context occupancy tracking, truncation warnings, TTFT latency, tokens/min rate, and model comparison metrics. Open dossier |
|---|---|---|---|---|
| Next steps | ||||
| Trust | ||||
| Review status | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed |
| Package trust | Package not verified | Package not verified | Package not verified | Package not verified |
| Source provenance | Source-backed | Source-backed | Source-backed | Source-backed |
| Submitter | — | — | — | — |
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | — | — | — | — |
| Category | statuslines | statuslines | statuslines | statuslines |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | JSONbored | JSONbored | JSONbored | JSONbored |
| Added | 2025-10-01 | 2025-10-23 | 2025-10-16 | 2025-10-23 |
| Platforms | Claude Code | Claude Code | Claude Code | Claude Code |
| Source repo | — | — | — | — |
| Safety notes | ✓Runs as a Claude Code statusline command on every refresh and depends on the local shell environment; a failure only affects status rendering, not your session. | ✓Runs as a Claude Code statusline command on every refresh and depends on the local shell environment; a failure only affects status rendering, not your session. | ✓Runs as a Claude Code statusline command on every refresh and depends on the local shell environment; a failure only affects status rendering, not your session. | ✓Runs as a Claude Code statusline command on every refresh and depends on the local shell environment; a failure only affects status rendering, not your session. |
| Privacy notes | ✓Reads the Claude Code statusline JSON from stdin (model, workspace path, token usage) and renders it in the local terminal; it does not send data off-machine. | ✓Reads the Claude Code statusline JSON from stdin (model, workspace path, token usage) and renders it in the local terminal; it does not send data off-machine. | ✓Reads the Claude Code statusline JSON from stdin (model, token usage, and cost) and renders it in the local terminal; it does not send data off-machine. | ✓Reads the Claude Code statusline JSON from stdin (model, token usage, context occupancy) and renders it in the local terminal; it does not send data off-machine. |
| Prerequisites |
|
|
|
|
| Install | — | — | — | — |
| Config | | | | |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Source-backed guides for putting this to work.
Instrument LLM and agent apps with traces, metrics, logs, and redaction.
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.