HeyCubit/effortless

Mods for Claude Code. effortless picks the reasoning effort for every prompt and shows the cache countdown. textless (desktop app) shows art, quotes and chess instead of the wall of text while Claude works.

What it solves

Claude Code can be expensive because it often uses high-effort settings for every task. This plugin automatically adjusts the model's reasoning effort based on the complexity of your prompt, saving money on simple tasks while maintaining high performance for difficult ones.

How it works

It adds a plugin to Claude Code that uses a "judge" (powered by Haiku 5.5 or an optional Jev key) to analyze every prompt before it runs. It assigns a Low, Medium, or High effort level accordingly. It also provides a status bar in your chat that tracks context usage, prompt cache health, and offers one-click tools for compacting chats or performing "handoffs" to start fresh sessions when context becomes too heavy.

Who it’s for

Developers who use Claude Code and want to reduce API costs without manually managing effort settings or sacrificing the quality of their coding assistance.

Highlights

  • Reduces costs by up to 42% on real coding tasks compared to standard high-effort settings.
  • Includes a visual status bar to monitor chat context, cache duration, and system health.
  • Automates chat compaction and session handoffs to keep performance fast and costs low.
  • Offers a "textless" companion mod to replace verbose step-by-step logs with pixel art while the model is working.
  • Fully open-source and runs locally on your machine with no external data sharing beyond the judge prompt.

Related

  • Project
    runtm-ai/runtm

    An open-source platform providing secure, isolated sandboxes for AI coding agents to build and deploy software to live HTTPS endpoints.

  • Project
    fivetaku/cc101

    CC101 is an open-source Korean/English guide that walks beginners through Claude Code from installation to advanced features like CLAUDE.md, MCP, Skills, and Hooks, presented as a fast, mobile-friendly static website.

  • Project
    Prorise-cool/Claude-Code-Multi-Agent

    Claude Code Multi‑Agent is an open‑source framework that gives Anthropic’s Claude Code project awareness and expert‑agent capabilities. It uses a Python Hook system and a locally‑run Ollama model to automatically detect the codebase type, analyse user intent, load 300+ domain‑specific “Skills” (backend, frontend, testing, security, etc.), and enforce automatic documentation (DEVELOPMENT.md, KNOWLEDGE.md, CHANGELOG.md). After cloning, installing Ollama, a model, and uv, you drop your project into the repo and Claude Code instantly knows its context, suggests appropriate tools, and can be driven with slash commands like `/backend‑specialist` or workflow commands such as `/kiro/spec`. Key points: - Zero‑config start; all configuration lives in `.claude/settings.json` and `prompts.json`. - Hooks run on session start, user prompt, tool use, etc., handling project detection, intent analysis, and doc updates. - Skills are defined by `SKILL.md` files and are auto‑discovered. - Works entirely locally (no external API), integrates with Git, and is MIT‑licensed. Ideal for developers or small teams who want a reproducible, on‑premise AI coding assistant.

  • Project
    tech-leads-club/harness-toolkit

    A security and governance toolkit for AI coding agents that enforces strict safety rules, prevents secret leaks, and mandates development workflows that agents cannot bypass.