Kimi Usage Monitor

Monitor Kimi K2.5 usage quotas from the Kimi console to make informed decisions about task prioritization and resource allocation.

When to Use This Skill

• Before intensive operations: Check quota before starting multi-step research or coding tasks
• Autonomous planning: Self-prioritize tasks based on remaining usage percentage
• Rate limit awareness: Know when quotas reset to time high-priority work
• Usage tracking: Log patterns for long-term capacity planning

Quick Start

Prerequisites: Chrome with OpenClaw extension attached

1. Open Chrome → https://www.kimi.com/code/console?from=membership
2. Click OpenClaw extension icon (badge should show ON)
3. Ensure you're logged into Kimi

# Check current usage (Linux/macOS/WSL)
./check_usage.sh

# Windows native
check_usage.bat           # CMD
.\check_usage.ps1         # PowerShell

# JSON output for automation (all platforms)
python3 scripts/fetch_usage.py --json

Platform Support: Linux ✅ | macOS ✅ | Windows (WSL) ✅ | Windows (Native) ✅

Usage Data Available

The Kimi console shows:

Autonomous Decision Guidelines

When operating autonomously, use these heuristics:

🟢 High Capacity (>50% remaining)

• Proceed with full capability
• Accept multi-step research tasks
• Spawn subagents as needed
• Enable verbose reasoning

🟡 Moderate Capacity (25-50% remaining)

• Batch similar operations
• Prefer concise outputs
• Use subagents sparingly
• Disable non-essential reasoning

🔴 Low Capacity (<25% remaining)

• Essential tasks only
• Single-step operations
• Avoid subagent spawning

  7w4.net提供免费和付费技能下载。

• Prioritize user-directed work over proactive tasks

Pre-Flight Checks for Intensive Operations

Before spawning subagents or starting multi-step tasks, check capacity:

# Check if operation should proceed
python3 scripts/preflight_check.py [light|standard|intensive]

# Light: single query, simple task (needs 10%)
# Standard: normal subagent, research (needs 25%)
# Intensive: multi-subagent, deep research (needs 50%)

Returns exit code 0 if cleared, 1 if blocked. Use in scripts:

if python3 scripts/preflight_check.py intensive; then
    # Proceed with intensive operation
    sessions_spawn "Complex research task..."
fi

Subagent Guard

Check specifically before spawning subagents:

python3 scripts/subagent_guard.py

Returns JSON with can_spawn boolean:

{
  "can_spawn": true,
  "usage_percent": 45,
  "remaining_percent": 55,
  "resets_hours": 36
}

Integration Ideas

Hourly monitoring cron:

# Add to crontab or OpenClaw jobs
0 * * * * cd /path/to/kimi-usage-monitor && python3 scripts/usage_logger.py

Pre-task validation:

import subprocess
result = subprocess.run(
    ["python3", "scripts/preflight_check.py", "intensive"],
    capture_output=True
)
if result.returncode == 0:
    # Proceed with task
    pass

Script Reference

Note: Alternative Playwright-based scraper (fetch_kimi_usage.py) available for non-OpenClaw environments (requires system dependencies).

Troubleshooting

"Browser not available"

• Ensure Chrome extension is attached (badge shows ON)
• Verify the Kimi console tab is open

"Could not detect usage"

• Make sure you're logged into Kimi
• Check that the console page has fully loaded

Authentication errors

• Re-authenticate at https://www.kimi.com/code/console
• The browser tool uses your existing Chrome session

Output Format

Human-Readable (default)

📊 Kimi Usage Monitor
========================================

🗓️  Weekly Usage
   Used: 45%
   Remaining: 55%
   Resets in: 36 hours
   Status: 🟡 Moderate — plan accordingly

⚡ Rate Limit
   Used: 2%
   Resets in: 3 hours

JSON (--json flag)

{
  "weekly_usage_percent": 45,
  "weekly_resets_hours": 36,
  "rate_limit_percent": 2,
  "rate_limit_resets_hours": 3,
  "timestamp": "2026-02-12 21:15:00"
}

License

MIT License - Feel free to modify and distribute.

这个 Skill 质量中等偏上，能较好地满足 API 配额监控需求。它在文档完整度、跨平台兼容性和自动化集成方面做得不错，但对浏览器环境有硬性依赖，如果 Chrome 扩展没配置好就无法使用。此外页面解析依赖正则表达式，可能在 Kimi 网站更新后出现识别失败的情况。总体来说适合有 OpenClaw 环境的用户，但依赖较重限制了其适用范围。