Die Werkzeugbeschreibungen sind auf Englisch.

Token-Effizienz

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

Anwendungsfall

Aktivität

Sortieren nach

90

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

    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
  2. 2
    Aktiv

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

    mcpgemessenes WachstumQuelle öffnen ↗

    Remote-Server, in der MCP-Konfiguration anzugeben https://mcplint-web.vercel.app/api/mcp

    0GitHub-Sternestabil
  3. 3
    Aktiv

    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.

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-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

    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
  6. 6
    Aktiv

    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…

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  7. 7

    Skill
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add riz007/somtum

    7GitHub-Sternestabil
  8. 8

    Skill
    Ruhend

    Drop-in Cursor rules to cut AI response tokens (no filler/hedging, preserve code + technical strings). Includes local, reproducible benchmarks.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/marcomondelli/bonsai ~/.claude/skills/bonsai

    0GitHub-Sternestabil
  9. 9
    Aktiv

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

    mcpgemessenes WachstumQuelle öffnen ↗

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

    2GitHub-Sternestabil
  10. 10
    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
  11. 11
    Aktiv

    Cut vision-LLM token costs by snapping images to tile boundaries — Claude, GPT, Gemini, Llama, Qwen

    mcpgemessenes WachstumQuelle öffnen ↗

    Installieren claude mcp add vision-squeezer -- npx vision-squeezer

    2GitHub-Sternestabil
  12. 12

    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
  13. 13

    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
  14. 14

    Skill
    Ruhend

    Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/memvid/claude-brain ~/.claude/skills/claude-brain

    575GitHub-Sternestabil
  15. 15
    Aktiv

    Context GC for LLM agents: offload large tool outputs and recall them to save tokens.

    mcpgemessenes WachstumQuelle öffnen ↗

    Installieren claude mcp add lethe -- uvx lethe-llm-context

    0GitHub-Sternestabil
  16. 16

    Agent
    Aktiv

    Agent context compressor and memory persistent orchestration

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sternestabil
  17. 17

    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
  18. 18
    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
  19. 19

    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
  20. 20

    Sonstige
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sternestabil
  21. 21
    Aktiv

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

    mcpgemessenes WachstumQuelle öffnen ↗

    Installieren claude mcp add tokentrust -- uvx tokentrust-cli

    0GitHub-Sternestabil
  22. 22
    Aktiv

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

    mcpgemessenes WachstumQuelle öffnen ↗

    Installieren claude mcp add token_optimizer -- uvx slimctx

    1GitHub-Sternestabil
  23. 23
    Aktiv

    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.

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sternestabil
  24. 24
    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
  25. 25

    Skill
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add janmaaarc/basecamp

    7GitHub-Sternestabil