Not in the top 1,000 by GitHub stars

STARKTANG108/kindle-token-panel

免越狱将闲置 Kindle(含咪咕版)改造成 AI 实时墨水屏看板:投影 Token Monitor 用量/费用/模型榜 + 全渠道在途 Agent 任务进度条(零依赖标准库 · Agent Skill)

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 932a03f8548e

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 932a03f8548e19cd79c6fa0453ca0b6d0fead7ac

10GitHub stars
Not availablestars in 7 days
1skill in this repository
1commit in 30 days

Heat

Insufficient history

Not enough history yet to measure heat. It appears after a few days of data.

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Nov 2, 2026Nov 2, 202610

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

kindle-token-panel

When your agent uses it

将闲置 Kindle(未越狱,含国际版与 Kindle X 咪咕版)改造为实时 AI Token 用量与在途多智能体任务墨水屏监控面板的完整技能与零依赖服务套件。

What it loads into context

Frontmatter

63 tokens

Always available to the agent

SKILL.md

1,645 tokens

When the skill is activated

Reference documents

3,107 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 🎯 核心架构与功能特性
  2. 🤖 AI Agent 自动化执行 SOP
  3. 🛠<U+FE0F> 故障排查与维护 (Troubleshooting)

Scripts executed separately

  • install_launchd.sh
  • kpanel
  • make_launcher_books.py
  • server.py

Files

  • .gitignoreasset189 bytes
  • LICENSEasset1,069 bytes
  • README.mddoc11,973 bytes
  • SKILL.mdcore5,512 bytes
  • SKILL.mdcore5,512 bytes
  • SKILL.mdcore5,512 bytes
  • SKILL.mdcore5,512 bytes
  • SKILL.mdcore5,512 bytes
  • SKILL.mdcore5,512 bytes
  • SKILL.mdcore5,512 bytes
  • SKILL.mdcore5,512 bytes
  • SKILL.mdcore5,512 bytes
  • install_launchd.shruns2,638 bytes
  • kpanelruns8,873 bytes
  • make_launcher_books.pyruns18,224 bytes
  • server.pyruns34,616 bytes
  • static/index.htmlasset27,962 bytes
Read SKILL.md

# 📟 Kindle 实时 AI Token 与任务监控面板 (Kindle Panel Skill)

本技能为 AI Agent 提供了自动化将各类闲置 Kindle 电子书阅读器(未越狱,全面支持国际版 Paperwhite / Oasis / Voyage / Scribe 以及定制版 **Kindle X 咪咕版 `KFBJWI`**)改造为桌面级实时 AI 监控墨水屏的完整自动化标准作业程序 (SOP)。

---

## 🎯 核心架构与功能特性

1. **零第三方依赖**:纯 Python 3 标准库实现 (`server.py`, `kpanel`, `make_launcher_books.py`),无需 `pip install` 任何额外库。
2. **绝对安全只读**:以 URI 只读模式 (`mode=ro`) 连接 Token Monitor 与 Antigravity 本地 SQLite,绝不写脏任何数据库。
3. **四通道在途任务聚合**:
   - **Antigravity 主会话与子代理**(实时解析 `task.md` 进度百分比与步数);
   - **Token Monitor 外部客户端**(Claude / Codex / Devin / OpenCode 活跃会话);
   - **本地长耗时脚本进程**(`ps` 智能识别爬虫、Remotion 渲染、FFmpeg 等,过滤 Chrome 子进程);
View the complete source on GitHub

Skills included

  • kindle-token-panel

Repository facts

License
MIT
Created
Oct 24, 2026
Last pushed
Oct 24, 2026
Forks
1
Open issues
0
Project activity
Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 7, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 8 notes
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 57 signals by file

.gitignore

  • Access to secretsline 16
    [Credential-related source omitted]

README.md

  • Network accessline 7
    [![License: MIT](https://img.shields.io/badge/License-MIT-black.svg)](LICENSE)
  • Network accessline 8
    [![Python 3.8+](https://img.shields.io/badge/Python-3.8%2B-blue.svg)](https://www.python.org/)
  • Network accessline 9
    [![Kindle Tested](https://img.shields.io/badge/Kindle-100%25%20Compatible-black.svg)](#-kindle-全机型硬件适配)
  • Network accessline 10
    [![Zero Dependencies](https://img.shields.io/badge/Dependencies-Zero%20(Pure%20StdLib)-success.svg)](#-核心特性)
  • Network accessline 128
    git clone https://github.com/STARKTANG108/kindle-token-panel.git
  • Network accessline 138
    控制台将输出服务地址(包含局域网 IP,如 `http://192.168.1.x:8765`)。
  • Network accessline 143
    1. 确保 Kindle 与电脑连接在**同一 Wi-Fi 局域网**; 2. 打开 Kindle 顶部菜单 -> **体验版浏览器 (Experimental Browser)**; 3. 输入终端打印的局域网地址(如 `http://192.168.1.x:8765`);
  • Network accessline 144
    2. 打开 Kindle 顶部菜单 -> **体验版浏览器 (Experimental Browser)**; 3. 输入终端打印的局域网地址(如 `http://192.168.1.x:8765`); 4. 进入面板后,点击浏览器右上角菜单,将页面**添加为书签**。
  • Network accessline 145
    3. 输入终端打印的局域网地址(如 `http://192.168.1.x:8765`);
  • Network accessline 213
    # 克隆到项目的 .agents/skills 目录下即可被智能体自动识别激活 mkdir -p .agents/skills git clone https://github.com/STARKTANG108/kindle-token-panel.git .agents/skills/kindle-token-panel
  • Network accessline 215
    git clone https://github.com/STARKTANG108/kindle-token-panel.git .agents/skills/kindle-token-panel

