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

88

Classifica degli strumenti

Ranked by normalized popularity across sources. I valori grezzi mantengono la propria finestra; una variazione richiede almeno due rilevazioni in 7 giorni.

  1. 1

    MCP
    Dormiente

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

    githubcrescita misurataApri fonte ↗

    35stelle GitHubstabile
  2. 2
    Dormiente

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

    githubcrescita misurataApri fonte ↗

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

    35stelle GitHubstabile
  3. 3
    Attivo

    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…

    githubcrescita misurataApri fonte ↗

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

    33stelle GitHubstabile
  4. 4
    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
  5. 5
    Attivo

    Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works as a Claude Code plugin.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add NodeNestor/claude-rolling-context

    31stelle GitHubstabile
  6. 6
    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
  7. 7

    Skill
    Attivo

    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.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add AndyShaman/senior-fable

    25stelle GitHub+2 (+8.7 %)
  8. 8

    Skill
    Attivo

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

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add realgarit/fable-baton

    24stelle GitHub+2 (+9.1 %)
  9. 9

    Skill
    Attivo

    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.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add jianzhichun/permafrost

    21stelle GitHubstabile
  10. 10

    Skill
    Attivo

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

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add coalesce-labs/catalyst

    20stelle GitHubstabile
  11. 11

    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
  12. 12
    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
  13. 13
    Attivo

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

    githubcrescita misurataApri fonte ↗

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

    17stelle GitHub+1 (+6.2 %)
  14. 14

    Agente
    Attivo

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

    githubcrescita misurataApri fonte ↗

    16stelle GitHubstabile
  15. 15
    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
  16. 16
    Attivo

    Staged context pruning for OpenCode, Oh My Pi, pi, and Claude Code.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add AshishKumar4/better-compact

    12stelle GitHub+1 (+9.1 %)
  17. 17

    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

    11stelle GitHub+2 (+22.2 %)
  18. 18
    Attivo

    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。

    githubcrescita misurataApri fonte ↗

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

    10stelle GitHub+1 (+11.1 %)
  19. 19
    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
  20. 20

    Skill
    Attivo

    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.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add sakebomb/mcp-recall

    8stelle GitHubstabile
  21. 21

    Skill
    Attivo

    🪒 YAGNI enforcement at the harness level, nudges toward the simplest solution and gates against unnecessary dependencies, file sprawl, and unchecked build growth.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add V-Songbird/razor

    8stelle GitHub+1 (+14.3 %)
  22. 22

    Skill
    Attivo

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

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add WaterTian/cc-hud

    8stelle 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

    Skill
    Attivo

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

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add riz007/somtum

    7stelle GitHubstabile

Risorse didattiche e di riferimento

Ranked by normalized popularity across sources. Queste risorse restano accessibili separatamente e non partecipano alla classifica principale.

  1. 1
    AttivoApri fonte ↗

    Molavi Agent Skills: Curated AI agent skills and MCP configs for Antigravity, Cursor, Codex & Claude — by Taghi Molavi

    githubRisorsacrescita misurata
    8stelle GitHubstabile