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

按实测增长排序,并在不同来源间归一化。 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

    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
  3. 3

    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
  4. 4
    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
  5. 5

    技能
    活跃

    Local-first memory and prompt-cache layer for Claude Code

    github实测增长打开来源 ↗

    安装 /plugin marketplace add riz007/somtum

    7GitHub 星标稳定
  6. 6

    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
  7. 7
    活跃

    Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.

    mcp实测增长打开来源 ↗

    安装 claude mcp add comparedge-llm-cost -- npx @comparedge/llm-cost-mcp

    2GitHub 星标稳定
  8. 8
    活跃

    A MCP that turns PDFs into structured text, tables, figures, metadata, annotations, and page-level evidence for selective retrieval by MCP-compatible AI agents. Improves the information quality AI agents receive while also reducing token…

    github实测增长打开来源 ↗

    17GitHub 星标稳定
  9. 9
    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
  10. 10

    技能
    活跃

    mcp-recall compresses MCP tool outputs (94 KB → 3.5 KB · 96%) and stores full results in SQLite for retrieval — up to 30x more tool calls per session for heavy MCP workloads.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add sakebomb/mcp-recall

    8GitHub 星标稳定
  11. 11
    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
  12. 12

    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
  13. 13
    休眠

    DAG-based Lossless Context Management for Claude Code. Every message preserved, summaries cascade as a DAG, patterns extracted via Lossless Dream — full recall and reflection across sessions.

    github实测增长打开来源 ↗

    15GitHub 星标稳定
  14. 14

    技能
    活跃

    Token-efficient Claude Code workspace with parallel agents and persistent memory. Research → Plan → Implement → Validate workflow.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add coalesce-labs/catalyst

    20GitHub 星标稳定
  15. 15
    活跃

    Claude Code skill: reduce token usage 60-80% — targeted reads, model switching, context management. One-line install.

    github实测增长打开来源 ↗

    2GitHub 星标稳定
  16. 16

    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

    49GitHub 星标+5 (+11.4 %)
  17. 17
    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
  18. 18
    活跃

    Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable

    mcp实测增长打开来源 ↗

    安装 claude mcp add token_optimizer -- uvx slimctx

    1GitHub 星标稳定
  19. 19
    活跃

    Turn your strongest model into a conductor: route each step to the cheapest capable model, and escalate only load-bearing pieces to a pricier reviewer that catches pitfalls early. Subscription, API, or hybrid.

    github实测增长打开来源 ↗

    2GitHub 星标稳定
  20. 20

    技能
    休眠

    ⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add Madhan230205/token-reducer

    44GitHub 星标稳定
  21. 21

    技能
    活跃

    A production-ready Claude Code setup. Global CLAUDE.md, coding rules, per-project memory, and token optimization.

    github实测增长打开来源 ↗

    安装 /plugin marketplace add janmaaarc/basecamp

    7GitHub 星标稳定
  22. 22

    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 %)
  23. 23
    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
  24. 24
    活跃

    Persistent memory for any AI — zero token cost until recall

    mcp实测增长打开来源 ↗

    44GitHub 星标稳定
  25. 25
    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