quota-tracker
Tracks API rate limits and quota status for Claude Code.
Install
mkdir -p .claude/skills/quota-tracker && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16184" && unzip -o skill.zip -d .claude/skills/quota-tracker && rm skill.zipInstalls to .claude/skills/quota-tracker
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Track Claude Code quota usage via Anthropic API rate limit headers. Shows 5h and 7d utilization, reset times, and quota status. Works with both subscription and API key auth.Key capabilities
- →Track Claude Code quota usage in real time.
- →Display 5-hour and 7-day utilization percentages.
- →Show reset times for 5-hour and 7-day quota windows.
- →Indicate current quota status (allowed or rejected).
- →Provide human-readable quota state.
- →Provide machine-readable quota state in JSON format.
How it works
A credential proxy intercepts Anthropic API rate limit headers from Claude Code responses and writes the quota state to a JSON file for real-time monitoring.
Inputs & outputs
When to use quota-tracker
- →Check remaining API quota
- →Monitor rate limit status
- →View quota reset times
About this skill
Quota Tracker
Monitor your Claude Code quota in real time by intercepting Anthropic API rate limit headers.
When to Use
- "How much quota do I have left?"
- "Am I close to the rate limit?"
- "When does my quota reset?"
- Before starting expensive tasks
How It Works
A credential proxy sits between Claude Code and the Anthropic API. It reads anthropic-ratelimit-unified-* headers from every API response and writes quota state to a JSON file.
Quick Check
# Read current quota state
cat quota-state.json
Output includes:
anthropic-ratelimit-unified-5h-utilization— % of 5-hour window usedanthropic-ratelimit-unified-7d-utilization— % of 7-day window usedanthropic-ratelimit-unified-5h-reset— when the 5h window resets (epoch)anthropic-ratelimit-unified-7d-reset— when the 7d window resets (epoch)anthropic-ratelimit-unified-status— "allowed" or "rejected"
Setup
1. Start the credential proxy
npx tsx "$SKILL_DIR/scripts/credential-proxy.ts"
This starts on port 7846 and reads OAuth credentials from macOS keychain.
2. Route Claude Code through the proxy
ANTHROPIC_BASE_URL=http://localhost:7846 claude ...
Or add to your voice agent's launchd plist:
<key>ANTHROPIC_BASE_URL</key>
<string>http://localhost:7846</string>
3. Read quota state
python3 "$SKILL_DIR/scripts/read-quota.py" # human readable
python3 "$SKILL_DIR/scripts/read-quota.py" --json # machine readable
python3 "$SKILL_DIR/scripts/read-quota.py" --gate # exit 1 if exhausted OR not routed
Requirements
- macOS (reads OAuth from keychain)
- Claude Code logged in (subscription or API key)
- Node.js with tsx
When not to use it
- →When the user is not using Claude Code.
- →When the user does not have macOS.
- →When the user does not have Node.js with tsx.
Prerequisites
Limitations
- →The skill requires macOS to read OAuth credentials from the keychain.
- →It requires Claude Code to be logged in.
- →It requires Node.js with tsx for the credential proxy.
How it compares
This skill provides real-time quota tracking by intercepting API headers, unlike checking usage through a separate dashboard.
Compared to similar skills
quota-tracker side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| quota-tracker (this skill) | 0 | 1mo | Review | Intermediate |
| agent-performance-monitor | 3 | 6mo | Review | Advanced |
| agent-performance-optimizer | 3 | 6mo | No flags | Advanced |
| coderabbit-observability | 1 | 1mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
agent-performance-monitor
ruvnet
Agent skill for performance-monitor - invoke with $agent-performance-monitor
agent-performance-optimizer
ruvnet
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer
coderabbit-observability
jeremylongshore
Set up comprehensive observability for CodeRabbit integrations with metrics, traces, and alerts. Use when implementing monitoring for CodeRabbit operations, setting up dashboards, or configuring alerting for CodeRabbit integration health. Trigger with phrases like "coderabbit monitoring", "coderabbit metrics", "coderabbit observability", "monitor coderabbit", "coderabbit alerts", "coderabbit tracing".
obs-alerts
shepard-system
Show active alerts and their resolution steps. Use this skill whenever the user asks about alerts, wants to know if anything is broken or firing, asks about Alertmanager state, mentions alert silences, or wants to troubleshoot a specific alert like OTelCollectorDown, LokiDown, HighSessionCost, or Se
mission-control-event-digest
MN755
Summarize recent Mission Control events without raw logs. Use when the user wants the last 5 minutes, last 15 minutes, since last interaction, or since orchestration start summarized in bridge-safe markdown.
yoyopod-logs
attmous
Tail YoYoPod runtime/service logs from Raspberry Pi