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 tallesborges · Claude Skill · ★ 185
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agentic-system-prompts safe to install? View the security audit →
AI Agent System Prompts Library What makes agentic coding applications different? TBH, it's mostly their system prompts, the tools they provide, and how they actually use them. In this repo, I'm documenting these system prompts and tools from different agentic coding solutions. Table of Contents Agent Comparison What's Included Research Value Contributing License Agent Comparison | [Codex CLI (Rust
| Stars | 185 |
| Forks | 24 |
| Language | Jinja |
| Category | Claude Skill |
| Quality Score | 64.3378692346963/100 |
| Last Updated | 2025-08-04 |
| Created | 2025-07-07 |
| Platforms | claude-code, cli, gemini |
| Est. Tokens | ~13k |
These tools work well together with agentic-system-prompts for enhanced workflows:
Looking for a agentic-system-prompts alternative? If you're comparing agentic-system-prompts with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Platform-agnostic AI agent: one Full-Stack Software Engineer brain, compiled into ready-to-paste adapters for
Tracking prompts, feature flags and metadata of Claude Code releases. Subscribe to ↓
A local sandbox for your AI agents
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
Explore other popular claude skill tools:
agentic-system-prompts is A curated collection of system prompts and tool definitions from production AI coding agents. It is categorized as a Claude Skill with 185 GitHub stars.
agentic-system-prompts is primarily written in Jinja. It covers topics such as claude-code, gemini-cli, prompt-engineering.
You can find installation instructions and usage details in the agentic-system-prompts GitHub repository at github.com/tallesborges/agentic-system-prompts. The project has 185 stars and 24 forks, indicating an active community.
The top alternatives to agentic-system-prompts on Agent Skills Hub include agent-skills, omnistack-agent, claude-code-changelog. 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: