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 bvisible/mcp-ssh-manager --skill ssh-operationsgit clone --depth 1 https://github.com/bvisible/mcp-ssh-managerWrote 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/bvisible/mcp-ssh-manager/ssh-operations)<a href="https://agentmods.dev/skills/bvisible/mcp-ssh-manager/ssh-operations"><img src="https://agentmods.dev/badge/skills/bvisible/mcp-ssh-manager/ssh-operations/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/bvisible/mcp-ssh-manager/ssh-operations"><img src="https://agentmods.dev/badge/skills/bvisible/mcp-ssh-manager/ssh-operations.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 | $0.00055 | $0.00616 |
| Opus 5.5 | $0.00022 | $0.00246 |
| Sonnet 5.5 | $0.00011 | $0.00123 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade D, and why
ssh-operations scanned grade D with 2 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 today.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
**Never put a password in a command.** Servers can carry a configured sudo password (`ssh_execute_sudo` uses it) and database credentials. Do not Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
first. A failed `rm -rf` that you run again with `sudo` is how an incident How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on someone's servers
You have a shell on machines that matter. The person who gave you this access cannot see what you are doing unless they have the control plane open. Behave accordingly.
Before you change anything
Look first. ssh_health_check returns CPU, memory, disk, uptime and an
overall status in one call. Reach for it before concluding that anything is
wrong — a "the site is down" report is often a full disk, and one call tells you.
Back up before you overwrite. ssh_deploy takes a backup by default; do not
turn that off to save time. Before a database import or a destructive migration,
ssh_backup_create first. A backup you did not need costs seconds; the one you
skipped costs the data.
Check what you are about to replace. ssh_execute with ls -la, cat, or
systemctl status before writing over a file or restarting a service. Read the
current state rather than assuming it.
While you work
One server at a time unless asked otherwise. ssh_execute_group runs on
every member of a group; that is powerful and unforgiving. If the task says "the
web servers", confirm which machines that means before running anything on all
of them.
Prefer the specific tool over a raw command. ssh_service_status instead of
systemctl status parsed by hand, ssh_db_query instead of piping SQL into a
client, ssh_tail instead of tail. They parse the output properly, they are
covered by the security modes, and their arguments are shell-quoted.
Never put a password in a command. Servers can carry a configured sudo
password (ssh_execute_sudo uses it) and database credentials. Do not
interpolate secrets into a command line: they end up in the remote process list
and in logs.
When something goes wrong
Do not retry a destructive command that failed. Find out why it failed
first. A failed rm -rf that you run again with sudo is how an incident
becomes an outage.
Say what you did. When you report back, name the servers you touched and the commands that changed something. The person reading you may not have been watching.
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.
- today First seen · 63 lines · 55 tokens per session scan D 4ee054c5b797
ssh-operations is a skill published in the GitHub repository bvisible/mcp-ssh-manager (519 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 616 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-26.
Other skills, from other repositories
piggyback-hosting
Hosting-Muster, um eine lokal gebaute Anwendung (eigene Datenbank, eigener API-Key, In-Process-State) sicher hostbar zu machen, ohne Nutzerverwaltung zu bauen. Kernzug — der Host speichert nichts, der Browser des Besuchers speichert alles — sodass Pro-Besucher-Accounts, Zugriffsprüfungen und Löschfristen…
c-files
Sync files to Google Drive, S3, Dropbox, OneDrive, and 70+ cloud providers using rclone.
safe-update-restart
Safe update/restart procedure for a production Hermes VPS that runs many live APIs, services, and multiple agent gateways sharing one venv. Full backup → controlled window → restart → verify every service and endpoint after. Never blind-restart.
cloud-backup
A guide to backing up files to cloud object storage such as Amazon S3 or Alibaba OSS, including copying, restoring, encryption, storage classes, and retention rules.
deployment
Kubernetes Deployment 管理.
flow-nexus-platform
Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges.