Flagged: dynamic eval(). Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by chr15m · Agent Tool · ★ 443
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is runprompt safe to install? View the security audit →
runprompt Run LLM .prompt files from your shell with a single-file Python script. A .prompt file contains the prompt and metadata (model, schema, config) in a single file. You can use it to run LLM prompts and get structured responses right in your shell. You can use it to automate AI workflows or build your own harness. Make prompts first-class artifacts. Check them into your repo and run them from the command line instead of making ad-hoc requests to AI chatbots. Quick start Spec compliance Quick start Download the single-file script: Or you can run it directly without installing using : Or install it via or to use it as a library: Create : Run it: bash export ANTHROPICAPIKEY="your-key" ./runprompt hello.prompt '{"nam
| Stars | 443 |
| Forks | 19 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 68.2776091298672/100 |
| Open Issues | 6 |
| Last Updated | 2026-08-09 |
| Created | 2025-11-27 |
| Platforms | cli, gemini, python |
| Est. Tokens | ~19k |
These tools work well together with runprompt for enhanced workflows:
Looking for a runprompt alternative? If you're comparing runprompt with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Python library for building with LLMs. One interface across 11 providers (OpenAI, Anthropic, Gemini, DeepSeek,
KEA Research - Multi-AI collaboration platform that combines responses from multiple AI models, cross-validate
LLM-powered Crypto Trading Framework with Vision AI chart analysis, real-time Neural Engine, and a live monito
Production-ready AI chat. Start here and make it your own. Formerly Sparka AI
A set of tools that gives agents powerful capabilities.
Agent samples built using the Strands Agents SDK.
Explore other popular agent tool tools:
runprompt is Run LLM prompts from your shell. It is categorized as a Agent Tool with 443 GitHub stars.
runprompt is primarily written in Python. It covers topics such as ai-agents, ai-development, anthropic.
You can find installation instructions and usage details in the runprompt GitHub repository at github.com/chr15m/runprompt. The project has 443 stars and 19 forks, indicating an active community.
runprompt is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to runprompt on Agent Skills Hub include SimplerLLM, kea-research, LLM_trader. 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: