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

44

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

    Statically audits MCP tool surfaces for token cost, schema quality, and design issues.

    mcp实测增长打开来源 ↗

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

    0GitHub 星标稳定
  2. 2
    活跃

    Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.

    mcp实测增长打开来源 ↗

    安装 claude mcp add tokentrust -- uvx tokentrust-cli

    0GitHub 星标稳定
  3. 3
    活跃

    Measure and shrink the token cost of Claude Code skills, tier by tier: the always-on system-prompt tax, the per-invocation body, and on-demand references, each priced at the rate it is actually billed.

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  4. 4

    技能
    活跃

    🤫 Token-lean sessions at the harness level. An easy to grasp output style, output-shrinking hooks, and log compression cut both input and output tokens.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add V-Songbird/hush

    47GitHub 星标+4 (+9.3 %)
  5. 5
    活跃

    Claude Code skill: caveman-style token efficiency, spoken with a real Spanish regional accent

    github实测增长打开来源 ↗

    安装 /plugin marketplace add Mun1to/SpanishCaveMan

    2GitHub 星标稳定
  6. 6
    活跃

    Persistent memory for any AI — zero token cost until recall

    mcp实测增长打开来源 ↗

    44GitHub 星标+3 (+7.3 %)
  7. 7

    智能体
    活跃

    Agent context compressor and memory persistent orchestration

    github实测增长打开来源 ↗

    2GitHub 星标稳定
  8. 8
    活跃

    Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our…

    github实测增长打开来源 ↗

    安装 /plugin marketplace add sup3x/claude-code-eco

    33GitHub 星标稳定
  9. 9
    活跃

    Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works as a Claude Code plugin.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add NodeNestor/claude-rolling-context

    31GitHub 星标+1 (+3.3 %)
  10. 10
    活跃

    Restore prior Claude Code AND Codex sessions with zero LLM calls. Cross-tool session handoff, cache-expiry prevention, real cost dashboard. One plugin, both hosts.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add ww-w-ai/super-token-saver

    31GitHub 星标稳定
  11. 11

    技能
    活跃

    Profile Claude Code context, discover repeated workflows, and regression-test your skills. Local-only, zero-dependency.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add nks0614/harnessay

    5GitHub 星标+2 (+66.7 %)
  12. 12

    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
  13. 13

    技能
    活跃

    🪒 YAGNI enforcement at the harness level, nudges toward the simplest solution and gates against unnecessary dependencies, file sprawl, and unchecked build growth.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add V-Songbird/razor

    8GitHub 星标+1 (+14.3 %)
  14. 14

    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
  15. 15
    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
  16. 16

    技能
    活跃

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

    github估算动量打开来源 ↗

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

    3GitHub 星标
  17. 17

    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
  18. 18

    活跃

    A high-performance, ergonomic web framework for Rust with native AI/LLM support.

    github估算动量打开来源 ↗

    61GitHub 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 ↗

    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