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 johnfkoo951 · Codex Skill · ★ 70
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is cmds-llm-wiki safe to install? View the security audit →
cmds-llm-wiki LLM Wiki 볼트 템플릿 — Karpathy LLM Wiki pattern + 미래의 나에게 보내는 편지 + Claude Code · Codex 듀얼 harness. Obsidian 볼트이자 Claude Code / Codex 프로젝트. 외부 소스 (기사·논문·전사) 를 LLM 이 컴파일하여 복리로 성장하는 persistent wiki 로 축적합니다. 🌐 Live Showcase: llm-wiki.cmdspace.work — 10 섹션 상세 페이지 (아키텍처 · 11 commands · 미래의 나에게 보내는 편지 · Quick Start) 제작: Yohan Koo (@YohanKoo) · CMDSPACE 에서 운영 중인 satellite 볼트를 템플릿화 무엇인가 Karpathy LLM Wiki pattern 의 실행 가능한 시작 킷 Raw Sources (불변) → Wiki (LLM 관리) → Schema (규칙) 3-layer Ingest · Query · Lint 3 operations + 두 개 핵심 파일 미래의 나에게 보내는 편지 — 시 "왜 수집?" 목적 질문을 강제하여 파편 축적 방지 Claude Code + Codex 듀얼 harness 11 slash commands (, , , , , , , , , , ) 2 PostToolUse hooks (raw source verbatim 검증 + qmd auto-reindex) Codex 미러: (10) + (10) + — 같은 operation 을 Codex·Cursor·Windsurf 등에서도 동일하게 실행 18 Obsidian Web Clipper JSON 템플릿 (Article / YouTube / Substack / X / arXiv / Stibee 등) 73개 Obsidian hotkey 바인딩 () — heading shortcuts, wikilink/callout 삽입, 사이드바 토글 등 선택적 mothership 볼트 연계 — 별도 PKM 볼트가 있다면 satellite 로 운영 가능 출처 및 참고 https://gist.github.com/karpathy/
| Stars | 70 |
| Forks | 27 |
| Language | Python |
| Category | Codex Skill |
| Quality Score | 61.4948473664177/100 |
| Open Issues | 2 |
| Last Updated | 2026-07-23 |
| Created | 2026-04-14 |
| Platforms | browser, claude-code, cli, codex, python |
| Est. Tokens | ~15k |
These tools work well together with cmds-llm-wiki for enhanced workflows:
Looking for a cmds-llm-wiki alternative? If you're comparing cmds-llm-wiki 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.
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca
Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-main
A compounding LLM-wiki, best fit as a personal second brain that organizes and updates itself as it grows, zer
Turn your markdown vault into a compounding knowledge wiki (Karpathy inspired). Six agent skills - knowledge g
A compile step for knowledge bases. Gives your agent a concept graph of your content — under 20s to index, 8ms
Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked
Explore other popular codex skill tools:
cmds-llm-wiki is LLM Wiki template — Karpathy 3-layer pattern + Gold In Gold Out purpose gate + dual Claude Code·Codex harness (11 commands, 2 hooks, 18 web clipper templates). It is categorized as a Codex Skill with 70 GitHub stars.
cmds-llm-wiki is primarily written in Python. It covers topics such as claude-code, knowledge-management, llm-wiki.
You can find installation instructions and usage details in the cmds-llm-wiki GitHub repository at github.com/johnfkoo951/cmds-llm-wiki. The project has 70 stars and 27 forks, indicating an active community.
The top alternatives to cmds-llm-wiki on Agent Skills Hub include skill-conductor, llm-wiki-plugin, Kompl. 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: