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 masci · LLM Plugin · ★ 128
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is banks safe to install? View the security audit →
banks Banks) is the linguist professor who will help you generate meaningful LLM prompts using a template language that makes sense. If you're still using for the job, keep reading. Docs are availab
| Stars | 128 |
| Forks | 21 |
| Language | Python |
| Category | LLM Plugin |
| License | MIT |
| Quality Score | 71.3413172481787/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-10 |
| Created | 2023-06-04 |
| Platforms | python |
| Est. Tokens | ~16k |
Looking for a banks alternative? If you're comparing banks with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A handy lib for smooth interaction with large language models (LLMs) and crafting AI apps.
The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for ca
Run LLM prompts from your shell
✨Lightweight LLM Client with MCP 🔌 & Characters 👤
Open-source versioning, tracing, and annotation tooling.
An Automated AI-Powered Prompt Optimization Framework
Explore other popular llm plugin tools:
banks is LLM prompt language based on Jinja. Banks provides tools and functions to build prompts text and chat messages from generic blueprints. It allows attaching metadata to prompts to ease their management. It is categorized as a LLM Plugin with 128 GitHub stars.
banks is primarily written in Python. It covers topics such as chatgpt, llm, nlp.
You can find installation instructions and usage details in the banks GitHub repository at github.com/masci/banks. The project has 128 stars and 21 forks, indicating an active community.
banks is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to banks on Agent Skills Hub include ai-microcore, gateway, runprompt. 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: