Token efficiency: tools for developers
Tools that reduce token costs, compress context or cache LLM requests. An entry can appear under several use cases when its topics or description provide several explicit signals.
Use case
Activity
Sort by
50 entries in this view.
Tool ranking
Ranked by measured growth, normalized across sources. Raw values keep their source-specific window, shown under each tool; a change requires at least two snapshots from the last 7 days.
- 1Active
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.
githubmeasured growthOpen source ↗
68 221GitHub stars+619 (+0.92 %) - 2Active
rtk
CLICLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
githubmeasured growthOpen source ↗
78 098GitHub stars+671 (+0.87 %) - 3Active
token-optimizer
OtherFind the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
githubmeasured growthOpen source ↗
2 084GitHub stars+120 (+6.1 %) - 4Active
Pay-per-call agent APIs over x402: web scraping, token compression, and semantic cache.
mcpmeasured growthOpen source ↗
Install
claude mcp add gate402-mcp -- npx gate402-mcp2GitHub stars+1 (+100.0 %) - 5Active
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.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add egorfedorov/claude-context-optimizer102GitHub stars+7 (+7.4 %) - 6Active
better-compact
SkillStaged context pruning for OpenCode, Oh My Pi, pi, and Claude Code.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add AshishKumar4/better-compact12GitHub stars+2 (+20.0 %) - 744GitHub stars+3 (+7.3 %)
- 8Active
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.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add V-Songbird/hush45GitHub stars+3 (+7.1 %) - 9Active
llmtrim
MCPMCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
mcpmeasured growthOpen source ↗
Install
claude mcp add llmtrim -- npx @llmtrim/cli222GitHub stars+6 (+2.8 %) - 10Active
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…
githubmeasured growthOpen source ↗
Install
git clone https://github.com/KbWen/agentic-os ~/.claude/skills/agentic-os150GitHub stars+5 (+3.4 %) - 11Active
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..
githubmeasured growthOpen source ↗
Install
/plugin marketplace add JingbiaoMei/Tokdash66GitHub stars+3 (+4.8 %) - 12Active
skillreaper
MCPCut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
githubmeasured growthOpen source ↗
54GitHub stars+2 (+3.8 %) - 13Active
fable-baton
SkillClaude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents
githubmeasured growthOpen source ↗
Install
/plugin marketplace add realgarit/fable-baton22GitHub stars+1 (+4.8 %) - 14Active
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.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add NodeNestor/claude-rolling-context31GitHub stars+1 (+3.3 %) - 15Active
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.
githubmeasured growthOpen source ↗
430GitHub stars+3 (+0.70 %) - 16Active
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…
githubmeasured growthOpen source ↗
Install
git clone https://github.com/athola/claude-night-market ~/.claude/skills/claude-night-market332GitHub stars+2 (+0.61 %) - 17Active
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.
githubmeasured growthOpen source ↗
115GitHub stars+1 (+0.88 %) - 18Active
vibe-skill
SkillClaude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage
githubmeasured growthOpen source ↗
Install
git clone https://github.com/pcx-wave/vibe-skill ~/.claude/skills/vibe-skill118GitHub stars+1 (+0.85 %) - 19Active
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.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add ppgranger/token-saver140GitHub stars+1 (+0.72 %) - 20Active
magic-compact
SkillLossless context compression plugin for Claude Code & OpenCode.
githubmeasured growthOpen source ↗
Install
/plugin marketplace add aerovato/magic-compact144GitHub stars+1 (+0.70 %) - 21Active
sqz
MCPPre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
mcpmeasured growthOpen source ↗
609GitHub starsstable - 22Active
toonify-mcp
MCPContext compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.
githubmeasured growthOpen source ↗
64GitHub starsstable - 23Active
RustAPI
LibraryA high-performance, ergonomic web framework for Rust with native AI/LLM support.
githubmeasured growthOpen source ↗
61GitHub starsstable - 24Active
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…
githubmeasured growthOpen source ↗
Install
/plugin marketplace add sup3x/claude-code-eco33GitHub starsstable
Learning resources
Ranked by measured growth, normalized across sources. These resources remain available separately and do not take part in the main tool ranking.
- 1ActiveOpen source ↗
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.
githubInstall
Resourcemeasured growthgit clone https://github.com/alexgreensh/outsourcerer ~/.claude/skills/outsourcerer142GitHub stars+5 (+3.6 %)