Best use case
ohmytoken is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. **Your AI spending, visualized as pixel art. In real-time.**
**Your AI spending, visualized as pixel art. In real-time.**
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "ohmytoken" skill to help with this workflow task. Context: **Your AI spending, visualized as pixel art. In real-time.**
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ohmytoken/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ohmytoken Compares
| Feature / Agent | ohmytoken | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
**Your AI spending, visualized as pixel art. In real-time.**
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# ohmytoken **Your AI spending, visualized as pixel art. In real-time.** Ever wondered where all your tokens go? ohmytoken turns your invisible LLM spending into a mesmerizing pixel bead board that fills up as you chat, code, and create with AI.  ## Why You'll Love It **It's weirdly addictive.** Each model gets its own color — Claude is coral, GPT is green, Gemini is blue. Watch your board fill up in spiral patterns, rain down like Tetris, or bloom from the center. Pick a cat-shaped board, a heart, a Mario mushroom, or a star. Your token art is unique to you. **It's social.** Share your board as a pixel art card with a QR code. See how you rank against other developers. Unlock achievements like "Night Owl" (coding at 2AM) or "Millionaire" (1M tokens burned). Browse the gallery of everyone's boards. ## Setup: 3 Steps, 2 Minutes ### Step 1: Get Your API Key 1. Go to [ohmytoken.dev](https://ohmytoken.dev) 2. Click **"GITHUB"** or **"GOOGLE"** to sign in (one click, no passwords) 3. You'll see a **Welcome** screen with your API Key — it looks like `omt_f9c399...` 4. Click **COPY** to copy it ### Step 2: Install the Skill Run this in your terminal: ```bash openclaw skill install @0x5446/ohmytoken ``` ### Step 3: Add Your API Key Set the environment variable (recommended — won't leak via git): ```bash export OHMYTOKEN_API_KEY="omt_paste_your_key_here" ``` Add this to your `~/.zshrc` or `~/.bashrc`, then `source ~/.zshrc`. **Done!** Open [ohmytoken.dev](https://ohmytoken.dev) and watch the beads drop as you use AI. ## Privacy & Security **We only collect token counts. Nothing else.** | What we send | What we NEVER send | |-------------|-------------------| | Model name (e.g. "gpt-4o") | Your prompts | | Prompt token count (integer) | Your responses | | Completion token count (integer) | Your API keys to providers | | | Your files, code, or data | | | Any conversation content | The tracker sends exactly **3 fields per request**: `model`, `prompt_tokens`, `completion_tokens`. That's it. Your prompts, responses, files, and code **never leave your machine**. **Note**: Like any HTTP request, your IP address is visible to the server during the connection. We do not log or store IP addresses. The `OHMYTOKEN_API_KEY` environment variable is the recommended way to configure your key — it stays out of version control and won't leak. The source code is fully open: [github.com/0x5446/ohmytoken-oss](https://github.com/0x5446/ohmytoken-oss) — audit it yourself. ## What You Get - **Real-time bead board** — tokens appear as colored pixels the moment you use them - **7 board shapes** — square, cat, heart, star, circle, diamond, mushroom - **7 fill animations** — sequential, spiral, center-out, random, snake, diagonal, rain - **4 time views** — today, this month, this year, all-time - **10 achievements** — from "First Burn" to "Millionaire" - **Leaderboards** — total tokens, efficiency, model diversity, night owl - **Share cards** — pixel art image + QR code + profile URL - **Embeddable badges** — SVG badge for your GitHub README - **Wrapped reports** — your personal token year-in-review ## Zero Friction - Works with every model OpenClaw supports - Runs silently in the background, never interrupts your workflow - Google/GitHub OAuth login, no new account to create - Completely free --- Questions? Issues? [github.com/0x5446/ohmytoken-oss/issues](https://github.com/0x5446/ohmytoken-oss/issues) Made with pixels and love. [ohmytoken.dev](https://ohmytoken.dev)
Related Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述