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/akacianl/basicdeploy-mcp/deploy-on-basicdeploynpx skills add AkaciaNL/basicdeploy-mcp --skill deploy-on-basicdeploygit clone --depth 1 https://github.com/AkaciaNL/basicdeploy-mcpWhat 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 | $0.00107 | $0.00892 |
| Opus 5 | $0.00053 | $0.00446 |
| Sonnet 5 | $0.00021 | $0.00178 |
| Haiku 4.5 | $0.00011 | $0.00089 |
Grade A, and why
deploy-on-basicdeploy 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 yesterday.
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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy on BasicDeploy
BasicDeploy gives each app a live container with a PostgreSQL database, S3-compatible object storage, and a public HTTPS URL, all wired in. Follow these steps to deploy reliably.
The one rule that breaks deploys
The container's public URL is always routed to port 8080. Your app MUST listen on
0.0.0.0:8080 — not localhost/127.0.0.1, and not 3000/5000/8000. Any other port, or a
loopback bind, returns HTTP 503 at the public URL even though the process is running. If the
framework reads a PORT env var, set it to 8080.
Steps
- (Optional) Check the account: call
get_accountfor plan limits and selectable memory sizes. - Create a container: call
create_container(optionallymemoryMb). It returns the container id + public URL and auto-provisions a Postgres database and an S3 bucket. - Put the app in the container — two ways:
- Chat / remote connector (ChatGPT, Claude, Gemini): use
exec_command. There is no shared filesystem, sodeploy_app's tarball path will NOT work here. Write the app files into the container withexec_command(heredoc/echo, orgit clone), install deps, then start the server bound to0.0.0.0:8080. - Local stdio server: use
deploy_appwith a tarball path on your own machine (Dockerfile / package.json / requirements.txt / go.mod at the archive root).
- Chat / remote connector (ChatGPT, Claude, Gemini): use
- Use the preset env vars — do not hardcode:
DATABASE_URL(Postgres) andS3_ENDPOINT/S3_ACCESS_KEY/S3_SECRET_KEY/S3_BUCKETare already set in the container environment. Read them from the environment. - Keep it running: there is no init/supervisor — a process started via
exec_commandruns only until the container sleeps or restarts and is NOT relaunched. For a long-running web server, run it as the container's main process and enable always-on withset_always_on(free on Pro/Scale; a paid add-on on Free). For a one-shot job, re-run the start command after each wake. - Verify: open the public URL from step 2. A 503 means the app is on the wrong port or bound
to localhost — fix it to
0.0.0.0:8080. Useget_logsto debug.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 48 lines · 107 tokens per session scan A 82c8357a2df3
deploy-on-basicdeploy is a skill published in the GitHub repository AkaciaNL/basicdeploy-mcp (0 stars, last pushed 19d ago), licensed MIT. It adds 107 tokens to every session and 892 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
Docker Compose Generator
Generates production-ready docker-compose.yml files for any application stack.
ep
Workflow de deploy e gestão do Easypanel via MCP. Use sempre que o usuário pedir para fazer deploy, gerenciar projetos/serviços, configurar GitHub auto-deploy, checar logs, alterar env vars ou verificar status no Easypanel. Triggers: /ep, 'fazer deploy', 'deployar', 'redeployar', 'subir no easypanel', 'checar logs do…
docker-management
Manage Docker containers and images via MCP. Use when the user asks to docker ps, tail container logs, restart a service, exec into a container, check CPU/memory stats, or clean up images on the local host.
docker-essentials
Create and optimize Dockerfiles, docker-compose configurations, and container workflows. Use when containerizing applications, setting up development environments, or optimizing Docker builds.
kubernetes-patterns
Kubernetes deployment patterns, resource configuration, and operational best practices.
vercel
Deploy e operação da Vercel pelo terminal via Vercel CLI, complementando o MCP vercel-mcp-pro. Use quando o usuário pedir para fazer deploy, subir na Vercel, ver logs de deploy, configurar env vars, promover preview para produção, fazer rollback ou linkar um projeto. Triggers - /vercel, "deploy na vercel", "subir na…