agentmods.dev

tt-studio: Skill for Claude Code

.claude/skills/tt-studio-add-model/SKILL.md

tt-studio-add-model is a skill for Claude Code from tenstorrent/tt-studio. It costs 156 tokens per session (3,253 once invoked), scanned C, original, Apache-2.0.

A playbook for adding a model supported by TT-Inference-Server to TT-Studio when it cannot yet be deployed there. It covers catalog changes, deployment on real hardware, failures across the related software layers, running-container patches, and a patched container image.

In plain words
What is it for?
Use it to bring supported models into TT-Studio, diagnose deployment failures, test fixes on hardware, and prepare a patched image.
Why use it?
It gives a repeatable path through a change that spans the user interface, inference server, and hardware software. It also keeps work isolated in a Git worktree, a separate working directory tied to a branch.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is tenstorrent/tt-studio's own configuration. It tells Claude Code how to work on tt-studio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tt-studio configures →

not rated 52repo yesterday C scan 156 tokens original Apache-2.0
View source ↗ tenstorrent/tt-studio docs.tenstorrent.com
Reuse

Borrowing it

Nothing to install: this file belongs to tenstorrent/tt-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tenstorrent/tt-studio/main/.claude/skills/tt-studio-add-model/SKILL.md
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-add-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/tenstorrent/tt-studio/tt-studio-add-model/github.svg)](https://agentmods.dev/skills/tenstorrent/tt-studio/tt-studio-add-model)
Your own site
<a href="https://agentmods.dev/skills/tenstorrent/tt-studio/tt-studio-add-model"><img src="https://agentmods.dev/badge/skills/tenstorrent/tt-studio/tt-studio-add-model/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.

agentmods 80×15 button for tt-studio-add-model

Your own site · 80×15
<a href="https://agentmods.dev/skills/tenstorrent/tt-studio/tt-studio-add-model"><img src="https://agentmods.dev/badge/skills/tenstorrent/tt-studio/tt-studio-add-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,253 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 3 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00156 $0.03253
Opus 5.5 $0.00062 $0.01301
Sonnet 5.5 $0.00031 $0.00651
Haiku 4.5 $0.00016 $0.00325

Measured 21d ago against content hash 6d4186557235, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

tt-studio-add-model scanned grade C with 3 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 21d 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.

curl -X POST :8000/docker/deploy/ -d '{"model_id": "<id>", "weights_id": ""}'

Asks for rootmediumPrivilege escalation

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

| Token updated via Settings UI but container still gets the old one | **tt-studio** (known bug #1235) | `user_config.env` in the persistent volume is root-owned; the host inference-api can't read it and silently falls b

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s :8000/docker/get_containers/ | grep <model-name>
.claude/skills/tt-studio-add-model/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add a tt-inference-server Model to TT-Studio

Battle-tested playbook for taking a model from "listed in tt-inference-server" to "generating output through the TT-Studio UI", including the cross-repo triage when it doesn't work. Motif-Image-6B-Preview on p300x2 (tt-studio#1234, tt-metal#53197, tt-inference-server#4955/#4956) and mochi-1-preview are the reference runs of this playbook.

Ground rules

  • Work in a git worktree off origin/dev (git worktree add .claude/worktrees/<name> -b <username>/<feature> origin/dev). Never edit the main checkout's branch — it may be another session's live work.
  • All git/PR mechanics follow the feature-branch-pr skill: branch <username>/<feature> off dev, minimal in-scope diff, human commit messages, PR targets dev, no AI attribution anywhere (no Co-Authored-By trailers, no mention of AI tools in commits, PR text, or issues).
  • Ask the user before stopping someone's running deployment or changing shared state (tokens, .env, board resets).

1. Recon before touching anything

  1. Upstream truth: read the model_support doc (tt-inference-server/docs/model_support/<type>/<Model>_<device>.md) — HF repo, docker image + tag, impl, inference engine, tt-metal commit. Treat its "Complete 🟢" status as a claim to verify, not a fact: the Motif doc's own pinned image could not run the model at all.
  2. Artifact spec (the deploy-time source of truth for prod models): .artifacts/tt-inference-server/workflows/model_specs/<env>/*.yaml. If the model + device entry is already in the pinned artifact version, no artifact bump and no requires_dev_catalog/inference_artifact_ref are needed. Root model_spec.json / release_model_spec.json are generated exports — never edit them; .artifacts/ edits are ephemeral anyway.
  3. tt-studio catalog: check app/backend/shared_config/models_from_inference_server.json for the model and for a same-type sibling to copy field-for-field (e.g. FLUX.1-dev for an image model). Field mapping rules live in app/backend/shared_config/sync_models_from_inference_server.py (map_model_type, map_service_route, DEVICE_TYPE_TO_CONFIG).
  4. Hardware reality: tt-smi -ls, GET :8000/docker/chip-status/. Know the board semantics: a P300x2 "board" is ALL 4 chips (2 p300c cards); one multi-chip deployment occupies the whole board, and another multi-chip model cannot deploy until it's stopped.
  5. What's running: docker ps, GET :8000/docker/deployments/. If chips are occupied, ask the user before stopping anything, and record the occupant's model_id so it can be redeployed.

Read the full file on GitHub · 219 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. 21d ago First seen · 219 lines · 156 tokens per session scan C 6d4186557235

Subscribe to this mod's changes

tt-studio-add-model is a skill published in the GitHub repository tenstorrent/tt-studio (52 stars, last pushed yesterday), licensed Apache-2.0. It adds 156 tokens to every session and 3,253 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it C with 3 findings (sends data to an external url, asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-17.

Git and workflowHardware and IoTReactacceleratorai-agentsbackend-servicechat-applicationui-components
Related

tt-studio-add-model compared with skills from other repositories

tt-studio-add-model next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tt-studio-add-modeltenstorrent/tt-studioSkill52yesterdayApache-2.0C156Claude Code
git-safetytamagui/tamaguiSkill14ktodayMITA0Claude Code
release-safetytamagui/tamaguiSkill14ktodayMITA0Claude Code
compiler-commitreact/reactSkill252kyesterdayMITA42Claude Code
merge-seedkriasoft/react-starter-kitSkill24k4d agoMITA49Claude Code, Codex
tamagui-upgrade-v3tamagui/tamaguiSkill14ktodayMITA120Claude Code, Codex
tamaguitamagui/tamaguiSkill14ktodayMITA44Claude Code, Codex