remote-compute-ssh

remote-compute-ssh is a skill for Claude Code, Codex from aipoch/open-science. It costs 53 tokens per session (3,701 once invoked), scanned A, original, Apache-2.0.

A guide for using remote computers over SSH, including machines with GPUs or large amounts of memory. It covers short commands and longer jobs that run in the background.

In plain words
What is it for?
Use it to find available compute machines, run commands remotely, submit long-running jobs, collect their results, and publish the resulting files.
Why use it?
It helps decide where demanding scientific or data-processing work should run and keeps track of jobs that cannot finish in one command.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/aipoch/open-science/remote-compute-ssh
Any agent
npx skills add aipoch/open-science --skill remote-compute-ssh
Clone the repo
git clone --depth 1 https://github.com/aipoch/open-science

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for remote-compute-ssh

README.md
[![agentmods](https://agentmods.dev/badge/skills/aipoch/open-science/remote-compute-ssh.svg)](https://agentmods.dev/skills/aipoch/open-science/remote-compute-ssh)
Your own site
<a href="https://agentmods.dev/skills/aipoch/open-science/remote-compute-ssh"><img src="https://agentmods.dev/badge/skills/aipoch/open-science/remote-compute-ssh.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,701 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.03701
Opus 5 $0.00026 $0.01851
Sonnet 5 $0.00011 $0.00740
Haiku 4.5 $0.00005 $0.00370

Measured yesterday against content hash ad42e93914db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

remote-compute-ssh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

resources/skills/remote-compute-ssh/SKILL.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This skill covers remote compute over SSH: listing hosts, creating handles, running short remote commands (callCommand), reading/writing host knowledge docs, and the full async job lifecycle — submit → harvest → analysis turn → publish artifacts.

Where host.compute runs: host.compute lives ONLY on the control-plane REPL kernel — run every example below with the repl_execute tool (JavaScript), the same kernel that hosts host.mcp. The python/r data kernels have NO host.compute (SSH and approvals stay outside the sandbox workspace); calling it from a python/r cell will fail with host.compute is undefined.

Choose an execution location

Only Compute Hosts enabled for this Session are visible or callable. Discover them in one catalog; each entry has role selected or available. A non-empty selected pool is an execution instruction: run tool-backed task work on one or more selected hosts as the task requires. The pool has no priority and does not imply automatic multi-host scheduling. If no host is selected, choose from the available entries. Read details() only for candidates that need closer evaluation.

Never guess or reuse a provider id absent from the catalog. A user naming a disabled host does not make it callable; explain that it must first be enabled for this Session. If no eligible host is usable, explain the blocker and ask the user how to proceed.

const hosts = await host.compute.listHosts()
const selectedHosts = hosts.filter((host) => host.role === 'selected')
const candidates = selectedHosts.length > 0 ? selectedHosts : hosts

Each list item is a compact summary with provider_id, display_name, shape, status, and role (last_probe_ok, probe_failed, or not_probed). last_probe_ok means the most recent persisted Probe succeeded; it does not assert live connectivity. Knowledge documents and resource probe snapshots are deliberately excluded from discovery results.

API reference

// List this Session's enabled hosts as one role-bearing compact catalog
const hosts = await host.compute.listHosts()

// Compatibility discovery names remain available; both still hide disabled hosts.
const visibleHosts = await host.compute.listRegistered()
const selectedHosts = await host.compute.listPreferred()

// Create a handle to a specific host (no network call)
const c = host.compute.create('ssh:<alias>')

// Run a short remote command (throws on approval_denied / host_unreachable / timeout)
const result = await c.callCommand('<shell command>', '<one-line intent for the approval card>', {
  loginShell: true, // default: true — runs login profiles, then readable ~/.bashrc, before this command
  timeoutSeconds: 60 // optional — the host applies its own default (60s) when omitted
})
// result → { exit_code, stdout, stderr, truncated }

// Read the host knowledge doc and resource probe snapshot on demand.
// probe is explicitly null when this host has never been probed.
const info = await host.compute.details('ssh:<alias>', { mode: 'read' })

// Append a note to the host knowledge doc (agent writes; 32 KB cap enforced)
await host.compute.details('ssh:<alias>', {
  mode: 'append',
  text: '\n## Note\nlearned X on <date>'
})

// Replace the entire host knowledge doc (oldText must match the current doc exactly)
await host.compute.details('ssh:<alias>', {
  mode: 'replace',
  text: '<new full doc>',
  oldText: info.doc // from the read above
})

Read the full file on GitHub · 348 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday Changed · +23 lines ad42e93914db
  2. 4d ago First seen · 325 lines · 53 tokens per session scan A 2bbc300abb29

Subscribe to this mod's changes

remote-compute-ssh is a skill published in the GitHub repository aipoch/open-science (3,497 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 3,701 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

modal-compute

Run explicitly chosen research benchmark or replication jobs on Modal's serverless infrastructure. Use when a Feynman research workflow needs burst remote GPU compute and the Modal CLI is available.

companion-inc/feynman · 39 tokens

validate-gpu-cluster

Check whether a DeepOps-deployed Slurm or Kubernetes GPU cluster is healthy and report a machine-readable verdict. Use for health checks, post-deploy verification, "is the cluster working?" questions, and after any node or driver change.

NVIDIA/deepops · 54 tokens

compute-env-setup

Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.

companion-inc/feynman · 45 tokens

remote-compute-ssh

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.

companion-inc/feynman · 48 tokens

remote-compute-modal

Dispatch Feynman research notebook or experiment jobs to Modal. Use when a task has explicitly chosen Modal for bounded cloud compute, GPU jobs, or reproducible remote execution.

companion-inc/feynman · 39 tokens

source-verify

医学信源快速或完整核验。普通教育性医学问答用单一权威正文快速核验;最新版本、精确推荐、高风险药品、医保监管或跨版本请求升级为完整核验。只整理学习依据,不生成诊疗、处方、急诊处置、医保报销结论或HIS执行建议。.

TencentCloud/Octop · 80 tokens