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 dominodatalab/domino-claude-plugin --skill appsgit clone --depth 1 https://github.com/dominodatalab/domino-claude-pluginWrote 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/dominodatalab/domino-claude-plugin/apps)<a href="https://agentmods.dev/skills/dominodatalab/domino-claude-plugin/apps"><img src="https://agentmods.dev/badge/skills/dominodatalab/domino-claude-plugin/apps/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/dominodatalab/domino-claude-plugin/apps"><img src="https://agentmods.dev/badge/skills/dominodatalab/domino-claude-plugin/apps.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 | $0.00080 | $0.01459 |
| Opus 5 | $0.00040 | $0.00730 |
| Sonnet 5 | $0.00016 | $0.00292 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade B, and why
domino-apps scanned grade B with 2 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 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
resp = requests.post( "https://your-domino-instance/apps-internal/APP_ID/endpoint", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
API_TOKEN = requests.get("http://localhost:8899/access-token").text How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domino Apps Skill
This skill provides comprehensive knowledge for deploying web applications to Domino Data Lab, with special focus on React applications using Vite.
Key Concepts
Domino App Architecture
Domino apps run in containers behind a reverse proxy that:
- Authenticates users via Domino's auth system
- Strips the URL prefix before forwarding to your app
- Routes traffic to your app container
- Handles infrastructure provisioning, routing, and resource management
Note: Port selection is flexible; port 8888 is no longer required. You can use any port your application prefers.
Critical Configuration Points
- Host Binding: Bind to
0.0.0.0(not localhost) so Domino can reach your app - Relative Base Path: Use
base: './'in Vite config for React apps - app.sh: Entry point script (launch file) that Domino executes
Related Documentation
- REACT-VITE-GUIDE.md - Deep dive into Vite + React configuration
- REACT-CICD.md - CI/CD setup with GitHub Actions
- FRAMEWORKS.md - Streamlit, Dash, Flask configurations
- TROUBLESHOOTING.md - Common issues and solutions
Quick Start
React with Vite
// vite.config.js
import { defineConfig } from 'vite'
import react from '@vitejs/plugin-react'
export default defineConfig({
plugins: [react()],
base: './', // CRITICAL for Domino proxy
server: { host: '0.0.0.0', port: 8888, strictPort: true },
preview: { host: '0.0.0.0', port: 8888, strictPort: true },
})
# app.sh
#!/bin/bash
set -e
cd /mnt/code
npm ci
npm run build
npx serve -s dist -l 8888 --no-clipboard
Streamlit
# app.sh
#!/bin/bash
streamlit run app.py --server.port 8888 --server.address 0.0.0.0
Dash/Flask
# app.sh
#!/bin/bash
python app.py # Must bind to 0.0.0.0:8888
Environment Variables
Domino provides these environment variables to your app:
| Variable | Description |
|---|---|
DOMINO_PROJECT_NAME |
Current project name |
DOMINO_PROJECT_OWNER |
Project owner username |
DOMINO_RUN_ID |
Current run identifier |
DOMINO_STARTING_USERNAME |
User who started the app |
What ships with it
4 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.
- 9d ago First seen · 174 lines · 80 tokens per session scan B 386236221935
domino-apps is a skill published in the GitHub repository dominodatalab/domino-claude-plugin (6 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 1,459 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, 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
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
agent-platform-endpoint-management
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).
modal
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.