Borrowing it
Nothing to install: this file belongs to hunchom/claude-code-ssh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hunchom/claude-code-ssh/main/.claude/skills/operating-ssh-fleet/SKILL.mdgit clone --depth 1 https://github.com/hunchom/claude-code-sshWrote 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/hunchom/claude-code-ssh/operating-ssh-fleet)<a href="https://agentmods.dev/skills/hunchom/claude-code-ssh/operating-ssh-fleet"><img src="https://agentmods.dev/badge/skills/hunchom/claude-code-ssh/operating-ssh-fleet/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/hunchom/claude-code-ssh/operating-ssh-fleet"><img src="https://agentmods.dev/badge/skills/hunchom/claude-code-ssh/operating-ssh-fleet.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 | $0.00118 | $0.02696 |
| Opus 5.5 | $0.00047 | $0.01078 |
| Sonnet 5.5 | $0.00024 | $0.00539 |
| Haiku 4.5 | $0.00012 | $0.00270 |
Grade A, and why
operating-ssh-fleet 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 2mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating the SSH Fleet
Overview
ssh-manager is an MCP server that exposes 13 fat verb-tools (ssh_*) for operating a fleet of configured servers. Each tool covers one domain and multiplexes many operations through an action enum.
Core principle: For any server in the configuration, the ssh_* tools are the intended way to operate it — not raw ssh/scp/rsync through Bash. They are not a read-only convenience layer; they are the operator interface.
When to use
- Running, scripting, or backgrounding a command on a configured server
- Moving, reading, editing, or deploying files
- Reading or following logs; checking health, services, processes
- Databases, backups, Docker, tunnels, port probes, persistent sessions
- Multi-step changes across one or more servers
- Any time you would otherwise type
ssh host "...",scp, orrsyncin Bash for a configured host
When NOT to use
- The host is not in the configuration → raw
sshin Bash is fine. Runssh_fleetaction: serversto see what is configured. - Pure local work with no remote target.
The discipline: ssh_* over raw ssh
| Raw Bash | Why the tool wins |
|---|---|
ssh host "cmd" reconnects every call |
Tools hold a pooled connection — no per-call handshake |
ssh host journalctl dumps everything |
Output is head+tail truncated + compressed — won't flood context |
ssh host with inline password leaks on argv |
Credentials go via stdin/env, never ps-visible |
| Raw terminal dump | Structured results — per-segment exit codes, typed snapshots, sha256-verified transfers |
Violating the letter (using raw ssh "just this once") is violating the spirit. If the host is configured, use the tool.
The 13 tools
Always loaded. Pick the tool, then the action.
| Tool | Group | Actions | Replaces |
|---|---|---|---|
ssh_run |
core | exec, sudo, script, fleet, detach, job-status, job-kill | ssh host "cmd" |
ssh_find |
core | grep, locate, ls | ssh host "grep -rn …" |
ssh_file |
core | upload, download, sync, read, write, edit, diff, deploy, deploy-artifact | scp, cat > f <<EOF |
ssh_logs |
core | tail, follow-start, follow-read, follow-stop, journal | ssh host journalctl / tail -f |
ssh_service |
ops | status, start, stop, restart, enable, disable | ssh host systemctl … |
ssh_health |
ops | check, watch, procs, alerts | ssh host top/df/free |
ssh_db |
ops | query, list, dump, import | ssh host "mysql -e …" |
ssh_backup |
ops | create, list, restore, schedule | ssh host "tar/mysqldump …" |
ssh_docker |
ops | ps, logs, exec, restart, inspect | ssh host "docker …" |
ssh_session |
advanced | start, send, list, close, replay, memory | repeated ssh host "cmd" |
ssh_net |
advanced | tunnel-open, tunnel-list, tunnel-close, port-test | ssh -L/-R/-D, nc -z |
ssh_fleet |
advanced | servers, groups, aliases, command_alias, profiles, hooks, keys, history, connections | ssh -G, ~/.ssh/config |
ssh_plan |
advanced | run, approve | hand-sequenced batch of calls |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 126 lines · 118 tokens per session scan A b1322006287d
operating-ssh-fleet is a skill published in the GitHub repository hunchom/claude-code-ssh (2 stars, last pushed 3mo ago), licensed MIT. It adds 118 tokens to every session and 2,696 once invoked, about $0.0005 per session on Opus 5.5. 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
cloudflare-temporary-deploy
Deploy a Worker live, no account, via wrangler --temporary.
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
cli-backup-sync
Backup and restore OmniRoute data from the CLI. Trigger incremental snapshots, sync to cloud storage, manage backup schedules, and restore from archive files.
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.