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-managergit 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-manager)<a href="https://agentmods.dev/skills/bvisible/mcp-ssh-manager/ssh-manager"><img src="https://agentmods.dev/badge/skills/bvisible/mcp-ssh-manager/ssh-manager/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-manager"><img src="https://agentmods.dev/badge/skills/bvisible/mcp-ssh-manager/ssh-manager.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 | $0.00079 | $0.01187 |
| Opus 5.5 | $0.00032 | $0.00475 |
| Sonnet 5.5 | $0.00016 | $0.00237 |
| Haiku 4.5 | $0.00008 | $0.00119 |
Grade A, and why
ssh-manager 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 6d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using the SSH Manager tools
This skill covers the five core tools, the ones exposed in the default minimal mode. If
more groups are enabled (ssh-manager tools list), prefer the specific tool over a raw command.
| Tool | What it does | Changes the server? |
|---|---|---|
ssh_list_servers |
Lists configured servers: name, host, user, port, auth type, default directory, group. Never returns secrets. | no |
ssh_execute |
Runs one command line, returns stdout, stderr, code. |
depends on the command |
ssh_upload |
Copies ONE local file over SFTP, overwriting the target. No backup, no sudo. | yes |
ssh_download |
Copies ONE remote file to a local path (overwrites the local file). | no |
ssh_sync |
rsync over SSH. One side local:, the other remote:. dryRun previews, delete removes extras at the destination. |
yes |
Before the first command
- Call
ssh_list_serversonce and use the exact names. A name is lowercase and every character that is not a letter or a digit became_(my-site.ch→my_site_ch). Several names can share one host with different users: take the user with the rights you need and no more. ssh_executerunscd -- '<cwd, or the server's default directory>' && <your command>. Passcwdwhen the default is wrong. A missing directory fails the whole call.- A server can be in
readonlymode (destructive commands and uploads refused) orrestrictedmode (only commands matching its patterns). A refusal is the configuration working: do not look for a way around it, ask whoever owns the server.
Writing the command
- Assume the remote shell is
sh/dash, not bash: no<(…), no[[ … ]], no arrays, no{a,b}, no$'…'. A syntax error aborts the whole line before any part of it ran. Pipe instead, or wrap inbash -c '…'. - Heredocs work (
<<'EOF'). Quote the delimiter so nothing is expanded by the remote shell. - Chain with
&&when step two must not run after a failure. pgrep -fandpkill -fmatch every command line, including the shell that carries your command. Bracket one letter (pgrep -f '[n]ginx -g') and kill in one call, relaunch in the next.- Never put a password or token in the command line: it ends up in the remote process list and in logs. Use a file with mode 600 or an environment variable set on the remote side.
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.
- 6d ago First seen · 81 lines · 79 tokens per session scan A b080784481ba
ssh-manager is a skill published in the GitHub repository bvisible/mcp-ssh-manager (507 stars, last pushed 7d ago), licensed MIT. It adds 79 tokens to every session and 1,187 once invoked, about $0.0003 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 2026-10-10.
Other skills, from other repositories
mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.
github-release-management
GitHub release orchestration — automated versioning, testing, deployment, and rollback. Use when cutting a release, tagging a version, drafting release notes, or coordinating a deploy/rollback workflow.
ai-engineer-expert
Expert-level AI implementation, deployment, LLM integration, and production AI systems. Use when the user mentions AI engineering, LLM, deployment, production AI, or integration, or when the task involves LLM Patterns, LLM Integration, or Production Systems.
modal-serverless-gpu
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
cicd-expert
Expert-level CI/CD with GitHub Actions, Jenkins, deployment pipelines, and automation. Use when the user mentions CI/CD, GitHub Actions, Jenkins, GitLab CI, deployment, or automation, or when the task involves CI/CD Fundamentals, Pipeline Design, Workflow Basics, or Docker Build and Push.
helm-expert
Expert-level Helm 3 package management, chart development, templating, and production operations. Use when the user mentions Kubernetes, package manager, charts, templates, or deployment, or when the task involves Helm Architecture, Chart Structure, Values.yaml, or Helm Hooks.