Signal Garden

Skill 与 AgentSKILLS & AGENTS· CLAUDE-SKILL

token-optimizer

alexgreensh/token-optimizer

帮Claude Code等编程工具找出并修复浪费token的地方,自动压缩优化上下文。A tool that audits AI coding assistants for wasted context tokens and automatically reduces costs.

根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.

适用平台Platforms
claude-code · claude-desktop · claude-ai · codex · vscode · opencode · copilot · cursor
已识别的要求Documented requirements
Local runtime
许可LICENSE
未确认Not confirmed

每周一 1 封:本周热度最高的 10 个 GitHub 新项目。免费,随时退订。One email each Monday: the 10 hottest new GitHub projects this week. Free, unsubscribe any time.

订阅即表示你同意我们按隐私政策发送每周一周刊。我们会记录这次订阅的来源页面和活动标签,这条记录不包含 IP 地址。Subscribing means you agree that we email the Monday weekly digest as described in the privacy policy. We record the referring page and campaign tag for the signup, and that record does not include an IP address. 隐私政策Privacy Policy

Featured on Signal Garden
徽章主题Badge theme

能力CAPABILITIES

它能帮你做成什么What it helps you do

  1. 01

    找出对话里浪费的隐形字符并修掉

  2. 02

    自动压缩旧内容,避免对话越用越卡

  3. 03

    给上次没做完的活存个档,下次接着来

  4. 04

    打开面板看用量、质量和省下的开销

  5. 05

    装好后自动干活,不用每次手动跑命令

  1. 01

    Audit context window for wasted tokens.

  2. 02

    Automatically compress repetitive output.

  3. 03

    Detect and fix ghost tokens.

  4. 04

    Track cost savings over time.

  5. 05

    Generate a dashboard of context usage and quality.

上手GET STARTED

怎么装How to install

CLAUDE-PLUGIN
/plugin marketplace add alexgreensh/token-optimizer

选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.

打开项目文档Open project documentation ↗

使用限制LIMITATIONS

限制与风险Limits and risk

以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

未知Unknown

01需要 API KeyREQUIRES API KEY
未在文档中发现Not found in the docs
02需要本地环境NEEDS LOCAL RUNTIME
是Yes
03需要 DockerNEEDS DOCKER
未在文档中发现Not found in the docs
04难度DIFFICULTY
需要本地环境Needs a local runtime
05许可LICENSE
未在文档中发现Not found in the docs
06阶段STAGE
持续活跃Active
创建于 26 FEB 2026Created 26 FEB 2026

静态扫描STATIC SCAN

在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.

静态扫描未发现明显风险,但不代表安全。The static scan found no known risk patterns in the documentation, but that does not prove the project is safe.

项目动态PROJECT ACTIVITY

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

+22.3%+22.3%

2.5k → 3.0k stars · 49 个快照2.5k → 3.0k stars · 49 snapshots

状态STATUS

持续活跃Active

质量 A-Quality A-

这个项目在 2026 年 2 月创建,到 10 月已经积累 2526 个 star,说明关注度上升很快。Context window bloat is a common pain point for AI coding agent users.

每周一周刊Monday weekly digest

每周一 1 封:本周热度最高的 10 个 GitHub 新项目。免费,随时退订。One email each Monday: the 10 hottest new GitHub projects this week. Free, unsubscribe any time.

看第 1 期Read issue 1

订阅即表示你同意我们按隐私政策发送每周一周刊。我们会记录这次订阅的来源页面和活动标签,这条记录不包含 IP 地址。Subscribing means you agree that we email the Monday weekly digest as described in the privacy policy. We record the referring page and campaign tag for the signup, and that record does not include an IP address. 隐私政策Privacy Policy

订阅每周一周刊Subscribe to the Monday weekly digest
PROVENANCE · 这些结论的依据是什么Where these conclusions come from
来源 URLSource URL
https://github.com/alexgreensh/token-optimizer
原始数据哈希Raw data hash
c6c965b59ae2c8b316259da49e1b928f
解析时间Parsed at
2026-11-20T23:52:08.087Z
最后一次验证Last verified
2026-11-20T22:14:42.723Z
增长测量时间Growth measured
2026-11-20T23:59:22.010Z
发现查询Discovery queries
focus:token:repo:topic-context-engineering, focus:token:repo:topic-token-optimization
分类来源Category source
rules
焦点Focus
token (13)

依赖:Dependencies:@earendil-works/pi-coding-agent

完整解析证据 JSONFull parse evidence JSON
{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "tree: .claude-plugin/"
    },
    {
      "agent": "claude-desktop",
      "evidence": "readme: …. ## A Status Bar Inside the Claude Desktop App <p align=\"center\"> <a…"
    },
    {
      "agent": "claude-ai",
      "evidence": "readme: …**Claude Code cloud sessions (claude.ai/code).** Cloud sessions load…"
    },
    {
      "agent": "codex",
      "evidence": "readme: …Cursor, Claude Code, Copilot, Codex CLI | 🟢 17 integrations | 🔴 Cla…"
    },
    {
      "agent": "vscode",
      "evidence": "readme: …ti-platform | 🟢 Claude Code, VS Code, Codex, OpenClaw, OpenCode, H…"
    },
    {
      "agent": "opencode",
      "evidence": "readme: ….io/token-optimizer/platforms/opencode/\"><img src=\"skills/token-opti…"
    },
    {
      "agent": "copilot",
      "evidence": "readme: …/copilot.svg\" width=\"96\" alt=\"GitHub Copilot\"></a> <picture><source medi…"
    },
    {
      "agent": "cursor",
      "evidence": "cowork/token-optimizer/skills/token-coach/SKILL.md: …rs** hear Cursor terms only: `.cursor/rules` and `AGENTS.md` (there is no…"
    }
  ],
  "apiKey": null,
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 0,
      "dev-tools": 0,
      "indie-web": 0,
      "skill-agent": 3,
      "productivity": 6
    },
    "primary": "skill-agent",
    "secondary": "claude-skill"
  },
  "localRuntime": "tion? Go for it. Full source, runs locally, no license purchase needed. That inclu",
  "skillMdTotal": 17,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 0,
    "media": 0,
    "design": 0,
    "browser": 0,
    "devtool": 0,
    "security": 0,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "17 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "skills/ directory with 32 markdown files",
      "weight": 0.75
    },
    {
      "signal": "Claude Code plugin manifest",
      "weight": 0.7
    }
  ],
  "scannedSources": [
    "readme",
    "cowork/token-optimizer/skills/fleet-auditor/SKILL.md",
    "cowork/token-optimizer/skills/resume-checkpoint/SKILL.md",
    "cowork/token-optimizer/skills/token-coach/SKILL.md",
    "cowork/token-optimizer/skills/token-dashboard/SKILL.md",
    "cowork/token-optimizer/skills/token-optimizer/SKILL.md",
    "devin/SKILL.md",
    "openclaw/skills/token-optimizer/SKILL.md",
    "plugins/token-optimizer/skills/fleet-auditor/SKILL.md",
    "plugins/token-optimizer/skills/resume-checkpoint/SKILL.md",
    "plugins/token-optimizer/skills/token-coach/SKILL.md",
    "plugins/token-optimizer/skills/token-dashboard/SKILL.md",
    "plugins/token-optimizer/skills/token-optimizer/SKILL.md",
    "skills/fleet-auditor/SKILL.md",
    "skills/resume-checkpoint/SKILL.md",
    "skills/token-coach/SKILL.md",
    "skills/token-dashboard/SKILL.md",
    "skills/token-optimizer/SKILL.md"
  ],
  "skillMdFetched": 17
}