by Kulaxyz · Codex Skill · ★ 500
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Always-on token-efficiency skill for coding agents (Claude Code, Codex, Cursor, Windsurf, Cline). ~31% lower bill on average, no loss of correctness.
| Stars | 500 |
| Forks | 4 |
| Language | Shell |
| Category | Codex Skill |
| Quality Score | 48.6445355213528/100 |
| Last Updated | 2026-07-04 |
| Created | 2026-07-03 |
| Platforms | claude-code, cli, codex |
| Est. Tokens | ~1k |
Looking for a token-diet alternative? If you're comparing token-diet with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery,
A Claude or Codex skill for deliberate skill development during AI-assisted coding
Skills for pi coding agent (compatible with Claude Code and Codex CLI)
AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart sear
Supercharge AI coding agents with portable skills. Install, translate & share skills across Claude Code, Curso
Free, open-source desktop manager for AI Agent Skills. Write a skill once, sync it to 32 AI coding tools (Clau
Explore other popular codex skill tools:
token-diet is Always-on token-efficiency skill for coding agents (Claude Code, Codex, Cursor, Windsurf, Cline). ~31% lower bill on average, no loss of correctness.. It is categorized as a Codex Skill with 500 GitHub stars.
token-diet is primarily written in Shell.
You can find installation instructions and usage details in the token-diet GitHub repository at github.com/Kulaxyz/token-diet. The project has 500 stars and 4 forks, indicating an active community.
The top alternatives to token-diet on Agent Skills Hub include agent-skill-creator, learning-opportunities, pi-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: