Le descrizioni degli strumenti sono in inglese.

Efficienza dei token

Strumenti per ridurre i costi dei token e comprimere il contesto.

Utilizzo

Attività

Ordina per

101

Classifica degli strumenti

Classifica per crescita misurata e normalizzata tra le fonti. I valori grezzi mantengono la propria finestra; una variazione richiede almeno due rilevazioni in 7 giorni.

  1. 1

    Skill
    Attivo

    Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts, efficiency scores, git-aware suggestions — all local, zero config.

    JavaScriptLicenza: MIT
    • ai-tools
    • anthropic
    • claude-code
    • claude-code-plugin
    • cli-plugin

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add egorfedorov/claude-context-optimizer

    102stelle GitHub+7 (+7.4 %)
  2. 2

    Altro
    Attivo

    Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

    Python
    • agentskills
    • claude-code
    • claude-code-skill
    • claude-plugin
    • context-engineering

    githubcrescita misurataApri fonte ↗

    2 084stelle GitHub+120 (+6.1 %)
  3. 3

    Skill
    Attivo

    Agent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage across providers with heatmaps, cost tracking, token counting and quota resets..

    PythonLicenza: MIT
    • agent
    • analytics
    • anthropic
    • claude-code
    • claude-code-plugin

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add JingbiaoMei/Tokdash

    66stelle GitHub+3 (+4.8 %)
  4. 4

    MCP
    Attivo

    Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

    GoLicenza: MIT
    • agent-skills
    • ai-agents
    • anthropic
    • claude-code
    • claude-code-plugin

    githubcrescita misurataApri fonte ↗

    54stelle GitHub+2 (+3.8 %)
  5. 5

    Skill
    Attivo

    Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and…

    PythonLicenza: MIT
    • agent-framework
    • agent-orchestration
    • agentic-development
    • agents-md
    • ai-agent

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/KbWen/agentic-os ~/.claude/skills/agentic-os

    150stelle GitHub+5 (+3.4 %)
  6. 6

    Skill
    Attivo

    Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

    PythonLicenza: MIT
    • ai-tools
    • claude-ai
    • claude-code
    • claude-code-plugin
    • claude-skills

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add 0xhimanshu/governor

    133stelle GitHub+4 (+3.1 %)
  7. 7

    MCP
    Attivo

    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

    ↓ 171 download/settimanaRustLicenza: MPL-2.0

      mcpcrescita misurataApri fonte ↗

      Installa claude mcp add llmtrim -- npx @llmtrim/cli

      222stelle GitHub+6 (+2.8 %)
    • 8

      Skill
      Attivo

      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…

      PythonLicenza: MIT
      • agent-memory
      • agent-skills
      • agentic-workflow
      • agents
      • anthropic

      githubcrescita misurataApri fonte ↗

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

      55stelle GitHub+1 (+1.9 %)
    • 9

      MCP
      Attivo

      Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

      PythonLicenza: Apache-2.0
      • agent
      • ai
      • anthropic
      • claude-code
      • compression

      githubcrescita misurataApri fonte ↗

      68 221stelle GitHub+619 (+0.92 %)
    • 10

      MCP
      Attivo

      Tinder for your Claude Code skills, subagents and MCP servers. Swipe away what wastes context, scan for prompt injection, get honest token costs. Fixes what it finds and actually deletes. Zero dependencies, Claude Code + Codex.

      ShellLicenza: MIT
      • agent-skills
      • ai-agents
      • claude
      • claude-code
      • claude-code-marketplace

      githubcrescita misurataApri fonte ↗

      115stelle GitHub+1 (+0.88 %)
    • 11

      CLI
      Attivo

      CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

      RustLicenza: Apache-2.0
      • agentic-coding
      • ai-coding
      • anthropic
      • claude-code
      • cli

      githubcrescita misurataApri fonte ↗

      78 098stelle GitHub+671 (+0.87 %)
    • 12

      Skill
      Attivo

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

      Shell
      • claude
      • claude-ai
      • claude-ai-skills
      • claude-code
      • claude-skill

      githubcrescita misurataApri fonte ↗

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

      118stelle GitHub+1 (+0.85 %)
    • 13

      Skill
      Attivo

      Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces.

      PythonLicenza: Apache-2.0
      • agentic-ai
      • ai-coding-assistant
      • claude-code
      • claude-code-plugin
      • cli-tools

      githubcrescita misurataApri fonte ↗

      Installa /plugin marketplace add ppgranger/token-saver

      140stelle GitHub+1 (+0.72 %)
    • 14

      MCP
      Attivo

      Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

      TypeScriptLicenza: MIT
      • accuracy
      • agents
      • claude-skills
      • context
      • harness

      githubcrescita misurataApri fonte ↗

      430stelle GitHub+3 (+0.70 %)
    • 15

      Skill
      Attivo

      Lossless context compression plugin for Claude Code & OpenCode.

      TypeScriptLicenza: BSD-3-Clause
      • anthropic
      • chatgpt
      • claude
      • claude-code
      • claude-code-plugin

      githubcrescita misurataApri fonte ↗

      Installa /plugin marketplace add aerovato/magic-compact

      144stelle GitHub+1 (+0.70 %)
    • 16

      Skill
      Attivo

      23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128…

      PythonLicenza: MIT
      • ai-agents
      • architecture-patterns
      • awesome-claude-code
      • awesome-claude-skills
      • claude-agents

      githubcrescita misurataApri fonte ↗

      Installa git clone https://github.com/athola/claude-night-market ~/.claude/skills/claude-night-market

      332stelle GitHub+2 (+0.61 %)
    • 17

      Skill
      Dormiente

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

      PythonLicenza: MIT
      • anthropic
      • claude-code
      • claude-code-plugin
      • llm-tools
      • token-optimization

      githubcrescita misurataApri fonte ↗

      Installa /plugin marketplace add abhisekjha/pith

      98stelle GitHubstabile
    • 18

      Skill
      Attivo

      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…

      HTMLLicenza: MIT
      • ai
      • anthropic
      • claude
      • claude-code
      • claude-skills

      githubcrescita misurataApri fonte ↗

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

      81stelle GitHubstabile
    • 19

      Skill
      Dormiente

      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.

      TypeScriptLicenza: MIT
      • ai-tools
      • anthropic
      • claude
      • claude-agents
      • claude-ai

      githubcrescita misurataApri fonte ↗

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

      574stelle GitHubstabile
    • 20

      Skill
      Attivo

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

      JavaScriptLicenza: MIT
      • ai-productivity
      • anthropic
      • cat
      • claude
      • claude-code

      githubcrescita misurataApri fonte ↗

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

      50stelle GitHubstabile
    • 21

      Skill
      Attivo

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

      • agent-skills
      • ai
      • ai-agents
      • anthropic
      • claude

      githubcrescita misurataApri fonte ↗

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

      65stelle GitHubstabile
    • 22

      MCP
      Attivo

      Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.

      RustLicenza: NOASSERTION

        mcpcrescita misurataApri fonte ↗

        609stelle GitHubstabile
      • 23

        MCP
        Attivo

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

        TypeScriptLicenza: MIT
        • claude-code
        • claude-code-plugin
        • context-compression
        • context-window
        • developer-tooling

        githubcrescita misurataApri fonte ↗

        64stelle GitHubstabile
      • 24

        MCP
        SconosciutoUltimo commit: non disponibile

        AI agent token-cost telemetry + 429 prediction. Per-agent attribution, anomaly + routing + quota.

        mcpcrescita misurataApri fonte ↗

        Installa claude mcp add openclaw-cost-tracker-mcp -- uvx openclaw-cost-tracker-mcp

        129download in 7 giornistabile

      Risorse didattiche e di riferimento

      Classifica per crescita misurata e normalizzata tra le fonti. Queste risorse restano accessibili separatamente e non partecipano alla classifica principale.

      1. 1

        outsourcerer

        Skill
        AttivoApri fonte ↗

        Make the most out of your subscriptions. Delegate work to other harnesses and models, while keeping your main session the orchestrator. Nothing new to learn. Keep working like you do, but better.

        Shell
        • agent-skills
        • agentic-workflow
        • claude-code
        • codex
        • fable
        github

        Installa git clone https://github.com/alexgreensh/outsourcerer ~/.claude/skills/outsourcerer

        Risorsacrescita misurata
        142stelle GitHub+5 (+3.6 %)