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 GODGOD126 · Codex Skill · ★ 129
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is self-improving-for-codex safe to install? View the security audit →
Self-improving for Codex 让 Codex 通过 与本地 Markdown 记忆文件形成可审计、可维护的长期改进闭环。 A Codex-native, file-based memory loop. No background service, telemetry, or OpenClaw-only runtime required. 为什么需要它 Codex 不会自动把任意文件当作长期记忆。这个 Skill 使用 Codex 原生的 作为稳定入口，把长期偏好、可复用经验、环境报错和能力缺口分别写入职责清晰的文件，避免把所有内容堆进一个不断膨胀的提示词。 核心能力 审计已有的全局 、记忆目录和相关自动化，优先保留现有配置。 建立并维护五类职责分离的记忆文件。 生成适合 Codex 的 集成片段。 定义从原始记录晋升到 / 的保守规则。 可选设计夜间精炼任务，用于去重、合并和清理过时内容。 明确区分 Codex 原生能力与 OpenClaw 的 、 等专用机制。 安装 将仓库克隆到 Codex 的全局 Skill 目录： 重新打开 Codex，确认技能列表中出现 。 使用 在 Codex 中直接说明要使用这个 Skill，例如： 也可以用中文： text 使用 self-improving-for-codex 检查我现有的 AGENTS.md 和 memories，保留已有内容
| Stars | 129 |
| Forks | 17 |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 49.1223488024933/100 |
| Open Issues | 1 |
| Last Updated | 2026-08-11 |
| Created | 2026-03-19 |
| Platforms | codex |
| Est. Tokens | ~1k |
Looking for a self-improving-for-codex alternative? If you're comparing self-improving-for-codex with other codex skill tools, these 3 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
开源了Codex Skills等集合，大部分是自己实际需要搞得，需要的自取。欢迎star
Skills for agentic development on Solana
A Codex/Claude skill that maintains per-repo operating theory documents.
Explore other popular codex skill tools:
self-improving-for-codex is A Codex-native self-improving skill based on AGENTS.md, memories, and nightly review automation.. It is categorized as a Codex Skill with 129 GitHub stars.
You can find installation instructions and usage details in the self-improving-for-codex GitHub repository at github.com/GODGOD126/self-improving-for-codex. The project has 129 stars and 17 forks, indicating an active community.
self-improving-for-codex is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to self-improving-for-codex on Agent Skills Hub include skills, solana-dev-skill, theorist. 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: