by ZiChuanLan · Codex Skill · ★ 238
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
npm i -g agent-purge # 或 npx agent-purge webTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
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 | 238 |
| Forks | 258 |
| Language | JavaScript |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 66/100 |
| Last Updated | 2026-10-26 |
| Created | 2026-10-25 |
| Platforms | browser, claude-code, codex, node |
| Est. Tokens | ~10k |
agent-purge 一份系统提示词，喂给多个 coding agent。支持替换（replace）、追加（append）、清空（off）三种模式，可热切换，全程可逆。 它做什么 每家 coding agent 读系统提示词的位置都不一样：有的认启动参数，有的认配置文件，有的只能靠插件改运行时对象。agent-purge 把这些入口统一成三件事： 三层都写的是同一份 的正文。 或 Web 总开关关掉时，全部撤回到原样——不留残渣。 安装 要求 Node ≥ 20，零依赖。 数据独立存放，升级不会被覆盖：默认 （Windows ），里面是 和 。想换位置就设环境变量： 旧版本（0.1.x）把数据放在包目录里，首次运行会自动搬到新家，原文件不动。 人设 = frontmatter（ / / / / ）+ 正文。正文就是会被写进系统提示词的那一段。 首次运行会在 下生成 起步模板。 支持情况...
These tools work well together with agent-purge for enhanced workflows:
Looking for a agent-purge alternative? If you're comparing agent-purge 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.
Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, H
Self-hosted mission control for AI coding agents: run Claude Code, OpenCode, Pi, Codex, and Antigravity & Gemi
Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Disco
📼 Declarative AI agent environment manager, written in Rust
Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 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: