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休眠
nekte
其他Agent-to-Agent coordination that doesn't waste your context window. Token-efficient protocol with progressive discovery, zero-schema invocation, gRPC transport, and task lifecycle management.
github实测增长打开来源 ↗
1GitHub 星标稳定 - 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活跃
A skill that shrink noisy log/output 60-90% before read — filter, group, dedupe, truncate. Cut token, cut cost, keep signal. By Dhayalan (aka Joy).
github实测增长打开来源 ↗
安装
/plugin marketplace add Da-ya7/PromptCompressor-skill1GitHub 星标稳定 - 4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-mcp2GitHub 星标稳定 - 5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 - 62GitHub 星标稳定
- 7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 - 8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 - 9活跃
hush
技能🤫 Claude shuts up until it's done. A Claude Code plugin: one short answer at the end, the file to open, and no log dumps in your chat.
github实测增长打开来源 ↗
安装
/plugin marketplace add V-Songbird/hush49GitHub 星标+5 (+11.4 %) - 10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 - 11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/SpanishCaveMan2GitHub 星标稳定 - 12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-reducer44GitHub 星标稳定 - 13活跃
Pay-per-call agent APIs over x402: web scraping, token compression, and semantic cache.
mcp实测增长打开来源 ↗
安装
claude mcp add gate402-mcp -- npx gate402-mcp2GitHub 星标稳定 - 1444GitHub 星标稳定
- 15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 densely6GitHub 星标稳定 - 16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 - 17休眠
Few-Word
技能Claude Code plugin that offloads large outputs to filesystem and retrieves when required.
github实测增长打开来源 ↗
安装
/plugin marketplace add sheeki03/Few-Word38GitHub 星标稳定 - 18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 - 19休眠
unclog
MCPAudit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.
github实测增长打开来源 ↗
35GitHub 星标稳定 - 20休眠
Save tokens while coding — your AI agent gets structured code context, not file dumps.
mcp实测增长打开来源 ↗
安装
claude mcp add codeweave -- npx @codeweave/mcp4GitHub 星标稳定 - 21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 - 22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 - 23活跃
Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.
mcp实测增长打开来源 ↗
安装
claude mcp add smart-context-mcp -- npx smart-context-mcp4GitHub 星标稳定 - 24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-eco33GitHub 星标稳定 - 25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