No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by runesleo · Codex Skill · ★ 711
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claude-code-workflow safe to install? View the security audit →
QuietHarness：让你的 AI 编程 Agent 更可靠 中文 · English 给你已经在使用的 AI 编程 Agent 装上一层极小、可回滚的工作边界：先看现状、保留无关改动、按风险验证、对不可逆动作先确认。 只用 Claude Code、Codex 或 Cursor 中的一个就能获得同一组核心可靠性边界。 多端兼容是以后更换工具时可以带走这些边界，不是安装门槛。 QuietHarness 不会给每个请求套一层仪式，也不是要求你复制我的私人系统。它把我长期使用后仍值得保留的行为压缩成 1,604 字节共享 Core，并提供 dry-run、备份、隔离测试和可逆安装。 适合谁 适合正在用任意一种 AI 编程 Agent 维护真实项目，并遇到过这些问题的人： Agent 没检查现有改动就覆盖文件； 没运行测试，却把任务说成完成； 一个小修改被扩成不必要的重构和流程； 删除、发布、生产变更或凭证操作没有在正确位置停下来确认； 更换 Agent 后，又要从头重写同一套基本边界。 如果你需要完整任务数据库、后台自动化或团队编排平台，QuietHarness 本身并不提供这些能力；后文的 Leo System 只是可选参考。 先在一个隔离项目试用 下面三个选项只选一个。先 dry-run 查看精确目标，再执行 ；试用规则只写入 ，不会改动你的用户级 Claude/Codex 配置。 Claude Code 写入 与 。 Codex 只写入 。 Cursor bash ./scripts/install.sh --dry-run --cursor-project "$demodir" ./scripts/install.sh --apply --cursor-project "$d
| Stars | 711 |
| Forks | 88 |
| Language | Shell |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 67.4912685155845/100 |
| Last Updated | 2026-09-18 |
| Created | 2026-03-03 |
| Platforms | claude-code, cli, codex |
| Est. Tokens | ~12k |
These tools work well together with claude-code-workflow for enhanced workflows:
Looking for a claude-code-workflow alternative? If you're comparing claude-code-workflow 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.
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
471 plugins, 3,069 skills, 347 agents for Claude Code. Open-source marketplace at tonsofskills.com with the cc
Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery,
everything-claude-code 中文翻译项目：完整的 Claude Code 配置集合（agents, skills, hooks, commands, rules, MCPs）。源自 Anthropic
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM
Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucke
Explore other popular codex skill tools:
claude-code-workflow is QuietHarness：Claude Code、Codex、Cursor 共用的轻量 AI 工作系统. It is categorized as a Codex Skill with 711 GitHub stars.
claude-code-workflow is primarily written in Shell. It covers topics such as agent-workflow, ai-agents, claude-code.
You can find installation instructions and usage details in the claude-code-workflow GitHub repository at github.com/runesleo/claude-code-workflow. The project has 711 stars and 88 forks, indicating an active community.
claude-code-workflow is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to claude-code-workflow on Agent Skills Hub include Overture, claude-code-plugins-plus-skills, agent-skill-creator. 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: