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

98

Classifica degli strumenti

Ranked by creation date, newest first; undated entries come last. I valori grezzi mantengono la propria finestra; una variazione richiede almeno due rilevazioni in 7 giorni.

  1. 1

    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…

    githubcrescita misurataApri fonte ↗

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

    55stelle GitHubstabile
  2. 2

    Skill
    Attivo

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

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add riz007/somtum

    7stelle GitHubstabile
  3. 3

    MCP
    Dormiente

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

    githubcrescita misurataApri fonte ↗

    35stelle GitHubstabile
  4. 4

    Skill
    Dormiente

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

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add abhisekjha/pith

    98stelle GitHubstabile
  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…

    githubcrescita misurataApri fonte ↗

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

    155stelle GitHub+8 (+5.4 %)
  6. 6
    Attivo

    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…

    githubcrescita misurataApri fonte ↗

    17stelle GitHubstabile
  7. 7
    Attivo

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

    githubcrescita misurataApri fonte ↗

    2stelle GitHubstabile
  8. 8

    Skill
    Dormiente

    Say more with less. Claude Code skill/plugin that cuts ~60-70% of output tokens while keeping natural, readable English.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add o4f6bgpac3/concise

    10stelle GitHub+2 (+25.0 %)
  9. 9
    Attivo

    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.

    githubcrescita misurataApri fonte ↗

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

    31stelle GitHubstabile
  10. 10

    Skill
    Attivo

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

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add GabrielBarberini/laconic

    19stelle GitHubstabile
  11. 11

    Altro
    Dormiente

    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.

    githubcrescita misurataApri fonte ↗

    1stelle GitHubstabile
  12. 12

    Skill
    Attivo

    Compact Claude Code statusline — zero-dependency, crash-free on Windows

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add WaterTian/cc-hud

    8stelle GitHubstabile
  13. 13
    Attivo

    Persistent memory for any AI — zero token cost until recall

    mcpcrescita misurataApri fonte ↗

    44stelle GitHub+3 (+7.3 %)
  14. 14
    Dormiente

    ⚡ 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.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add Madhan230205/token-reducer

    44stelle GitHubstabile
  15. 15
    Attivo

    20 power-user skills for Claude Code: session memory and consolidation, context compression, multi-agent orchestration, adversarial bug hunting, security review, calibrated estimation and decision archaeology. Drop-in SKILL.md files. Built…

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/irfad7/claude-power-skills ~/.claude/skills/claude-power-skills

    4stelle GitHubstabile
  16. 16
    Dormiente

    Analyze your MCP setup: token costs, grades, duplicates, and optimization tips

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add mcp-checkup -- npx mcp-checkup

    1stelle GitHubstabile
  17. 17
    Dormiente

    Save tokens while coding — your AI agent gets structured code context, not file dumps.

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add codeweave -- npx @codeweave/mcp

    4stelle GitHubstabile
  18. 18
    Attivo

    Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add smart-context-mcp -- npx smart-context-mcp

    4stelle GitHubstabile
  19. 19
    Attivo

    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.

    githubcrescita misurataApri fonte ↗

    2stelle GitHubstabile
  20. 20
    Dormiente

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

    githubcrescita misurataApri fonte ↗

    9stelle GitHubstabile
  21. 21
    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.

    githubcrescita misurataApri fonte ↗

    115stelle GitHub+1 (+0.88 %)
  22. 22
    Dormiente

    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.

    githubcrescita misurataApri fonte ↗

    15stelle GitHubstabile
  23. 23
    Attivo

    Persistent memory + security layer for Claude Code (MCP plugin). Agents remember your project across sessions (~87% fewer context tokens), every tool call lands in a tamper-evident HMAC audit chain, and skills are AST-scanned +…

    githubcrescita misurataApri fonte ↗

    8stelle GitHubstabile
  24. 24
    Dormiente

    Claude Code plugin — inventory all your installed skills, check structure, and find updates. Free, zero dependencies.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add VersoXBT/skill-manager

    6stelle GitHubstabile
  25. 25
    Dormiente

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

    githubcrescita misurataApri fonte ↗

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

    26stelle GitHubstabile