Die Werkzeugbeschreibungen sind auf Englisch.
Token-Effizienz
Werkzeuge zur Senkung von Token-Kosten und Komprimierung von Kontext.
Anwendungsfall
Aktivität
Sortieren nach
96
Werkzeug-Rangliste
Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.
- 1Aktiv
headroom
MCPCompress 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.
githubgemessenes WachstumQuelle öffnen ↗
68 221GitHub-Sterne+619 (+0.92 %) - 2Aktiv
rtk
CLICLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
githubgemessenes WachstumQuelle öffnen ↗
78 098GitHub-Sterne+671 (+0.87 %) - 3Aktiv
token-optimizer
SonstigeFind the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
githubgemessenes WachstumQuelle öffnen ↗
2 084GitHub-Sterne+120 (+6.1 %) - 4Aktiv
Pay-per-call agent APIs over x402: web scraping, token compression, and semantic cache.
mcpgemessenes WachstumQuelle öffnen ↗
Installieren
claude mcp add gate402-mcp -- npx gate402-mcp2GitHub-Sterne+1 (+100.0 %) - 5Aktiv
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.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add egorfedorov/claude-context-optimizer102GitHub-Sterne+7 (+7.4 %) - 6Aktiv
better-compact
SkillStaged context pruning for OpenCode, Oh My Pi, pi, and Claude Code.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add AshishKumar4/better-compact12GitHub-Sterne+2 (+20.0 %) - 7Aktiv
Persistent memory for any AI — zero token cost until recall
mcpgemessenes WachstumQuelle öffnen ↗
44GitHub-Sterne+3 (+7.3 %) - 8Aktiv
hush
Skill🤫 Token-lean sessions at the harness level. An easy to grasp output style, output-shrinking hooks, and log compression cut both input and output tokens.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add V-Songbird/hush45GitHub-Sterne+3 (+7.1 %) - 9Aktiv
llmtrim
MCPMCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
mcpgemessenes WachstumQuelle öffnen ↗
Installieren
claude mcp add llmtrim -- npx @llmtrim/cli222GitHub-Sterne+6 (+2.8 %) - 10Aktiv
agentic-os
SkillGovernance 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…
githubgemessenes WachstumQuelle öffnen ↗
Installieren
git clone https://github.com/KbWen/agentic-os ~/.claude/skills/agentic-os150GitHub-Sterne+5 (+3.4 %) - 11Ruhend
concise
SkillSay more with less. Claude Code skill/plugin that cuts ~60-70% of output tokens while keeping natural, readable English.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add o4f6bgpac3/concise9GitHub-Sterne+1 (+12.5 %) - 12Aktiv
Tokdash
SkillAgent 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..
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add JingbiaoMei/Tokdash66GitHub-Sterne+3 (+4.8 %) - 13Aktiv
governor
SkillClaude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add 0xhimanshu/governor133GitHub-Sterne+4 (+3.1 %) - 14Aktiv
skillreaper
MCPCut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
githubgemessenes WachstumQuelle öffnen ↗
54GitHub-Sterne+2 (+3.8 %) - 15Aktiv
fable-baton
SkillClaude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add realgarit/fable-baton22GitHub-Sterne+1 (+4.8 %) - 16Aktiv
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.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add NodeNestor/claude-rolling-context31GitHub-Sterne+1 (+3.3 %) - 17Aktiv
ratel
MCPContext 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.
githubgemessenes WachstumQuelle öffnen ↗
430GitHub-Sterne+3 (+0.70 %) - 18Aktiv
webfetch
SkillOwn 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/webfetch55GitHub-Sterne+1 (+1.9 %) - 19Aktiv
claude-night-market
Skill23 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…
githubgemessenes WachstumQuelle öffnen ↗
Installieren
git clone https://github.com/athola/claude-night-market ~/.claude/skills/claude-night-market332GitHub-Sterne+2 (+0.61 %) - 20Aktiv
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.
githubgemessenes WachstumQuelle öffnen ↗
115GitHub-Sterne+1 (+0.88 %) - 21Aktiv
vibe-skill
SkillClaude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage
githubgemessenes WachstumQuelle öffnen ↗
Installieren
git clone https://github.com/pcx-wave/vibe-skill ~/.claude/skills/vibe-skill118GitHub-Sterne+1 (+0.85 %) - 22Aktiv
token-saver
SkillContent-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.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add ppgranger/token-saver140GitHub-Sterne+1 (+0.72 %) - 23Aktiv
magic-compact
SkillLossless context compression plugin for Claude Code & OpenCode.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add aerovato/magic-compact144GitHub-Sterne+1 (+0.70 %) - 24Aktiv
dao-code
SonstigeOpen-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous…
githubgemessenes WachstumQuelle öffnen ↗
1 254GitHub-Sternestabil
Lern- und Referenzressourcen
Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.
- 1AktivQuelle öffnen ↗
outsourcerer
SkillMake 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.
githubInstallieren
Ressourcegemessenes Wachstumgit clone https://github.com/alexgreensh/outsourcerer ~/.claude/skills/outsourcerer142GitHub-Sterne+5 (+3.6 %)