Remote Compute SSH
DevOps & Securityremote-compute-sshRemote Compute SSH is an Agent Skill for devops & security published in the companion-inc/feynman repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Run Feynman research jobs on SSH, Slurm, or lab hosts. Use when a task needs remote host setup, job submission, log harvest, artifact sync, or GPU/cluster execution outside Modal.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/companion-inc/feynman/blob/HEAD/skills/remote-compute-ssh/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/remote-compute-ssh, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Remote Compute: SSH
Use this skill for lab machines, SSH hosts, and Slurm-style research jobs.
Workflow:
- Record host alias, scheduler, working directory, environment module/conda/container needs, data paths, and artifact return path.
- Verify access and a tiny smoke command before the main job.
- Submit with a bounded script that logs package versions, hardware, command, and seed.
- Harvest stdout/stderr, job id, exit status, produced artifacts, and checksums into the Feynman workspace.
- Mark failed or partial jobs honestly; do not fabricate remote artifacts from local expectations.
Keep remote credentials and private paths out of user-facing summaries unless they are needed for reproducibility.