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
96
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 capsulectx4GitHub 星标稳定 - 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-efficiency2GitHub 星标稳定 - 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-booster1GitHub 星标稳定 - 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-context0GitHub 星标稳定 - 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 compactprompt0GitHub 星标稳定 - 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-hud10GitHub 星标+1 (+11.1 %) - 8活跃
skillreaper
MCPCut 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/permafrost21GitHub 星标稳定 - 10活跃
llmtrim
MCPMCP 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/cli222GitHub 星标稳定 - 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/core0GitHub 星标稳定 - 12活跃
lazy-cat
技能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-cat50GitHub 星标稳定 - 13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/contextforge1GitHub 星标稳定 - 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-compressor35GitHub 星标稳定 - 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-skill17GitHub 星标+1 (+6.2 %) - 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-V365GitHub 星标稳定 - 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-skills81GitHub 星标稳定 - 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-squeezer2GitHub 星标稳定 - 19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-skill117GitHub 星标稳定 - 20休眠
rosetta
其他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-revive6GitHub 星标稳定 - 22活跃
governor
技能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/governor133GitHub 星标+2 (+1.5 %) - 23休眠
bonsai
技能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/bonsai0GitHub 星标稳定 - 24活跃
webfetch
技能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/webfetch55GitHub 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
资源实测增长git clone https://github.com/toshon-jennings/SUMMARY-md ~/.claude/skills/SUMMARY-md0GitHub 星标稳定