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
90
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.
- 1Attivo
SpanishCaveMan
SkillClaude Code skill: caveman-style token efficiency, spoken with a real Spanish regional accent
githubcrescita misurataApri fonte ↗
Installa
/plugin marketplace add Mun1to/SpanishCaveMan2stelle GitHubstabile - 244stelle GitHubstabile
- 3Attivo
Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files.
mcpcrescita misurataApri fonte ↗
Installa
claude mcp add agent-booster -- uvx agent-booster1stelle GitHubstabile - 4Attivo
MCP server that cuts AI coding agent token usage via framework-aware context optimization
mcpcrescita misurataApri fonte ↗
Installa
claude mcp add ai-optimizer -- npx @ai-optimizer/core0stelle GitHubstabile - 5Attivo
vibe-skill
SkillClaude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage
githubcrescita misurataApri fonte ↗
Installa
git clone https://github.com/pcx-wave/vibe-skill ~/.claude/skills/vibe-skill117stelle GitHubstabile - 6Attivo
Pay-per-call agent APIs over x402: web scraping, token compression, and semantic cache.
mcpcrescita misurataApri fonte ↗
Installa
claude mcp add gate402-mcp -- npx gate402-mcp2stelle GitHubstabile - 7Dormiente
Few-Word
SkillClaude Code plugin that offloads large outputs to filesystem and retrieves when required.
githubcrescita misurataApri fonte ↗
Installa
/plugin marketplace add sheeki03/Few-Word38stelle GitHubstabile - 8Attivo
laconic
SkillToken-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.
githubcrescita misurataApri fonte ↗
Installa
/plugin marketplace add GabrielBarberini/laconic19stelle GitHubstabile - 9Dormiente
rosetta
AltroTranslate any language to English before Claude processes it. ~49% token savings combined with caveman.
githubcrescita misurataApri fonte ↗
2stelle GitHubstabile - 10Dormiente
unclog
MCPAudit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.
githubcrescita misurataApri fonte ↗
35stelle GitHubstabile - 11Dormiente
Analyze your MCP setup: token costs, grades, duplicates, and optimization tips
mcpcrescita misurataApri fonte ↗
Installa
claude mcp add mcp-checkup -- npx mcp-checkup1stelle GitHubstabile - 12Attivo
token-efficiency
SkillA Claude Code plugin that shows exactly where your AI coding session wasted tokens — and how to fix it. Flags waste, never quality. Runs locally.
githubcrescita misurataApri fonte ↗
Installa
/plugin marketplace add Jimmynycu/token-efficiency2stelle GitHubstabile - 13Dormiente
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-compressor35stelle GitHubstabile - 14Attivo
cc-hud
SkillCompact Claude Code statusline — zero-dependency, crash-free on Windows
githubcrescita misurataApri fonte ↗
Installa
/plugin marketplace add WaterTian/cc-hud8stelle GitHubstabile - 15Attivo
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 - 16Dormiente
Save tokens while coding — your AI agent gets structured code context, not file dumps.
mcpcrescita misurataApri fonte ↗
Installa
claude mcp add codeweave -- npx @codeweave/mcp4stelle GitHubstabile - 17Attivo
claude-code-eco
SkillEco 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-eco33stelle GitHubstabile - 18Dormiente
contextforge
SkillAgent context gate for Codex, Claude Code, Copilot, MCP, Cursor, Cline, Gemini and Windsurf repos
githubcrescita misurataApri fonte ↗
Installa
git clone https://github.com/grnbtqdbyx-create/contextforge ~/.claude/skills/contextforge1stelle GitHubstabile - 19Attivo
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-mcp4stelle GitHubstabile - 20Attivo
super-token-saver
SkillRestore 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-saver31stelle GitHubstabile - 21Attivo
Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
mcpcrescita misurataApri fonte ↗
Installa
claude mcp add compactprompt -- uvx compactprompt0stelle GitHubstabile - 22Attivo
Compact, source-linked context packs that reduce token waste for coding agents.
mcpcrescita misurataApri fonte ↗
Installa
claude mcp add capsule -- npx capsulectx4stelle GitHubstabile - 23Attivo
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-context31stelle GitHubstabile - 24Attivo
Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages.
githubcrescita misurataApri fonte ↗
Installa
/plugin marketplace add sofumel/claude-handoff-revive6stelle GitHubstabile - 25Attivo
A skill that shrink noisy log/output 60-90% before read — filter, group, dedupe, truncate. Cut token, cut cost, keep signal. By Dhayalan (aka Joy).
githubcrescita misurataApri fonte ↗
Installa
/plugin marketplace add Da-ya7/PromptCompressor-skill1stelle GitHubstabile