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 frontier-ai-next/mgarlbot --skill ops_tmux_remote_deploygit clone --depth 1 https://github.com/frontier-ai-next/mgarlbotWrote 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/frontier-ai-next/mgarlbot/ops_tmux_remote_deploy)<a href="https://agentmods.dev/skills/frontier-ai-next/mgarlbot/ops_tmux_remote_deploy"><img src="https://agentmods.dev/badge/skills/frontier-ai-next/mgarlbot/ops_tmux_remote_deploy/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/frontier-ai-next/mgarlbot/ops_tmux_remote_deploy"><img src="https://agentmods.dev/badge/skills/frontier-ai-next/mgarlbot/ops_tmux_remote_deploy.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 | $0.00030 | $0.00987 |
| Opus 5 | $0.00015 | $0.00494 |
| Sonnet 5 | $0.00006 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
ops_tmux_remote_deploy scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Check core tools: `tmux`, `curl`, `ss` (or `netstat` fallback). How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remote deploy via tmux (single VPS baseline)
Use this skill when the user wants: "deploy on that server", "run frps and project in tmux", "keep processes alive after disconnect".
Always run commands on VPS via SSH wrapper:
ssh -F /data/.ssh/config vps 'REMOTE_COMMAND_HERE'
Never run host-level commands locally when the task is explicitly remote.
Goal
Create and maintain two tmux sessions on the VPS:
frps— FRP server process.project_app— project runtime process (docker compose or native command).
Both sessions must be idempotent and verifiable.
Standard sequence
-
Preflight
- Verify SSH connectivity.
- Check core tools:
tmux,curl,ss(ornetstatfallback). - Install
tmuxif missing (non-interactive apt for Debian/Ubuntu).
-
Prepare frps
- Ensure
frpsbinary + config path are known (ask only if impossible to infer). - Restart
frpssession safely:tmux has-session -t frps-> kill if exists.- start detached with explicit command and logs.
- Ensure
-
Prepare app runtime
- If repo has compose files and user asked containerized deploy: use
docker compose upinproject_app. - Otherwise start provided app command in
project_app. - Same idempotent session restart pattern as
frps.
- If repo has compose files and user asked containerized deploy: use
-
Health checks (mandatory)
tmux lscontains both sessions.- Process check (
pgrep -af frps, app process ordocker compose ps). - Port check with
ss -ltnpfor expected bind ports. - HTTP check with
curl -fsS(or status code check) for app endpoint.
-
Operational output
- Report only operational facts: session names, process status, listening ports, endpoint status.
- Provide follow-up commands for logs:
tmux capture-pane -pt frps -S -120tmux capture-pane -pt project_app -S -120
Canonical command snippets
SSH preflight:
ssh -F /data/.ssh/config vps 'set -e; uname -a; command -v tmux >/dev/null || echo "__NO_TMUX__"'
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.
- 9d ago First seen · 98 lines · 30 tokens per session scan A 810bb3bd6e02
ops_tmux_remote_deploy is a skill published in the GitHub repository frontier-ai-next/mgarlbot (17 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 987 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
network-rca
Kubernetes network root cause analysis skill powered by Kubeshark MCP. Use this skill whenever the user wants to investigate past incidents, perform retrospective traffic analysis, take or manage traffic snapshots, extract PCAPs, dissect L7 API calls from historical captures, compare traffic patterns over time, detect…
modal-serverless-gpu
Run approved CPU or GPU work through OpenScience computejob on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.
givemeanode-agent-compute
Operate GiveMeANode GPU nodes, batch jobs, storage, and rollout sandboxes through its connected MCP server with bounded spend, durable recovery, and explicit approval for paid or destructive actions.
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.