by Wenzhi-Ding · Agent Tool · ★ 76
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
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 | 76 |
| Forks | 1 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 48/100 |
| Last Updated | 2026-10-01 |
| Created | 2026-08-14 |
| Platforms | python |
| Est. Tokens | ~13k |
wenzhi-plugins 给 coding agent 的行为插件仓库：humanize 注入「说人话」写作规则，skill-stats 统计技能触发来源。ZCode 可直接订阅本市场；用其他 coding agent 的，把仓库地址发给你的 agent、让它照仓库迁移适配，同样能用上。各插件的完整说明见各自目录下的 README。 插件 humanize 通过 UserPromptSubmit hook 在每条用户消息后注入一段「说人话」要求，抑制残句、翻译腔和空洞大词；会话回复和为用户起草的产出物（论文、报告、对外邮件等）都适用，可随时用开关文件关闭。 详见 plugins/humanize/README.md。 skill-stats 统计每个技能（skill）被触发的次数，并区分触发来源：你在输入框敲 触发，还是 agent 在任务中主动选择调用。在会话里输入...
Explore other popular agent tool 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: