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

    MCP
    Active

    Persistent memory for any AI — zero token cost until recall

    RustLicense: Apache-2.0

      mcpmeasured growthOpen source ↗

      44GitHub stars+3 (+7.3 %)
    • 2

      MCP
      Dormant

      Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.

      PythonLicense: MIT
      • claude
      • claude-code
      • claude-code-plugin
      • cli
      • context-window

      githubmeasured growthOpen source ↗

      35GitHub starsstable
    • 3

      Skill
      Dormant

      Convert long AI conversations into portable conversation state graphs for LLM handoffs.

      License: MIT
      • age
      • agent
      • ai
      • chatgpt
      • claude-ai

      githubmeasured growthOpen source ↗

      Install git clone https://github.com/Adityapal67/context-graph-compressor ~/.claude/skills/context-graph-compressor

      35GitHub starsstable
    • 4

      Skill
      Active

      Eco 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…

      JavaScriptLicense: MIT
      • ai-agents
      • anthropic
      • claude
      • claude-ai
      • claude-code

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add sup3x/claude-code-eco

      33GitHub starsstable
    • 5

      Skill
      Active

      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.

      PythonLicense: MIT
      • ai-agent
      • ai-coding
      • anthropic
      • claude
      • claude-code

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add NodeNestor/claude-rolling-context

      31GitHub stars+1 (+3.3 %)
    • 6

      Skill
      Active

      Restore prior Claude Code AND Codex sessions with zero LLM calls. Cross-tool session handoff, cache-expiry prevention, real cost dashboard. One plugin, both hosts.

      JavaScriptLicense: Apache-2.0
      • anthropic-api
      • api-cost
      • billing-analytics
      • cache-management
      • claude-code

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add ww-w-ai/super-token-saver

      31GitHub starsstable
    • 7

      Skill
      Dormant

      Give your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.

      Python
      • agent-teams
      • ai-agents
      • anthropic
      • claude
      • claude-ai

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add Gr122lyBr/claude-teams-brain

      26GitHub starsstable
    • 8

      Skill
      Active

      Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.

      License: MIT
      • agent-skills
      • ai-agents
      • anthropic
      • claude
      • claude-code

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add AndyShaman/senior-fable

      23GitHub starsstable
    • 9

      Skill
      Active

      Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents

      HTMLLicense: MIT
      • anthropic
      • claude-code
      • claude-code-plugin
      • fable
      • hooks

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add realgarit/fable-baton

      22GitHub starsstable
    • 10

      Skill
      Active

      Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.

      PythonLicense: MIT
      • cache-optimization
      • claude-code
      • claude-code-plugin
      • cost-optimization
      • deepseek

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add jianzhichun/permafrost

      21GitHub starsstable
    • 11

      Skill
      Active

      Token-efficient Claude Code workspace with parallel agents and persistent memory. Research → Plan → Implement → Validate workflow.

      JavaScript
      • agent-memory
      • agentic-coding
      • ai-agents
      • ai-coding
      • claude-code-commands

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add coalesce-labs/catalyst

      20GitHub starsstable
    • 12

      Skill
      Active

      Token-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.

      PythonLicense: MIT
      • ai-assistant
      • anthropic
      • brevity
      • claude
      • claude-code

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add GabrielBarberini/laconic

      19GitHub starsstable
    • 13

      MCP
      Active

      A MCP that turns PDFs into structured text, tables, figures, metadata, annotations, and page-level evidence for selective retrieval by MCP-compatible AI agents. Improves the information quality AI agents receive while also reducing token…

      JavaScriptLicense: AGPL-3.0
      • ai
      • ai-tools
      • claude
      • claude-code
      • claude-code-plugin

      githubmeasured growthOpen source ↗

      17GitHub starsstable
    • 14

      Skill
      Active

      Claude Code skill — delegate coding tasks to Opencode, supervise via git diff & save 50-90% Claude token usage

      Python
      • claude
      • claude-skills
      • delegation
      • opencode
      • orchestration

      githubmeasured growthOpen source ↗

      Install git clone https://github.com/pcx-wave/opencode-skill ~/.claude/skills/opencode-skill

      17GitHub stars+1 (+6.2 %)
    • 15

      Agent
      Active

      Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.

      PythonLicense: Apache-2.0
      • a2a
      • ag-ui
      • agentic-ai
      • ai-agents
      • ai-coding

      githubmeasured growthOpen source ↗

      16GitHub starsstable
    • 16

      MCP
      Dormant

      DAG-based Lossless Context Management for Claude Code. Every message preserved, summaries cascade as a DAG, patterns extracted via Lossless Dream — full recall and reflection across sessions.

      PythonLicense: MIT
      • claude
      • claude-code
      • claude-code-plugin
      • coding-agent
      • context-management

      githubmeasured growthOpen source ↗

      15GitHub starsstable
    • 17

      Skill
      Active

      Staged context pruning for OpenCode, Oh My Pi, pi, and Claude Code.

      TypeScriptLicense: AGPL-3.0
      • ai
      • ai-agents
      • claude-code
      • claude-code-plugin
      • coding-agent

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add AshishKumar4/better-compact

      12GitHub stars+1 (+9.1 %)
    • 18

      Skill
      Active

      Claude Code skill — delegate coding tasks to Gemini CLI and supervise via git diff

      Python
      • claude
      • claude-code
      • claude-skill
      • claude-skill-recommended
      • claude-skills

      githubestimated momentumOpen source ↗

      Install git clone https://github.com/pcx-wave/gemini-skill ~/.claude/skills/gemini-skill

      12GitHub stars—
    • 19

      Skill
      Dormant

      Say more with less. Claude Code skill/plugin that cuts ~60-70% of output tokens while keeping natural, readable English.

      ShellLicense: MIT
      • ai-coding
      • claude-code
      • claude-code-plugin
      • claude-code-plugins
      • claude-code-skill

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add o4f6bgpac3/concise

      10GitHub stars+2 (+25.0 %)
    • 20

      CLI
      Dormant

      Optimize Claude Code token usage — 22 skills, 8 hooks, 6 rules. One npm install. Zero manual steps. Cut costs by 67%.

      ShellLicense: MIT
      • ai
      • ai-coding
      • anthropic
      • claude
      • claude-code

      githubmeasured growthOpen source ↗

      9GitHub starsstable
    • 21

      Skill
      Active

      对标 claude-hud 核心功能，控制在 7 行以内更轻量。内置 13 个国产大模型平台用量查询 (智谱 GLM / MiniMax / DeepSeek / Kimi / StepFun / SiliconFlow 等)，第三方代理用户也能实时看到额度消耗。

      TypeScriptLicense: MIT
      • anthropic
      • claude
      • claude-code
      • claude-code-plugin
      • cli

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add zander-zyx/claude-mini-hud

      9GitHub starsstable
    • 22

      Skill
      Active

      mcp-recall compresses MCP tool outputs (94 KB → 3.5 KB · 96%) and stores full results in SQLite for retrieval — up to 30x more tool calls per session for heavy MCP workloads.

      TypeScriptLicense: MIT
      • bun
      • claude
      • claude-code
      • claude-code-plugin
      • context-window

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add sakebomb/mcp-recall

      8GitHub starsstable
    • 23

      Skill
      Active

      Compact Claude Code statusline — zero-dependency, crash-free on Windows

      TypeScriptLicense: MIT
      • claude
      • claude-code
      • claude-code-plugin
      • context-window
      • deepseek

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add WaterTian/cc-hud

      8GitHub starsstable
    • 24

      MCP
      Active

      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 +…

      TypeScriptLicense: MIT
      • agent-security
      • ai-agent-memory
      • ai-agents
      • audit-trail
      • claude-code

      githubmeasured growthOpen source ↗

      8GitHub starsstable
    • 25

      Skill
      Active

      🪒 YAGNI enforcement at the harness level, nudges toward the simplest solution and gates against unnecessary dependencies, file sprawl, and unchecked build growth.

      JavaScriptLicense: MIT
      • ai
      • anthropic
      • claude
      • claude-code
      • claude-code-plugin

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add V-Songbird/razor

      8GitHub stars+1 (+14.3 %)