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 javded-itres/Holix --skill holix-sshgit clone --depth 1 https://github.com/javded-itres/HolixWrote 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/javded-itres/holix/holix-ssh)<a href="https://agentmods.dev/skills/javded-itres/holix/holix-ssh"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-ssh/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/javded-itres/holix/holix-ssh"><img src="https://agentmods.dev/badge/skills/javded-itres/holix/holix-ssh.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 | $0.00048 | $0.00444 |
| Opus 5.5 | $0.00019 | $0.00178 |
| Sonnet 5.5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
holix-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 5d 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.
What it actually says
When to use
The user wants a command, file read, or service check on another machine.
Load this skill with skill_view before the first remote call of the task.
Procedure
- Call
ssh_exec.hostandcommandare separate arguments. hostis an alias from the SSH config list in the system prompt, oruser@hostwhen the user gave an address and there is no alias. Do not invent a user when that list already names one.- Put a script in
stdin. Do not build a local heredoc and do not wrap the command in quotes for the local shell. - Timeout defaults to 120 seconds. Raise it up to 600 only when the remote command needs it.
- If the result is an error, show stderr to the user and stop. One failure is enough.
Do not
- Do not call
run_terminal_commandwithssh,scp, orsftp. - Do not allocate a TTY, run
ssh -v, or runssh-add. - Do not append
&or poll a background SSH session. - Do not put SSH options in
host(-o,ProxyCommand, an empty host). - Do not print keys, tokens, or the contents of
.ssh.
Examples
ssh_exec(host="ai-server-local", command="uname -a")
ssh_exec(host="[email protected]", command="python3 -", stdin="<script>")
Verification
- The turn used
ssh_exec, not a localsshstring. - A failure was reported once, without a second connection attempt.
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.
- 5d ago First seen · 48 lines · 48 tokens per session scan A f3b5bb20808e
holix-ssh is a skill published in the GitHub repository javded-itres/Holix (17 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 444 once invoked, about $0.0002 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 2026-10-12.
Other skills, from other repositories
Remote Experiment Execution
A workflow for running code and commands on a remote server through the compute-helper command-line tool. It synchronizes local code, runs it remotely, and can retrieve result files.
nosignups-catalog
Catálogo curado de ferramentas open source sem signup (NoSignups.net). 234 tools organizadas por categoria e relevância para DevOps/self-hosted/operations. Use para encontrar alternativas open source a ferramentas SaaS, especialmente focado em self-hosted, privacidade e automação.
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.
cloudflare-temporary-deploy
Deploy a Worker live, no account, via wrangler --temporary.
pinggy-tunnel
Zero-install localhost tunnels over SSH via Pinggy.
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.