Die Werkzeugbeschreibungen sind auf Englisch.

Token-Effizienz

Werkzeuge zur Senkung von Token-Kosten und Komprimierung von Kontext.

Anwendungsfall

Aktivität

Sortieren nach

92

Werkzeug-Rangliste

Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.

  1. 1

    Skill
    Aktiv

    Claude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/pcx-wave/vibe-skill ~/.claude/skills/vibe-skill

    117GitHub-Sternestabil
  2. 2

    Skill
    Ruhend

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

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add abhisekjha/pith

    98GitHub-Sternestabil
  3. 3
    Ruhend

    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…

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/myunwang/ppt-report-skills ~/.claude/skills/ppt-report-skills

    81GitHub-Sternestabil
  4. 4
    Ruhend

    SpiderBrain v3 is a multi-platform skill/framework to reduce token usage and AI hallucinations across Claude, Cursor, and other AI tools.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/abhishek-performdigital/Spiderbrain-V3 ~/.claude/skills/Spiderbrain-V3

    65GitHub-Sternestabil
  5. 5
    Aktiv

    Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.

    githubgemessenes WachstumQuelle öffnen ↗

    64GitHub-Sternestabil
  6. 6

    Skill
    Aktiv

    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…

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/firish/webfetch ~/.claude/skills/webfetch

    55GitHub-Sternestabil
  7. 7

    Skill
    Aktiv

    Claude Code skills for developers who code like cats — never more effort than the problem requires.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/albertobarnabo/lazy-cat ~/.claude/skills/lazy-cat

    50GitHub-Sternestabil
  8. 8
    Ruhend

    ⚡ 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.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add Madhan230205/token-reducer

    44GitHub-Sternestabil
  9. 9

    Skill
    Ruhend

    Claude Code plugin that offloads large outputs to filesystem and retrieves when required.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add sheeki03/Few-Word

    38GitHub-Sternestabil
  10. 10

    MCP
    Ruhend

    Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.

    githubgemessenes WachstumQuelle öffnen ↗

    35GitHub-Sternestabil
  11. 11
    Ruhend

    Convert long AI conversations into portable conversation state graphs for LLM handoffs.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/Adityapal67/context-graph-compressor ~/.claude/skills/context-graph-compressor

    35GitHub-Sternestabil
  12. 12
    Aktiv

    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…

    githubgemessenes WachstumQuelle öffnen ↗

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

    33GitHub-Sternestabil
  13. 13
    Aktiv

    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.

    githubgemessenes WachstumQuelle öffnen ↗

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

    31GitHub-Sternestabil
  14. 14
    Ruhend

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

    githubgemessenes WachstumQuelle öffnen ↗

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

    26GitHub-Sternestabil
  15. 15

    Skill
    Aktiv

    Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add AndyShaman/senior-fable

    23GitHub-Sternestabil
  16. 16

    Skill
    Aktiv

    Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add realgarit/fable-baton

    22GitHub-Sternestabil
  17. 17

    Skill
    Aktiv

    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.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add jianzhichun/permafrost

    21GitHub-Sternestabil
  18. 18

    Skill
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add coalesce-labs/catalyst

    20GitHub-Sternestabil
  19. 19

    Skill
    Aktiv

    Token-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add GabrielBarberini/laconic

    19GitHub-Sternestabil
  20. 20
    Aktiv

    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…

    githubgemessenes WachstumQuelle öffnen ↗

    17GitHub-Sternestabil
  21. 21

    Agent
    Aktiv

    Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.

    githubgemessenes WachstumQuelle öffnen ↗

    16GitHub-Sternestabil
  22. 22
    Ruhend

    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.

    githubgemessenes WachstumQuelle öffnen ↗

    15GitHub-Sternestabil
  23. 23
    Ruhend

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

    githubgemessenes WachstumQuelle öffnen ↗

    9GitHub-Sternestabil
  24. 24
    Aktiv

    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。

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add zander-zyx/claude-mini-hud

    9GitHub-Sternestabil
  25. 25

    Skill
    Aktiv

    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.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add sakebomb/mcp-recall

    8GitHub-Sternestabil