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

90 entries in this view.

Tool ranking

Ranked by normalized popularity 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.

  1. 1

    CLI
    Active

    CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

    githubmeasured growthOpen source ↗

    78 349GitHub stars+703 (+0.91 %)
  2. 2

    MCP
    Active

    Compress 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 629GitHub stars+784 (+1.2 %)
  3. 3
    Active

    Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

    githubmeasured growthOpen source ↗

    2 122GitHub stars+108 (+5.4 %)
  4. 4

    MCP
    Active

    Context 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 ↗

    433GitHub stars+5 (+1.2 %)
  5. 5
    Active

    23 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-market

    333GitHub stars+2 (+0.60 %)
  6. 6

    MCP
    Active

    MCP 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/cli

    222GitHub stars+6 (+2.8 %)
  7. 7

    Skill
    Active

    Governance 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-os

    155GitHub stars+8 (+5.4 %)
  8. 8
    Active

    Lossless context compression plugin for Claude Code & OpenCode.

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add aerovato/magic-compact

    146GitHub stars+1 (+0.69 %)
  9. 9

    Skill
    Active

    Content-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-saver

    142GitHub stars+2 (+1.4 %)
  10. 10

    Skill
    Active

    Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add 0xhimanshu/governor

    133GitHub stars+3 (+2.3 %)
  11. 11

    Skill
    Active

    Claude 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-skill

    117GitHub starsstable
  12. 12
    Active

    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 %)
  13. 13
    Active

    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-optimizer

    103GitHub stars+6 (+6.2 %)
  14. 14

    Skill
    Dormant

    Pith is the hook that makes Claude Code sessions last 3x longer.

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add abhisekjha/pith

    98GitHub starsstable
  15. 15
    Dormant

    A Claude Code skill for web report decks — richer ECharts charts, one file per slide (edit one page, save tokens), and complex structure diagrams. 16:9 & vertical, PDF/image export.网页版 PPT 汇报的 Claude Code skill:ECharts 把数据画得更好看、每页一个文件改一页省…

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/myunwang/ppt-report-skills ~/.claude/skills/ppt-report-skills

    81GitHub starsstable
  16. 16

    Skill
    Active

    Agent 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/Tokdash

    67GitHub stars+3 (+4.7 %)
  17. 17
    Dormant

    SpiderBrain v3 is a multi-platform skill/framework to reduce token usage and AI hallucinations across Claude, Cursor, and other AI tools.

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/abhishek-performdigital/Spiderbrain-V3 ~/.claude/skills/Spiderbrain-V3

    65GitHub starsstable
  18. 18
    Active

    Context 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
  19. 19

    Library
    Active

    A high-performance, ergonomic web framework for Rust with native AI/LLM support.

    githubestimated momentumOpen source ↗

    61GitHub stars
  20. 20

    Skill
    Active

    Own 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…

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/firish/webfetch ~/.claude/skills/webfetch

    55GitHub starsstable
  21. 21
    Active

    Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

    githubmeasured growthOpen source ↗

    55GitHub stars+1 (+1.9 %)
  22. 22

    Skill
    Active

    Claude Code skills for developers who code like cats — never more effort than the problem requires.

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/albertobarnabo/lazy-cat ~/.claude/skills/lazy-cat

    50GitHub starsstable
  23. 23

    Skill
    Active

    🤫 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/hush

    47GitHub stars+4 (+9.3 %)
  24. 24
    Dormant

    ⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add Madhan230205/token-reducer

    44GitHub starsstable

Learning resources

Ranked by normalized popularity across sources. These resources remain available separately and do not take part in the main tool ranking.

  1. 1
    ActiveOpen source ↗

    Make 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.

    github

    Install git clone https://github.com/alexgreensh/outsourcerer ~/.claude/skills/outsourcerer

    Resourcemeasured growth
    142GitHub stars+3 (+2.2 %)