SKILL.md

  • Network accessline 51
    部署完成后,终端会打印本机访问地址与局域网 IP(例如 `http://192.168.1.x:8765`)。

install_launchd.sh

  • Executable scriptline 1
    #!/bin/zsh
  • Dangerous shell operationline 21
    rm -f "$old_file"
  • Dangerous shell operationline 28
    rm -f "$PLIST_PATH"
  • Network accessline 46
    cat > "$PLIST_PATH" <<EOF <?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
  • Network accessline 47
    <?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd"> <plist version="1.0">
  • Network accessline 48
    <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
  • Network accessline 73
    echo "================================================================" echo "  [kindle-panel] macOS 开机自启常驻服务已成功部署并加载!" echo "  • 本机访问: http://127.0.0.1:${PORT}"
  • Network accessline 74
    echo "  [kindle-panel] macOS 开机自启常驻服务已成功部署并加载!" echo "  • 本机访问: http://127.0.0.1:${PORT}" echo "  • 局域网 Kindle 访问: http://${LAN_IP}:${PORT}"
  • Network accessline 75
    echo "  • 本机访问: http://127.0.0.1:${PORT}"
  • Network accessline 76
    echo "  • 局域网 Kindle 访问: http://${LAN_IP}:${PORT}"

kpanel

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Network accessline 17
    [Credential-related source omitted]
  • Access to secretsline 17
    [Credential-related source omitted]
  • Network accessline 18
    DEFAULT_BASE_URL = f"http://127.0.0.1:{DEFAULT_PORT}"
  • Network accessline 21
    def make_request(url, method="GET", data=None, timeout=3.0):     """Execute HTTP request using urllib."""     req = urllib.request.Request(url, method=method)
  • Network accessline 22
    """Execute HTTP request using urllib."""     req = urllib.request.Request(url, method=method)     req.add_header("User-Agent", "kpanel-cli/1.0")
  • Network accessline 23
    req = urllib.request.Request(url, method=method)
  • Network accessline 30
    try:         with urllib.request.urlopen(req, timeout=timeout) as resp:
  • Network accessline 31
    with urllib.request.urlopen(req, timeout=timeout) as resp:

make_launcher_books.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Network accessline 38
    pass     try:         s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
  • Network accessline 39
    try:         s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)         s.connect(("8.8.8.8", 80))
  • Network accessline 40
    s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
  • Possible obfuscationline 91
    out.extend(b"%PDF-1.4\n%\xe2\xe3\xcf\xd3\n")
  • Possible obfuscationline 320
    rec2_flis = b"FLIS\x00\x00\x00\x08\x00\x41\x00\x00\x00\x00\x00\x00\xff\xff\xff\xff\x00\x01\x00\x03\x00\x00\x00\x00\x00\x00\x00\x00\xff\xff\xff\xff"
  • Possible obfuscationline 324
    b"FCIS\x00\x00\x00\x14\x00\x00\x00\x10\x00\x00\x00\x01\x00\x00\x00\x00"
  • Possible obfuscationline 326
    + b"\x00\x00\x00\x00\x00\x00\x00\x20\x00\x00\x00\x08\x00\x01\x00\x01\x00\x00\x00\x00"
  • Access to secretsline 454
    [Credential-related source omitted]
  • Network accessline 469
    "--url",         default=None,         help=f"Custom primary dashboard URL (default: http://{default_ip}:<port>)"
  • Network accessline 470
    default=None,         help=f"Custom primary dashboard URL (default: http://{default_ip}:<port>)"     )
  • Network accessline 471
    help=f"Custom primary dashboard URL (default: http://{default_ip}:<port>)"
  • Network accessline 474
    "--backup-url",         default=None,         help=f"Custom backup dashboard URL (default: http://{default_mdns}:<port>)"
  • Network accessline 475
    default=None,         help=f"Custom backup dashboard URL (default: http://{default_mdns}:<port>)"     )
  • Network accessline 476
    help=f"Custom backup dashboard URL (default: http://{default_mdns}:<port>)"
  • Network accessline 491
    port = args.port     primary_url = args.url or f"http://{default_ip}:{port}"
  • Network accessline 492
    primary_url = args.url or f"http://{default_ip}:{port}"
  • Network accessline 493
    backup_url = args.backup_url or f"http://{default_mdns}:{port}"

server.py

  • Executable scriptline 1
    #!/usr/bin/env python3
  • Access to secretsline 20
    [Credential-related source omitted]
  • Access to secretsline 25
    [Credential-related source omitted]
  • Access to secretsline 26
    [Credential-related source omitted]
  • Network accessline 902
    print(f"==================================================")     print(f"  Kindle Real-Time Monitoring Panel Server")     print(f"  Listening on: http://0.0.0.0:{PORT}")
  • Network accessline 903
    print(f"  Kindle Real-Time Monitoring Panel Server")     print(f"  Listening on: http://0.0.0.0:{PORT}")     print(f"  PID: {os.getpid()}")
  • Network accessline 904
    print(f"  Listening on: http://0.0.0.0:{PORT}")

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 1 fact
  • Contacts www.apple.com, which SKILL.md, the README and the plugin manifest do not mentioninstall_launchd.sh:48High confidence
Signal confidence: 56 facts

and 6 more

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.