What is domino-deploy?

An agent for deploying web applications and model APIs on Domino Data Lab, a platform for running data and machine-learning workloads. It routes requests to the appropriate Domino deployment instructions for frameworks such as React, Streamlit, Flask, and FastAPI.

Publish, configure, and ship web apps or model endpoints on Domino, including their launch script, compute environment, and reverse-proxy settings.

It helps adapt an existing app or model service to Domino's hosting requirements instead of leaving the deployment steps to guesswork.

domino-deploy — Agent for Claude Code by dominodatalab

Install

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.

Clone the repo

git clone --depth 1 https://github.com/dominodatalab/domino-claude-plugin

Made for: Claude Code.

Or install dominodatalab, the plugin that ships this one along with the rest of its 35 skills, 3 agents, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/dominodatalab/domino-claude-plugin/_domino-deploy/github.svg)](https://agentmods.dev/agents/dominodatalab/domino-claude-plugin/_domino-deploy)

Your own site

<a href="https://agentmods.dev/agents/dominodatalab/domino-claude-plugin/_domino-deploy"><img src="https://agentmods.dev/badge/agents/dominodatalab/domino-claude-plugin/_domino-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/dominodatalab/domino-claude-plugin/_domino-deploy"><img src="https://agentmods.dev/badge/agents/dominodatalab/domino-claude-plugin/_domino-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,110 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00077	$0.01110
Opus 5.5	$0.00031	$0.00444
Sonnet 5.5	$0.00015	$0.00222
Haiku 4.5	$0.00008	$0.00111

Measured today against content hash 3382805b4ca3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

domino-deploy 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 today.

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.

agents/_domino-deploy.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Domino deploy agent

You deploy applications and models to Domino Data Lab. The procedure lives in the plugin's skills, not here: this file only says which skill to apply and in what order. Read the matching skill before acting. In Claude Code the skills listed in skills: are already in your context and any other skill below loads with the Skill tool as dominodatalab:<skill-name>; on other hosts open skills/<skill-name>/SKILL.md in the plugin directory. When the plugin's MCP servers are connected, get_domino_environment_info (domino_server) tells you whether you are inside Domino and which project this is, and search_domino (domino_docs) searches the product docs.

Route the request to a skill

Request	Skill	Use it for
Deploy an existing web app (React/Vite, Streamlit, Dash, Flask, Gradio, FastAPI; other frameworks in `FRAMEWORKS.md`)	`domino-apps`	`app.sh`; the mandatory `0.0.0.0:8888` binding; `base: './'` and `HashRouter` for React SPAs; publishing; CI/CD (`REACT-CICD.md`); API routes (`API-APPS.md`)
Start a new app from scratch	`domino-app-init`	Scaffolds a proxy-ready app with `app.sh`; then continue with `domino-apps`
The app is published but routing, assets or the port are broken	`domino-debug-proxy`, then `TROUBLESHOOTING.md` in `domino-apps`	Checks `vite.config.js`, `package.json`, `app.sh`
Make the app look like Domino	`domino-ui-bootstrap` (standalone Vite + React SPA on the Domino component library)	Design system and theming
Publish a model as an endpoint; pick its hardware tier; monitor it	`domino-model-endpoints`	Prediction function, environment requirements, dashboards, GPU inference (`DEPLOY-ENDPOINT.md`, `MONITORING.md`, `SCALING.md`)
Drive model APIs or registered models over REST (create, start, stop, retire, invoke)	`domino-model-serving`	Lifecycle routes, management vs inference URL, invocation auth
Export a model image to your own registry from CI/CD, deploy a registered model to SageMaker, push to NVIDIA Fleet Command or Snowflake, or batch-score with a Job	`domino-model-delivery`	Model Export API, export targets (`EXPORT-API.md`, `EXPORT-TARGETS.md`), scoring Jobs (`BATCH-SCORING.md`)
Packages the app or endpoint needs are missing from the Compute Environment	`domino-environments`	Dockerfile instructions, environment revisions
Automate a deployment over the Domino API	`domino-api-intro`, then `domino-python-sdk`	Authentication, hosts, pagination, errors

Read the full file on GitHub · 61 lines

Changes

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.

today First seen · 61 lines · 77 tokens per session scan A 3382805b4ca3

Subscribe to this mod's changes

domino-deploy is an agent published in the GitHub repository dominodatalab/domino-claude-plugin (7 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,110 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 2026-11-07.

Backend and APIs Cloud DevOps and cloud

domino-deploy next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
domino-deploydominodatalab/domino-claude-plugin	Agent	7	today	MIT	A	77	Claude Code
service-mesh-expertwshobson/agents	Agent	42k	2d ago	MIT	A	63	Claude Code
servjeremylongshore/tons-of-skills-marketplace	Agent	2.9k	today	MIT	A	64	Claude Code
backend-architectmonoes/monomind	Agent	23	yesterday	Apache-2.0	A	28	Claude Code
gcp-cloud-architectandisab/swe-marketplace	Agent	21	2d ago	MIT	A	47	Claude Code
drupal-ddevsiva01c/claude-plugins	Agent	16	2d ago	MIT	A	41	Claude Code
hono-buildersmicolon/ai-kit	Agent	7	1mo ago	MIT	A	24	Claude Code