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 EliFuzz · Codex Skill · ★ 269
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is awesome-system-prompts safe to install? View the security audit →
Prompt Labs - Leaked System Prompts LLMs Aider: AI-powered coding assistant that helps developers modify codebases efficiently through natural language prompts and context-aware code changes Latest Architect Mode: outlining how an AI acts as an expert architect engineer to provide clear, concise, and change-focused instructions to an "editor engineer" for modifying code within a git repository Ask Mode: as an expert code analyst AI, detailing its read-only nature for code analysis and question answering, its emphasis on brief responses, and its capability to request additional files for analysis. File Mode: "file listing" format for an AI assistant, which involves returning the entire content of a file (either existing or new) within a specific fenced code block structure to propose code changes. Patch Mode: "V4A Diff Format Rules" used by an expert software developer agent, detailing how it should propose code changes, create new files, and refactor existing ones using a unified patch format with context-aware diffs for Add, Update, and Delete operations. System Prompt: AI software developer coding best practices, interaction rules, and the precise block format for code modificat
| Stars | 269 |
| Forks | 51 |
| Language | JavaScript |
| Category | Codex Skill |
| License | GPL-3.0 |
| Quality Score | 55.8325661970269/100 |
| Open Issues | 2 |
| Last Updated | 2026-03-06 |
| Created | 2025-10-03 |
| Platforms | claude-code, codex, gemini, node, vscode |
| Est. Tokens | ~1240k |
Looking for a awesome-system-prompts alternative? If you're comparing awesome-system-prompts 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.
CodexFlow is a unified desktop workbench for AI coding agents (Codex/Claude/Gemini/Antigravity) across Windows
Lightweight Agent Workstation for Codex CLI + Claude Code — with task scheduler, git worktree & remote control
The definitive resource for Agent Skills - modular capabilities revolutionizing AI agent architecture
Install our local first extensions for your favorite AI IDE or Terminal Agent. Process your histories into reu
Chat with any codebase in under two minutes | Fully local or via third-party APIs
Coding Agent Session Manager for Claude Code / Gemini CLI / Codex CLI / Cursor Agent / Copilot CLI / Cline CLI
Explore other popular codex skill tools:
awesome-system-prompts is A collection of system prompts and tool definitions from various AI coding agents: Augment Code, Claude Code, Cluely, Cursor, Devin AI, Kiro, Perplexity, VSCode Agent, Gemini, Codex, OpenAI. It is categorized as a Codex Skill with 269 GitHub stars.
awesome-system-prompts is primarily written in JavaScript. It covers topics such as ai, anthropic, awesome.
You can find installation instructions and usage details in the awesome-system-prompts GitHub repository at github.com/EliFuzz/awesome-system-prompts. The project has 269 stars and 51 forks, indicating an active community.
awesome-system-prompts is released under the GPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to awesome-system-prompts on Agent Skills Hub include CodexFlow, codexia, awesome-agent-skills. 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: