AI Vampire Guard — AI skill for Claude Code
Monitor your Claude Code burn rate.
How to install AI Vampire Guard
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open cbruyndoncx/ai-vampire-guard and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What AI Vampire Guard does
Monitor your Claude Code burn rate. Prevent AI-amplified burnout. Single-file Python script with SVG gauge, trend sparkline, and automatic hooks.
Alternatives in AI
- Oh My Claudecode — 32 specialized agents and 7 execution modes for Claude Code, with smart model routing and automatic paralleliz 10.9k ★
- Architecture Diagram Generator — Generate beautiful dark-themed system architecture diagrams as standalone HTML/SVG files 7k ★
- Open Researcher — 🔥 Visual AI research assistant that displays real-time thinking, provides split-view analysis, and automatic 634 ★
README
AI Vampire Guard
**Monitor your Claude Code burn rate. Prevent AI-amplified burnout.**

Steve Yegge coined the term "AI Vampire" — when AI tools amplify your productivity so much that you burn through your energy without realizing it. You finish the day having shipped more than ever, but you're completely drained.
AI Vampire Guard makes your cognitive load visible. It reads your Claude Code session logs and produces a daily burn-rate score from 0 to 100, visualized as a gauge with three zones:
| Zone | Score | What It Means |
|---|---|---|
| GREEN | 0–39 | Sustainable pace |
| AMBER | 40–69 | Watch your energy |
| RED | 70–100 | Overdrive — take a break |
The score isn't just token count. It weighs six factors: output volume, tool call intensity, session depth, parallel sessions, task complexity, and your personal cognitive engagement.
Requirements
- Python 3.11+ (
python3 --version) - uv — the fast Python package manager (
curl -LsSf https://astral.sh/uv/install.sh | sh) - Claude Code — reads session logs from
~/.claude/projects/
No other dependencies. The script uses PEP 723 inline metadata — `uv run` installs `click` and `rich` automatically on first run.
Install (60 seconds)
Option A: Automatic Install (Recommended)
Run the installer — it downloads the script and config from GitHub, places them in `~/.claude/scripts/`, and configures Claude Code hooks:
curl -sL https://raw.githubusercontent.com/cbruyndoncx/ai-vampire-guard/main/install_vampire_guard.py \
| uv run -
Preview first with `--dry-run`, or remove later with `--uninstall`:
uv run ~/.claude/scripts/install_vampire_guard.py --dry-run
uv run ~/.claude/scripts/install_vampire_guard.py --uninstall
Option B: Manual Install
Download the script and config yourself, then configure hooks manually (see [Automatic Monitoring](#automatic-monitoring-hooks) below):
Related Skills
Safety Guard
Enforces Law 3 (One Thing at a Time) of the 7 Laws of AI Agent Discipline by scoping edits to a directory and
Gauge Calibrate
Refresh the tracked model's (default Fable) weekly % estimate from claude.ai/settings/usage -- the one number
Usage
macOS menu bar & Windows tray app pinning Claude Code, Codex & Antigravity quota, burn rate, and cost to your
Burn O Meter
See what your AI coding agents really cost — tokens, spend, cache efficiency and rate limits. Works with Claud
ClaudeUsageMonitor
Free always-on-top desktop widget for Windows and macOS that shows your Claude usage limits live - 5-hour sess
Claude Code Experience Kit
Harness-level customizations for Claude Code: give the agent live sight of its own context fill, quota window,
Related Agents
Release Auditor
Pre-release audit for a single plugin in the monorepo — takes a plugin slug and cross-references plugin.json v
Script Reviewer
Senior scripting reviewer (2026) auditing a single kit script — Python, bash, or Node ESM (.mjs). Reviews invo
LLM FinOps Architect
LLM FinOps Architect specializing in model-tier routing, cost-envelope governance, burn-rate monitoring, per-p