tt-studio-cli

tt-studio-cli is a skill for Claude Code from tenstorrent/tt-studio. It costs 168 tokens per session (2,761 once invoked), scanned B, original, Apache-2.0.

Development guidance for TT-Studio’s Python command-line program, including its commands, package layout, terminal output, and configuration handling.

In plain words
What is it for?
Use it when modifying setup, start, stop, purge, logs, status, or bug-report commands and their supporting code.
Why use it?
It helps changes fit the project’s existing command-line conventions and keeps the main launcher organized.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

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.

agentmods
npx agentmods add skills/tenstorrent/tt-studio/tt-studio-cli
Any agent
npx skills add tenstorrent/tt-studio --skill tt-studio-cli
Clone the repo
git clone --depth 1 https://github.com/tenstorrent/tt-studio

Made for: Claude Code.

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.

agentmods badge for tt-studio-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/tenstorrent/tt-studio/tt-studio-cli.svg)](https://agentmods.dev/skills/tenstorrent/tt-studio/tt-studio-cli)
Your own site
<a href="https://agentmods.dev/skills/tenstorrent/tt-studio/tt-studio-cli"><img src="https://agentmods.dev/badge/skills/tenstorrent/tt-studio/tt-studio-cli.svg" alt="Measured on agentmods" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,761 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00168 $0.02761
Opus 5 $0.00084 $0.01380
Sonnet 5 $0.00034 $0.00552
Haiku 4.5 $0.00017 $0.00276

Measured 6d ago against content hash 7e2ea4b88bb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

tt-studio-cli scanned grade B with 1 finding 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 6d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`--fix-docker` or Linux-only `sudo service docker start`. Compose **v2** only.
.claude/skills/tt-studio-cli/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TT-Studio CLI (python run.py / tt_setup/)

python run.py is the one entrypoint for everything (setup, start, stop, purge, logs, status, bug reports). run.py itself is a thin shim: it bootstraps deps into a managed venv and delegates to the tt_setup/ package. startup.sh is deprecated.

Read this before touching the launcher. For the terminal-output design system specifically, dev-docs/launcher-terminal-design.md is the canonical reference — this skill covers the broader "how the launcher is built and how we like CLIs."

Architecture

run.pytt_setup.bootstrap.ensure_environment() (venv) → tt_setup.cli.main().

The package is split into focused subpackages, each with an __init__.py that re-exports its prior public surface:

Area Package / module
CLI surface + orchestration cli/ (_args.py = Typer flags, _run.py = phased flow + early dispatch)
Terminal design system console/ (_theme, _stepper, _panels, _prompts, _steps)
Env & secrets config env_config/ (_values, _dotenv, _preferences, _hf_access, _version, _configure)
Host services lifecycle services/ (_ports, _fastapi, _docker_control, _frontend, _health)
Inference-server artifact inference_server/ (_catalog, _config, _env, _git, _metadata, _privileges, _orchestrator)
Stop / purge teardown cleanup/ (_runtime, _orchestrate, _resource_ops)
Docker build/failure diag docker_diag/ (_build_progress, _diagnostics)
Standalone modules bootstrap.py, shell.py, startup_checks.py, docker.py, constants.py, logging.py, monitor.py/monitor_app.py (--status TUI), bug_report.py (--report-bug), shortcut.py (--install-shortcut), spdx.py, settings.py, venv_utils.py

The re-export rule. A package's __init__.py imports and re-exports the names its submodules define, so from tt_setup.console import step and import tt_setup.console as C keep working. When you add/move a submodule, wire its public names through the __init__.

Read the full file on GitHub · 170 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.

  1. 6d ago First seen · 170 lines · 168 tokens per session scan B 7e2ea4b88bb0

Subscribe to this mod's changes

tt-studio-cli is a skill published in the GitHub repository tenstorrent/tt-studio (49 stars, last pushed today), licensed Apache-2.0. It adds 168 tokens to every session and 2,761 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

compiler-orchestrator

Orchestrate the Rust compiler port end-to-end. Discovers the current frontier, fixes failing passes, ports new passes, reviews, and commits in a loop.

react/react · 38 tokens

client-setup

Create a vanilla tRPC client with createTRPCClient (), configure link chain with httpBatchLink/httpLink, dynamic headers for auth, transformer on links (not client constructor). Infer types with inferRouterInputs and inferRouterOutputs. AbortController signal support. TRPCClientError typing.

trpc/trpc · 63 tokens

adapter-express

Mount tRPC as Express middleware with createExpressMiddleware() from @trpc/server/adapters/express. Access Express req/res in createContext via CreateExpressContextOptions. Mount at a path prefix like app.use('/trpc', ...). Avoid global express.json() conflicting with tRPC body parsing for FormData.

trpc/trpc · 67 tokens

trpc-router

Entry point for all tRPC skills. Decision tree routing by task: initTRPC.create(), t.router(), t.procedure, createTRPCClient, adapters, subscriptions, React Query, Next.js, links, middleware, validators, error handling, caching, FormData.

trpc/trpc · 59 tokens

review-pending-pr-reviews

Review, grill, edit, and post pending PR review drafts saved by /review-pr (or its batch/cron runners). Lists drafts that have not yet been posted, walks the maintainer through each finding, then posts, closes, or discards. Use when the user says "post my pending reviews", "what reviews are waiting", "go through the…

nrwl/nx · 93 tokens

compiler-port

Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.

react/react · 35 tokens