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

混合排名:实测增长优先。 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

    20 power-user skills for Claude Code: session memory and consolidation, context compression, multi-agent orchestration, adversarial bug hunting, security review, calibrated estimation and decision archaeology. Drop-in SKILL.md files. Built…

    github实测增长打开来源 ↗

    安装 git clone https://github.com/irfad7/claude-power-skills ~/.claude/skills/claude-power-skills

    4GitHub 星标稳定
  2. 2
    休眠

    Give your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add Gr122lyBr/claude-teams-brain

    26GitHub 星标稳定
  3. 3

    技能
    休眠

    Pith is the hook that makes Claude Code sessions last 3x longer.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add abhisekjha/pith

    98GitHub 星标稳定
  4. 4
    休眠

    Optimize Claude Code token usage — 22 skills, 8 hooks, 6 rules. One npm install. Zero manual steps. Cut costs by 67%.

    github实测增长打开来源 ↗

    9GitHub 星标稳定
  5. 5

    MCP
    活跃

    Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.

    mcp实测增长打开来源 ↗

    安装 claude mcp add distil -- npx @munhq/distil

    1GitHub 星标稳定
  6. 6

    技能
    活跃

    Automatically detect and disable irrelevant Claude Code skills per project to save tokens and streamline your tech workflow.

    github实测增长打开来源 ↗

    安装 git clone https://github.com/mrdenox109-nyx/skill-manager ~/.claude/skills/skill-manager

    5GitHub 星标稳定
  7. 7
    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
  8. 8

    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
  9. 9
    活跃

    Lossless context compression: 2-8x fewer tokens, byte-exact recovery, search inside payloads

    mcp实测增长打开来源 ↗

    安装 claude mcp add densely -- uvx densely

    6GitHub 星标稳定
  10. 10
    活跃

    A Claude Code hook that routes each Read on a PDF to the path that actually works: text layer to UTF-8 text, scans to vision, and neither one through poppler.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add WatsonTsai/pdf-text-router

    7GitHub 星标稳定
  11. 11

    技能
    活跃

    The Agent Knowledge Kit & Architecture System — 10–32x token-efficient architecture discovery for AI coding agents

    github实测增长打开来源 ↗

    安装 git clone https://github.com/chama-x/quiv ~/.claude/skills/quiv

    3GitHub 星标稳定
  12. 12

    技能
    活跃

    Cut Claude Code token costs by delegating bulk LLM work to cheap models. 600+ models via NanoGPT, OpenRouter, Groq or local Ollama — batched, resumable, with real per-call cost tracking.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add bicced/sidequest

    1GitHub 星标稳定
  13. 13
    未知最近提交:暂无数据

    AI agent token-cost telemetry + 429 prediction. Per-agent attribution, anomaly + routing + quota.

    mcp实测增长打开来源 ↗

    安装 claude mcp add openclaw-cost-tracker-mcp -- uvx openclaw-cost-tracker-mcp

    1297 天下载量稳定
  14. 14

    技能
    休眠

    Claude Code plugin — inventory all your installed skills, check structure, and find updates. Free, zero dependencies.

    github估算动量打开来源 ↗

    安装 /plugin marketplace add VersoXBT/skill-manager

    6GitHub 星标

学习与参考资源

按实测增长排序,并在不同来源间归一化。 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
  2. 2
    活跃打开来源 ↗

    Molavi Agent Skills: Curated AI agent skills and MCP configs for Antigravity, Cursor, Codex & Claude — by Taghi Molavi

    github资源实测增长
    8GitHub 星标稳定

无公开指标的条目

混合排名:实测增长优先。 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
    未知最近提交:暂无数据

    Semantic context compression and cognitive memory layer for LLM swarms.

    mcp指标未公开打开来源 ↗

    需在 MCP 配置中声明的远程服务器 https://recallmax-mcp.vercel.app/api/mcp

    无公开指标
  2. 2
    未知最近提交:暂无数据

    MCP server for Skim code transformation. Compresses code 60-95% for LLM context optimization.

    mcp指标未公开打开来源 ↗

    安装 claude mcp add skim-mcp-server -- npx skim-mcp-server

    无公开指标
  3. 3
    未知最近提交:暂无数据

    Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.

    mcp指标未公开打开来源 ↗

    安装 claude mcp add mcp-token-optimizer -- npx mcp-token-optimizer

    无公开指标
  4. 4
    未知最近提交:暂无数据

    LLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.

    mcp指标未公开打开来源 ↗

    需在 MCP 配置中声明的远程服务器 https://cache.api.ainode.tech/mcp

    无公开指标
  5. 5

    MCP
    未知最近提交:暂无数据

    Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.

    mcp指标未公开打开来源 ↗

    无公开指标