Die Werkzeugbeschreibungen sind auf Englisch.
Token-Effizienz
Werkzeuge zur Senkung von Token-Kosten und Komprimierung von Kontext.
Anwendungsfall
Aktivität
Sortieren nach
43
Werkzeug-Rangliste
Gemischte Rangfolge: Gemessenes Wachstum hat Vorrang. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.
- 1Aktiv
Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.
mcpgemessenes WachstumQuelle öffnen ↗
Installieren
claude mcp add tokentrust -- uvx tokentrust-cli0GitHub-Sternestabil - 2Aktiv
Measure and shrink the token cost of Claude Code skills, tier by tier: the always-on system-prompt tax, the per-invocation body, and on-demand references, each priced at the rate it is actually billed.
githubgemessenes WachstumQuelle öffnen ↗
1GitHub-Sternestabil - 3Aktiv
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/hush47GitHub-Sterne+4 (+9.3 %) - 4Aktiv
SpanishCaveMan
SkillClaude Code skill: caveman-style token efficiency, spoken with a real Spanish regional accent
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add Mun1to/SpanishCaveMan2GitHub-Sternestabil - 5Aktiv
Persistent memory for any AI — zero token cost until recall
mcpgemessenes WachstumQuelle öffnen ↗
44GitHub-Sterne+3 (+7.3 %) - 6Aktiv
cycgraph
AgentAgent context compressor and memory persistent orchestration
githubgemessenes WachstumQuelle öffnen ↗
2GitHub-Sternestabil - 7Aktiv
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…
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add sup3x/claude-code-eco33GitHub-Sternestabil - 8Aktiv
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 %) - 9Aktiv
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.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add ww-w-ai/super-token-saver31GitHub-Sternestabil - 10Aktiv
harnessay
SkillProfile Claude Code context, discover repeated workflows, and regression-test your skills. Local-only, zero-dependency.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add nks0614/harnessay5GitHub-Sterne+2 (+66.7 %) - 11Aktiv
skill-manager
SkillAutomatically detect and disable irrelevant Claude Code skills per project to save tokens and streamline your tech workflow.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
git clone https://github.com/mrdenox109-nyx/skill-manager ~/.claude/skills/skill-manager5GitHub-Sternestabil - 12Aktiv
razor
Skill🪒 YAGNI enforcement at the harness level, nudges toward the simplest solution and gates against unnecessary dependencies, file sprawl, and unchecked build growth.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add V-Songbird/razor8GitHub-Sterne+1 (+14.3 %) - 13Aktiv
distil
MCPContext optimization for LLM agents: tool registry, result masking, budgeting, compaction.
mcpgemessenes WachstumQuelle öffnen ↗
Installieren
claude mcp add distil -- npx @munhq/distil1GitHub-Sternestabil - 14Aktiv
pdf-text-router
SkillA Claude Code hook that routes each Read on a PDF to the path that actually works: text layer to UTF-8 text, scans to vision, and neither one through poppler.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add WatsonTsai/pdf-text-router7GitHub-Sternestabil - 15Aktiv
quiv
SkillThe Agent Knowledge Kit & Architecture System — 10–32x token-efficient architecture discovery for AI coding agents
githubgeschätztes MomentumQuelle öffnen ↗
Installieren
git clone https://github.com/chama-x/quiv ~/.claude/skills/quiv3GitHub-Sterne— - 16Aktiv
sidequest
SkillCut Claude Code token costs by delegating bulk LLM work to cheap models. 600+ models via NanoGPT, OpenRouter, Groq or local Ollama — batched, resumable, with real per-call cost tracking.
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add bicced/sidequest1GitHub-Sternestabil - 17Aktiv
RustAPI
BibliothekA high-performance, ergonomic web framework for Rust with native AI/LLM support.
githubgeschätztes MomentumQuelle öffnen ↗
61GitHub-Sterne—
Lern- und Referenzressourcen
Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.
- 1AktivQuelle öffnen ↗
Molavi Agent Skills: Curated AI agent skills and MCP configs for Antigravity, Cursor, Codex & Claude — by Taghi Molavi
githubRessourcegemessenes Wachstum8GitHub-Sternestabil