工具说明为英文。

令牌效率

降低令牌成本并压缩上下文的工具。

用途

活跃度

排序方式

90

工具排名

Ranked by creation date, newest first; undated entries come last. 原始值保留各自的数据窗口;计算变化需要 7 天内至少两次测量。

  1. 1
    活跃

    Usage-aware status line for Claude Code: session & weekly rate-limit gauges with reset countdowns and a precise context-window meter, plus tokens, git & weather. Template-driven and extensible — set it up by chatting with Claude or via a…

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  2. 2
    活跃

    Compact, source-linked context packs that reduce token waste for coding agents.

    mcp实测增长打开来源 ↗

    安装 claude mcp add capsule -- npx capsulectx

    4GitHub 星标稳定
  3. 3
    活跃

    A Claude Code plugin that shows exactly where your AI coding session wasted tokens — and how to fix it. Flags waste, never quality. Runs locally.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add Jimmynycu/token-efficiency

    2GitHub 星标稳定
  4. 4
    活跃

    Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files.

    mcp实测增长打开来源 ↗

    安装 claude mcp add agent-booster -- uvx agent-booster

    1GitHub 星标稳定
  5. 5
    活跃

    Context GC for LLM agents: offload large tool outputs and recall them to save tokens.

    mcp实测增长打开来源 ↗

    安装 claude mcp add lethe -- uvx lethe-llm-context

    0GitHub 星标稳定
  6. 6
    活跃

    Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.

    mcp实测增长打开来源 ↗

    安装 claude mcp add compactprompt -- uvx compactprompt

    0GitHub 星标稳定
  7. 7
    活跃

    对标 claude-hud 核心功能,控制在 7 行以内更轻量。内置 13 个国产大模型平台用量查询 (智谱 GLM / MiniMax / DeepSeek / Kimi / StepFun / SiliconFlow 等),第三方代理用户也能实时看到额度消耗。

    github实测增长打开来源 ↗

    安装 /plugin marketplace add zander-zyx/claude-mini-hud

    10GitHub 星标+1 (+11.1 %)
  8. 8
    活跃

    Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

    github实测增长打开来源 ↗

    55GitHub 星标+1 (+1.9 %)
  9. 9

    技能
    活跃

    Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add jianzhichun/permafrost

    21GitHub 星标稳定
  10. 10

    MCP
    活跃

    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

    mcp实测增长打开来源 ↗

    安装 claude mcp add llmtrim -- npx @llmtrim/cli

    222GitHub 星标稳定
  11. 11
    活跃

    MCP server that cuts AI coding agent token usage via framework-aware context optimization

    mcp实测增长打开来源 ↗

    安装 claude mcp add ai-optimizer -- npx @ai-optimizer/core

    0GitHub 星标稳定
  12. 12

    技能
    活跃

    Claude Code skills for developers who code like cats — never more effort than the problem requires.

    github实测增长打开来源 ↗

    安装 git clone https://github.com/albertobarnabo/lazy-cat ~/.claude/skills/lazy-cat

    50GitHub 星标稳定
  13. 13

    技能
    休眠

    Agent context gate for Codex, Claude Code, Copilot, MCP, Cursor, Cline, Gemini and Windsurf repos

    github实测增长打开来源 ↗

    安装 git clone https://github.com/grnbtqdbyx-create/contextforge ~/.claude/skills/contextforge

    1GitHub 星标稳定
  14. 14
    休眠

    Convert long AI conversations into portable conversation state graphs for LLM handoffs.

    github实测增长打开来源 ↗

    安装 git clone https://github.com/Adityapal67/context-graph-compressor ~/.claude/skills/context-graph-compressor

    35GitHub 星标稳定
  15. 15
    活跃

    Claude Code skill — delegate coding tasks to Opencode, supervise via git diff & save 50-90% Claude token usage

    github实测增长打开来源 ↗

    安装 git clone https://github.com/pcx-wave/opencode-skill ~/.claude/skills/opencode-skill

    17GitHub 星标+1 (+6.2 %)
  16. 16
    休眠

    SpiderBrain v3 is a multi-platform skill/framework to reduce token usage and AI hallucinations across Claude, Cursor, and other AI tools.

    github实测增长打开来源 ↗

    安装 git clone https://github.com/abhishek-performdigital/Spiderbrain-V3 ~/.claude/skills/Spiderbrain-V3

    65GitHub 星标稳定
  17. 17
    休眠

    A Claude Code skill for web report decks — richer ECharts charts, one file per slide (edit one page, save tokens), and complex structure diagrams. 16:9 & vertical, PDF/image export.网页版 PPT 汇报的 Claude Code skill:ECharts 把数据画得更好看、每页一个文件改一页省…

    github实测增长打开来源 ↗

    安装 git clone https://github.com/myunwang/ppt-report-skills ~/.claude/skills/ppt-report-skills

    81GitHub 星标稳定
  18. 18
    活跃

    Cut vision-LLM token costs by snapping images to tile boundaries — Claude, GPT, Gemini, Llama, Qwen

    mcp实测增长打开来源 ↗

    安装 claude mcp add vision-squeezer -- npx vision-squeezer

    2GitHub 星标稳定
  19. 19

    技能
    活跃

    Claude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage

    github实测增长打开来源 ↗

    安装 git clone https://github.com/pcx-wave/vibe-skill ~/.claude/skills/vibe-skill

    117GitHub 星标稳定
  20. 20

    其他
    休眠

    Translate any language to English before Claude processes it. ~49% token savings combined with caveman.

    github实测增长打开来源 ↗

    2GitHub 星标稳定
  21. 21
    活跃

    Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add sofumel/claude-handoff-revive

    6GitHub 星标稳定
  22. 22

    技能
    活跃

    Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add 0xhimanshu/governor

    133GitHub 星标+2 (+1.5 %)
  23. 23

    技能
    休眠

    Drop-in Cursor rules to cut AI response tokens (no filler/hedging, preserve code + technical strings). Includes local, reproducible benchmarks.

    github实测增长打开来源 ↗

    安装 git clone https://github.com/marcomondelli/bonsai ~/.claude/skills/bonsai

    0GitHub 星标稳定
  24. 24

    技能
    活跃

    Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with…

    github实测增长打开来源 ↗

    安装 git clone https://github.com/firish/webfetch ~/.claude/skills/webfetch

    55GitHub 星标稳定

学习与参考资源

Ranked by creation date, newest first; undated entries come last. 这些资源可单独访问,不参与主要排名。

  1. 1
    活跃打开来源 ↗

    A cheat sheet that stops AI agents from scanning your whole repo and saves you tokens.

    github

    安装 git clone https://github.com/toshon-jennings/SUMMARY-md ~/.claude/skills/SUMMARY-md

    资源实测增长
    0GitHub 星标稳定