simplify-codebase — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 tt-a1i · Codex Skill · ★ 432

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is simplify-codebase safe to install? View the security audit →

About simplify-codebase

Simplify Codebase 先证明,再删除。让代码库少维护一些事实、状态与契约。 是一个面向现有代码库的 Agent Skill。它帮助编码智能体识别并安全移除偶然复杂度,同时保护仍然有效的行为、边界与兼容性。 它不追求“删得多”。它关心的是:一次改动能否减少团队今后必须持续保持一致的概念和义务。 为什么需要它 代码库里的冗余很少只是“某个函数没人调用”。它也可能是重复状态、失去所有者的抽象、只剩测试消费的接口、早已无效的兼容路径,或者被保留在共享文件中的半截功能。 静态检查可以提供线索,但不能单独证明一项删除是安全的。这个 Skill 会继续追踪运行时消费者、动态注册、持久化格式、公共接口、历史决策与验证边界,再决定应该删除、合并、保留,还是标记为暂时无法判断。 核心原则: 删除代码行只是结果。真正的收益是删除一个需要长期维护的事实、状态、契约或概念。 工作方式 每个候选都要形成一份证明记录: 它位于哪个所有权边界、符号、文件,以及能够验证时的行号; 它增加了什么维护负担; 生产、测试、动态和外部消费者分别是谁; 完整删除边界在哪里,包括共享文件内部的成员; 会放弃什么可观察行为或兼容性; 哪个最小验证可以揭示错误删除; 减少的复杂度是否大于新引入的迁移或替代机制。 它会谨慎对待 公共 API、动态加载和插件注册; 数据格式、迁移、回放与向后兼容; 授权、隔离、输入校验和数据丢失防护; 并发、取消、清理和生命周期所有权; 生成文件、共享资源和仓库外消费者; 仍然有效的 ADR、RFC 与架构约束。 发现真实消费者、边界尚未查清,或者简化只是把复杂度搬到别处时,它会建议保留,而不是为了输出结果强行删除。 安装 让 Codex 安装: text Insta

agent-skillsai-agentscode-qualitycodebasecodexdeveloper-toolsrefactoring

Quick Facts

Stars432
Forks15
LanguageHTML
CategoryCodex Skill
LicenseMIT
Quality Score63.9134621942368/100
Open Issues2
Last Updated2026-09-04
Created2026-08-24
Platformscodex
Est. Tokens~16k

Compatible Skills

These tools work well together with simplify-codebase for enhanced workflows:

simplify-codebase alternative? Top 6 similar tools

Looking for a simplify-codebase alternative? If you're comparing simplify-codebase 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.

  • pilot-shell by maxritter · ⭐ 2.1k

    Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software

  • brooks-lint by hyhmrright · ⭐ 1.5k

    AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severit

  • claude-code-workflows by shinpr · ⭐ 682

    Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.

  • roam-code by Cranot · ⭐ 518

    Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman

  • claude-workflow-v2 by CloudAI-X · ⭐ 1.4k

    Universal Claude Code workflow plugin with agents, skills, hooks, and commands

  • codesight by Houseofmvps · ⭐ 1.3k

    Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Co

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular HTML Agent Tools

Frequently Asked Questions

What is simplify-codebase?

simplify-codebase is Prove and remove accidental codebase complexity without breaking behavior.. It is categorized as a Codex Skill with 432 GitHub stars.

What programming language is simplify-codebase written in?

simplify-codebase is primarily written in HTML. It covers topics such as agent-skills, ai-agents, code-quality.

How do I install or use simplify-codebase?

You can find installation instructions and usage details in the simplify-codebase GitHub repository at github.com/tt-a1i/simplify-codebase. The project has 432 stars and 15 forks, indicating an active community.

What license does simplify-codebase use?

simplify-codebase is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to simplify-codebase?

The top alternatives to simplify-codebase on Agent Skills Hub include pilot-shell, brooks-lint, claude-code-workflows. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Codex Skill tools