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.
git clone --depth 1 https://github.com/tenstorrent/tt-studioWrote 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/rules/tenstorrent/tt-studio/docker-deployment)<a href="https://agentmods.dev/rules/tenstorrent/tt-studio/docker-deployment"><img src="https://agentmods.dev/badge/rules/tenstorrent/tt-studio/docker-deployment/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/rules/tenstorrent/tt-studio/docker-deployment"><img src="https://agentmods.dev/badge/rules/tenstorrent/tt-studio/docker-deployment.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 | $0.00000 | $0.00825 |
| Opus 5.5 | $0.00000 | $0.00330 |
| Sonnet 5.5 | $0.00000 | $0.00165 |
| Haiku 4.5 | $0.00000 | $0.00082 |
Grade A, and why
docker-deployment 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 1mo 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.
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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker & Deployment Rules
Rules for containerization, deployment, and infrastructure management in TT Studio.
Deployment Architecture
TT Studio uses a multi-container architecture:
- Frontend Container: React app served via Vite
- Backend Container: Django REST API
- TT Inference Server: FastAPI model inference service
- Hardware Integration: Automatic
/dev/tenstorrentmounting
Setup Script (run.py) Guidelines
The run.py script is the primary interface for TT Studio management:
Core Functionality
- Automatic submodule initialization and management
- Environment variable configuration and validation
- Docker container orchestration
- Hardware detection and integration
- Development and production mode support
Environment Variables
Required variables that must be configured:
JWT_SECRET: Authentication token secretHF_TOKEN: Hugging Face API token for model accessDJANGO_SECRET_KEY: Django security keyTAVILY_API_KEY: Search functionality (optional)
Command Patterns
# Standard setup
python run.py
# Development mode with live reload
python run.py --dev
# Cleanup containers and services
python run.py --stop
Docker Best Practices
Container Design
- Use multi-stage builds for optimization
- Implement proper health checks
- Handle graceful shutdown signals
- Mount only necessary volumes
Hardware Integration
- Automatically detect Tenstorrent devices
- Mount
/dev/tenstorrentwhen available - Provide fallback behavior for missing hardware
- Handle device permissions correctly
Development Mode
- Mount source code volumes for live reload
- Support hot reloading for both frontend and backend
- Maintain development dependencies in separate layers
- Enable debug modes and logging
Production Mode
- Optimize container sizes
- Use production-ready web servers
- Implement proper logging and monitoring
- Handle environment-specific configurations
Port Management
Standard port allocation:
- Frontend: 3000 (Vite dev server)
- TT Inference Server: 8001 (FastAPI)
- Backend: Integrated with frontend container
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.
- 1mo ago First seen · 146 lines · 0 tokens per session scan A c7e3e6c1f1bf
docker-deployment is a cursor rule published in the GitHub repository tenstorrent/tt-studio (51 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 825 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
general
Wonder Blocks design system conventions, component patterns, and coding standards.
mdc-files
Best practices for writing .mdc cursor rules files.
ui-kit-react
React/TypeScript UI kit conventions — components, stories, tests, exports.
windsurfrules
Create detailed components with these requirements.
tanstack-start-guide
TanStack Start best practices emphasizing client-first architecture, type safety, and modern React patterns.
new-component
Workflow for creating new React components.