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/general)<a href="https://agentmods.dev/rules/tenstorrent/tt-studio/general"><img src="https://agentmods.dev/badge/rules/tenstorrent/tt-studio/general/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/general"><img src="https://agentmods.dev/badge/rules/tenstorrent/tt-studio/general.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 | $0.00948 | $0.00948 |
| Opus 5.5 | $0.00379 | $0.00379 |
| Sonnet 5.5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
general 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TT Studio General Development Rules
You are an expert developer working on TT Studio, a web-based AI model management and interaction platform for Tenstorrent hardware.
Project Context
TT Studio is designed to:
- Provide an intuitive GUI for deploying AI models on Tenstorrent hardware
- Support multiple AI model types: Chat (LLMs), Vision (YOLO), Speech (Whisper), Image Generation
- Handle automatic hardware detection and containerized model execution
- Integrate with TT Inference Server and TT-Metal framework
- Offer both local hardware and remote API endpoint connectivity
SPDX License Requirements
MANDATORY: Every new file MUST include appropriate SPDX headers:
Python files:
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: © 2026 Tenstorrent AI ULC
JavaScript/TypeScript files:
// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: © 2026 Tenstorrent AI ULC
Architecture Overview
- Frontend: React + TypeScript + Vite (port 3000)
- Backend: Django REST API (integrated with frontend)
- TT Inference Server: FastAPI (port 8001)
- Containerization: Docker for model isolation
- Hardware: Tenstorrent AI accelerators (auto-detected)
Development Workflow
-
Setup & Environment
- Use
python run.pyfor all setup and management (NOTstartup.sh) - Automatic submodule handling - no manual git submodule commands needed
- Environment variables: JWT_SECRET, HF_TOKEN, DJANGO_SECRET_KEY, TAVILY_API_KEY
- Support both
--devand production modes
- Use
-
Code Quality Standards
- Follow TypeScript strict mode settings
- Use ESLint configuration with header requirements
- Implement proper error handling for AI model operations
- Consider hardware availability in all model-related features
-
Testing Philosophy
- Focus on business logic and user workflows
- Test AI model deployment and inference flows
- Mock hardware dependencies appropriately
- Test error scenarios (hardware unavailable, model failures)
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 · 131 lines · 948 tokens per session scan A 028a79aaa989
general is a cursor rule published in the GitHub repository tenstorrent/tt-studio (51 stars, last pushed yesterday), licensed Apache-2.0. It adds 948 tokens to every session, about $0.0038 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 2026-08-30.
Other cursor rules, from other repositories
openrouter-new-account-rpm
OpenRouter new-account-rpm is a per-model 20 RPM cap that ages out after 7 days.
react-tanstack-router-query-cursorrules-prompt-file
Cursor rules for React SPAs combining TanStack Router v1 and TanStack Query v5 for zero-loading-spinner routing and type-safe server state.
react-tanstack-router-query
React SPA with TanStack Router v1 + TanStack Query v5 — the definitive pattern for zero-loading-spinner routing, type-safe URLs, and cache-first data.
nextjs15-react19-vercelai-tailwind-cursorrules-prompt-file
Cursor rules for Next.js development with React 19, Vercel AI, and Tailwind CSS integration.
general
Wonder Blocks design system conventions, component patterns, and coding standards.
mdc-files
Best practices for writing .mdc cursor rules files.