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.
npx skills add yale-som-hpc/claude-code-marketplace --skill staying-connectedgit clone --depth 1 https://github.com/yale-som-hpc/claude-code-marketplaceWrote 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.
[](https://agentmods.dev/skills/yale-som-hpc/claude-code-marketplace/staying-connected)<a href="https://agentmods.dev/skills/yale-som-hpc/claude-code-marketplace/staying-connected"><img src="https://agentmods.dev/badge/skills/yale-som-hpc/claude-code-marketplace/staying-connected/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yale-som-hpc/claude-code-marketplace/staying-connected"><img src="https://agentmods.dev/badge/skills/yale-som-hpc/claude-code-marketplace/staying-connected.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.02181 |
| Opus 5 | $0.00040 | $0.01091 |
| Sonnet 5 | $0.00016 | $0.00436 |
| Haiku 4.5 | $0.00008 | $0.00218 |
Grade A, and why
staying-connected 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 12d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Staying Connected
Rule: a dropped laptop connection should never kill cluster work. Pick a model up front, make the session durable, and keep the agent's own footprint off the login node.
There are two ways to run Claude Code against the cluster. They fail differently, so they need different tools. Decide which one you are in before anything else.
| Model | Claude Code runs on | What breaks on a drop | Fix |
|---|---|---|---|
| A | the cluster login node (you SSH in, then start Claude there) | the agent process is killed when your SSH dies | session persistence on the login node (tmux) |
| B | your laptop, driving the cluster over SSH | each ssh hpc <cmd> is a fresh shell that forgets cwd/modules/env |
a persistent remote shell (zmx) |
Cluster facts agents should know
Current as of 2026-06-05. Verify with command -v on the login node before recommending a tool.
tmux(3.2a) is installed system-wide on the login node. It is the default persistence tool.mosh,mosh-server,screen,autossh, and Eternal Terminal (et) are not installed on the cluster. mosh and ET need a server-side binary, so they are unavailable until SOM IT installs them — see resilience ladder.zellijandzmxare not system-wide; they only work if a user installed them under~/.local/bin.hpc.som.yale.educurrently resolves to a single login node (hpc-ln02). There is a second login node on the internal network, but the public name points at one host today, so a tmux session is reliably where you left it. This can change — see the reattach gotcha.
Baseline: SSH config (do this regardless of model)
On your laptop, ~/.ssh/config. This keeps idle links from being silently dropped and reuses one connection for the agent's many ssh calls:
Host hpc
HostName hpc.som.yale.edu
User yournetid
ServerAliveInterval 60
ServerAliveCountMax 3
ControlMaster auto
ControlPath ~/.ssh/cm-%r@%h:%p
ControlPersist 10m
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.
- 12d ago First seen · 135 lines · 80 tokens per session scan A 4ef69295f877
staying-connected is a skill published in the GitHub repository yale-som-hpc/claude-code-marketplace (5 stars, last pushed 2mo ago), licensed Unlicense. It adds 80 tokens to every session and 2,181 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…