← 返回 Skills 市场
407
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install ohmytoken
功能描述
Visualize your AI token usage as real-time pixel art with customizable boards, animations, achievements, and social sharing powered by ohmytoken.
安全使用建议
This skill appears internally consistent, but note that the remote service (api.ohmytoken.dev) will see your model names, token counts, and your IP address and can attribute activity to the provided API key. If you care about linking usage to your identity, review the open-source repo at https://github.com/0x5446/ohmytoken-oss, check the service's privacy policy, and consider using a dedicated or limited-scoped API key. If you want extra assurance, audit the published source before installing or use a throwaway key.
功能分析
Type: OpenClaw Skill
Name: ohmytoken
Version: 2.0.3
The OpenClaw skill 'ohmytoken' is benign. Its `src/index.ts` code accurately reflects the stated purpose of tracking LLM token usage by sending only the model name, prompt tokens, and completion tokens to `https://api.ohmytoken.dev/api/v1/ingest`. The `claw.json` manifest correctly declares the necessary 'network' permission. All documentation (`SKILL.md`, `README.md`, `instructions.md`) is transparent about data collection, explicitly stating what is and is not sent, and provides no evidence of prompt injection attempts or instructions for the AI agent to perform unauthorized actions.
能力评估
Purpose & Capability
Name/description say it visualizes token usage; the skill requires a single OHMYTOKEN_API_KEY and its code posts model + token counts to api.ohmytoken.dev — this is proportionate and expected for the described feature.
Instruction Scope
SKILL.md and instructions.md explicitly instruct adding OHMYTOKEN_API_KEY and claim only three fields (model, prompt_tokens, completion_tokens) are sent. The runtime code (src/index.ts) sends exactly those fields and nothing else; it does not read other files or env vars.
Install Mechanism
No install spec is present (instruction-only). There is a small code file included but nothing that downloads or executes external installers. No high-risk install URLs or archive extraction.
Credentials
Only OHMYTOKEN_API_KEY is required (declared in claw.json and SKILL.md). That single API key is appropriate for authenticating usage reports; no unrelated credentials or broad environment access are requested.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or system-wide privileges. It uses the normal onLLMResponse hook and does not modify other skills or agent configuration.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install ohmytoken - 安装完成后，直接呼叫该 Skill 的名称或使用
/ohmytoken触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v2.0.3
Recommend env var over openclaw.json for API key storage to prevent accidental leakage
v2.0.2
Add requiredEnv declaration for OHMYTOKEN_API_KEY in claw.json
v2.0.1
Fix security scan findings: remove incorrect timestamp/IP claims, document OHMYTOKEN_API_KEY env var
v2.0.0
Version 2.0.0: Privacy-first LLM token tracking with pixel art visualization. Tracks model name + input/output tokens only. Zero prompts, zero code, zero content ever leaves your machine.
元数据
常见问题
ohmytoken 是什么？
Visualize your AI token usage as real-time pixel art with customizable boards, animations, achievements, and social sharing powered by ohmytoken. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 407 次。
如何安装 ohmytoken？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ohmytoken」即可一键安装，无需额外配置。
ohmytoken 是免费的吗？
是的，ohmytoken 完全免费（开源免费），可自由下载、安装和使用。
ohmytoken 支持哪些平台？
ohmytoken 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 ohmytoken？
由 a1pha（@0x5446）开发并维护，当前版本 v2.0.3。
推荐 Skills