Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Token Price Alert

ASecurity

🚨 **Monitor session tokens and get alerts at 75%/90%/95%**

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentspythongobashgitapidocumentation

Works with

terminalapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill token-price-alert --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Token Price Alert?

Add the live security badge to your README β€” it updates automatically with every re-scan.

Security grade badge for Token Price Alert
[![Security: A β€” Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-token-price-alert/badge)](https://www.skillsdirectory.com/skills/rondoflow-token-price-alert)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: token-price-alert
description: "🚨 **Monitor session tokens and get alerts at 75%/90%/95%**"
category: "Finance & Crypto"
author: community
version: "1.2.0"
icon: coins
---

# Token Alert Skill

🚨 **Monitor session tokens and get alerts at 75%/90%/95%**

## Overview

The Token Alert Skill automatically monitors your Clawdbot session token usage and sends alerts when you approach limits. Never lose context mid-conversation again!

## Features

- βœ… **6-Level Threshold System** - Alerts at 25%, 50%, 75%, 90%, 95%, 100%
- βœ… **Material Design Progress Bar** - Box-style (β–°/β–±) with color gradients
- βœ… **Rich UI Dashboard** - Interactive HTML dashboard with animations
- βœ… **Session Status** - Shows current token usage on demand
- βœ… **Telegram Alerts** - Get notified before hitting limits
- βœ… **HEARTBEAT Integration** - Optional automated checks
- βœ… **Stateless** - No state file needed, calculates on-demand
- βœ… **Session Estimates** - Predicts remaining sessions (~50k avg)

## Usage

### Interactive Dashboard

Ask Grym:
- "Show token dashboard"
- "Open dashboard"

Or run directly:
```bash
python3 ~/clawd/skills/token-alert/scripts/show_dashboard.py
```

### Terminal Check

Ask Grym:
- "Wie viele Tokens habe ich noch ΓΌbrig?"
- "Check token status"
- "Token usage?"

Or run:
```bash
python3 ~/clawd/skills/token-alert/scripts/check.py
```

### Automatic Alerts

Grym will automatically alert you when:
- 🟑 **25%** - Low warning (~150k tokens left)
- 🟠 **50%** - Medium warning (~100k tokens left)
- πŸ”Ά **75%** - High warning (~50k tokens left)
- πŸ”΄ **90%** - Critical warning (~20k tokens left)
- 🚨 **95%** - Emergency! (<10k tokens left)

### Example Output

```
πŸ”Ά Token Alert: Achtung!

πŸ”Ά β–°β–°β–°β–°β–°β–°β–°β–°β–°β–°β–°β–°β–°β–°β–°β–°β–°β–°β–°β–±β–±β–±β–±β–±β–± 78.0%
156,000 / 200,000 Tokens verwendet

⚠️ Status: High Warning (Rot-Orange Zone)
πŸ’‘ Verbleibend: ~44k Tokens
⏰ GeschÀtzte Sessions: <1 Session

πŸ”§ Empfehlung:
   βœ… Wichtige Entscheidungen jetzt treffen
   βœ… Neue Session vorbereiten
   βœ… Token-sparend arbeiten
```

## Installation

```bash
# Via ClawdHub
clawdhub install token-alert

# Manual
cd ~/clawd/skills
git clone https://github.com/r00tid/clawdbot-token-alert token-alert
```

## Configuration

### HEARTBEAT Integration (Optional)

Add to `~/clawd/HEARTBEAT.md`:

```markdown
### Token Usage Check (tΓ€glich)
- [ ] `python3 ~/clawd/skills/token-alert/scripts/check.py`
- **Warning ab 70%:** "⚠️ Session bei XX% - Token-Sparend ab jetzt!"
```

## How It Works

1. Uses Clawdbot's `session_status` tool
2. Calculates percentage of token usage
3. Compares against thresholds (75%, 90%, 95%)
4. Sends Telegram alert if threshold crossed

## Technical Details

### Files

```
skills/token-alert/
β”œβ”€β”€ SKILL.md                    # This file
β”œβ”€β”€ README.md                   # GitHub documentation
β”œβ”€β”€ LICENSE                     # MIT License
β”œβ”€β”€ .clawdhub/
β”‚   └── manifest.json           # ClawdHub metadata
β”œβ”€β”€ assets/
β”‚   β”œβ”€β”€ dashboard-78-high.png   # Screenshot (High Warning)
β”‚   └── dashboard-96-emergency.png  # Screenshot (Emergency)
└── scripts/
    β”œβ”€β”€ check.py                # Token checker (Terminal)
    β”œβ”€β”€ dashboard.html          # Rich UI dashboard
    └── show_dashboard.py       # Dashboard launcher
```

### Dependencies

- Python 3.8+
- Clawdbot session_status tool
- Optional: Telegram channel configured

### Script API

```python
# scripts/check.py
def get_session_tokens():
    """Get current session token usage via session_status tool"""
    
def check_thresholds(percent):
    """Check if usage exceeds thresholds"""
    
def format_alert(used, limit, percent, level):
    """Format alert message for Telegram"""
```

## When to Use

- **Before long tasks** - Check if you have enough tokens
- **Mid-conversation** - Monitor usage during long sessions
- **Daily check** - Add to HEARTBEAT for automatic monitoring

## Limitations

- Only monitors session tokens (not Claude.ai API limits)
- Requires active Clawdbot session
- Alert frequency can be noisy if near threshold

## Future Enhancements

- [ ] Claude.ai API limits scraping (optional)
- [ ] Historical token usage tracking
- [ ] Weekly/monthly usage reports
- [ ] Integration with `token-router` skill

## Support

- GitHub Issues: https://github.com/r00tid/clawdbot-token-alert/issues
- ClawdHub: https://clawdhub.com/skills/token-alert
- Docs: https://docs.clawd.bot

## License

MIT License - See LICENSE file

---

Built with ❀️ by Grym πŸ₯œ

Attribution

rondoflowrondoflow
View sourceMore from rondoflow β†’
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants β€” handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents β†’