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 agentmods add skills/frontier-ai-next/mgarlbot/docker_deploynpx skills add frontier-ai-next/mgarlbot --skill docker_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/docker_deploy)<a href="https://agentmods.dev/skills/frontier-ai-next/mgarlbot/docker_deploy"><img src="https://agentmods.dev/badge/skills/frontier-ai-next/mgarlbot/docker_deploy.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00560 |
| Opus 5 | $0.00011 | $0.00280 |
| Sonnet 5 | $0.00004 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade C, and why
docker_deploy scanned grade C 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Suggest `rm -rf /`, chmod-the-world, or destructive actions outside the task. What it actually says
Docker / Compose (test or prod stack)
Default chain: inspect project → artifacts → validate config → build (may take long) → detached run for daemons → report.
Work inside the target project tree (relative paths, cd into the service directory). With HOST SHELL MODE you may use absolute paths to other project roots on this machine.
If the user asks for apt / OS-level commands on a remote VPS, use skill vps_host_ssh (ssh -F /data/.ssh/config vps '...'), not local compose unless they explicitly want local only.
Public URL, Traefik/Nginx/frp, and REG.RU DNS — skills ops_reverse_proxy and ops_dns_regru (inspect proxy on the VPS first, then config).
Do not read or paste .env, keys, or tokens into the user-facing reply.
Steps
- Analyze: language/runtime from
pyproject.toml,package.json,go.mod,requirements.txt, existingDockerfile; entrypoint (CMD), ports, env var names only (not secret values). - Files: minimal working
Dockerfile, sensible.dockerignore,docker-compose.ymlif needed (build,ports,env_file:without baking secrets into the image). - Config:
docker compose config(ordocker-compose config) — fix until clean. - Build:
docker compose build— iterate from logs; do not treat a long build as failure until the command exits with an error. - Run: for APIs/web/daemons use
docker compose up -dso the session does not block on foreground logs unless the user asks for attached logs. - Verify:
docker compose psordocker ps --filter name=...; on failuredocker compose logs --tail=80 <service>. - Report: briefly what changed, service/container names, published ports, commands to verify and tail logs. State clearly e.g. “Deployed; check …”.
Do not
- Put real secrets in
Dockerfileor print.envcontents. - Suggest
rm -rf /, chmod-the-world, or destructive actions outside the task.
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 · 35 lines · 22 tokens per session scan C 7d025d56db6b
docker_deploy is a skill published in the GitHub repository frontier-ai-next/mgarlbot (17 stars, last pushed 28d ago), licensed MIT. It adds 22 tokens to every session and 560 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
exec-local-docker
Execute a TensorRT-LLM workload locally in Docker. Runs a fully-resolved Docker command in background, monitors completion, reads logs, and reports results. Workflow-agnostic — does not need to know if the workload is pytest, eval, benchmark, or a custom script.
dockerfile-slimming
Reduce container image size and build time with multi-stage builds and ordered layer caching.
Docker Compose Generator
Generates production-ready docker-compose.yml files for any application stack.
docker-container-escape
Escape from Docker containers to the host system using container misconfigurations, mounted sockets, privileged mode, capabilities abuse, and kernel exploits. Use this skill when testing containerized environments for breakout vulnerabilities during penetration tests. Covers Docker socket mounting, cgroup escapes…
test-environment-management
Test environment provisioning, infrastructure as code for testing, Docker/Kubernetes for test environments, service virtualization, and cost optimization. Use when managing test infrastructure, ensuring environment parity, or optimizing testing costs.
agentic-devops
Production-grade agent DevOps toolkit — Docker, process management, log analysis, and health monitoring. Built by engineers who run production.