HN Showcase
Back to browse
GitHub Repository

GenAI prompts as runnable programs

48 starsRust

Bring your own prompts in SSH remote shells

by tgalal·Mar 10, 2026·1 point·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainSolve My Problem

SSH integration where prompts execute locally but appear remotely is genuinely clever security-wise.

Strengths
  • •Local execution model means LLM tools never get SSH access to production servers.
  • •Provider load balancing and caching optimize token costs across multiple AI providers.
  • •Character variants let you define personality-specific prompt templates per use case.
Weaknesses
  • •Prompt management space is crowded with Claude Code, Cursor, and similar tools.
  • •Requires SSH setup and promptctl wrapper for every remote session.
Target Audience

DevOps engineers, developers managing remote servers

Similar To

Claude Code · Cursor · llm-cli

Post Description

Instead of giving LLM tools SSH access or installing them on a server, the following command:

$ promptctl ssh user@server

makes a set of locally defined prompts "magically" appear within the remote shell as executable command line programs.

For example, I have locally defined prompts for `llm-analyze-config` and `askai`. Then on (any) remote host I can:

# on remote host $ llm-analyze-config /etc/nginx.conf $ cat docker-compose.yml | askai "add a load balancer"

the prompts behind `llm-analyze-config` and `askai` execute on my local computer (even though they're invoked remotely) via the llm of my choosing.

This way LLM tools are never granted SSH access to the server, and nothing needs to be installed to the server.

Github: https://github.com/tgalal/promptcmd/

Docs: https://docs.promptcmd.sh/

Similar Projects