by lokikill123 · Codex Skill · ★ 117
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Featured in: OpenAI Codex Skills
git clone https://github.com/lokikill123/codex-token-skills.git
Taken from the project's README on GitHub.
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 117 |
| Forks | 11 |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 63/100 |
| Last Updated | 2026-06-15 |
| Created | 2026-06-15 |
| Platforms | cli, codex |
| Est. Tokens | ~2k |
⚡ Codex Token Skills 专为 DeepSeek V4 Pro 优化的 Codex skill,大幅降低 token 消耗并提升前缀缓存命中率。 []() 为什么需要? DeepSeek V4 Pro 的前缀缓存机制:系统提示词 + 上下文文件越稳定,缓存命中率越高。如果你的 SKILL.md / AGENTS.md 频繁变动,每次对话都要重新处理全部上下文,浪费大量 token。 这两个 skill 的核心思路: Skill 列表 🔧 token-saver — 强制省 token Smart 双模式: 简单任务(修 bug、改配置、装东西):禁止 preamble、禁止计划、禁止解释、禁止验证 复杂任务(vibecoding、数据分析、架构设计):允许简短交流,但严格控制 实测预计省 60-80% token。 🧠 memory — 全局持久记忆...
Looking for a codex-token-skills alternative? If you're comparing codex-token-skills 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.
This repository contains documentation created to better understand the open project
Curated skills, profiles, and config templates that supercharge Codex CLI — multi-model, deep research, image
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
Codex Skills Library is a curated library of reusable Codex skills for developers, individuals, and teams.
Best Practices for Claude Code Configuration
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: