token-efficiency
By undefdev
Automatically minimize token consumption in bash commands, file reads, JSON/YAML/TOML/CSV processing, and code searches during AI coding sessions, using efficient tools like jq, yq, awk, and ast-grep, triggered on session start, clear, or compact.
npx claudepluginhub undefdev/token-efficiency --plugin token-efficiencyComponent Overview
Component Details
Hooks (1)
README
Token Efficiency
A skill that teaches coding agents to minimize token waste in all tool use, file reading, and data processing operations.
Every byte of tool output is money and context window spent. This skill instills the habit of filtering, projecting, and truncating at the source — not dumping raw output and hoping for the best.
Sunset notice: This skill exists because current coding agents haven't yet internalized efficient tool use. As models improve and these practices become default behavior, this skill will be discontinued.
What it covers
- Structured query tools (
jq,yq,awk) over dump-and-read - Precision search (
ast-grep,rg) over broad text search - Git summary-first workflows (
--stat,--name-only) - Output noise suppression (quiet flags,
NO_COLOR, selective reads) - Hash-based change detection over re-reading files
- Coreutils over Python for simple transforms
Installation
Claude Code
First, add the marketplace:
/plugin marketplace add undefdev/token-efficiency
Then install:
/plugin install token-efficiency@undefdev-token-efficiency
Cursor
Not yet available on the Cursor Marketplace. For now, clone the repo and add the skill content to your project's rules manually.
Gemini CLI
gemini extensions install https://github.com/undefdev/token-efficiency
Codex
OpenCode
Similar Plugins
token-optimizer
Audit, fix, and monitor Claude Code context window usage. Find the ghost tokens.
alexgreenshclaude-slim
Analyze and reduce Claude Code token overhead
conserve
Resource optimization and performance monitoring toolkit for efficient Claude Code workflows
claude-cost-optimizer
Cost-conscious mode for Claude Code. Saves 30-60% on costs through concise responses, model routing, and efficient workflow patterns.
Sagargupta16pith
Token optimization for Claude Code. Automatic tool output compression (40-60% reduction), token meter in statusline, auto-compact at 70% context, structured output formats, self-building project wiki, URL ingestion, Karpathy compile pass, and semantic lint.
Help us improve
Share bugs, ideas, or general feedback.
