run-in-altai

run-in-altai is a skill for Claude Code from altaidevorg/altai-app. It costs 76 tokens per session (868 once invoked), scanned B, original, Apache-2.0.

A workflow rule for running Google Colab and Jupyter notebook work inside the ALTAI app. Colab is Google's hosted notebook service, while Jupyter is a notebook environment for running code in cells.

In plain words
What is it for?
Use it to open Colab or Jupyter tabs, run notebook code through ALTAI's supported connection, and handle Colab GPU tasks.
Why use it?
It keeps notebooks, logins, runtimes, and code execution in the app instead of sending the user to a separate browser or process.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the altai-sample plugin — 2 skills, 1 hook shipped together

Good fit Use it to open Colab or Jupyter tabs, run notebook code through ALTAI's supported connection, and handle Colab GPU tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/altaidevorg/altai-app/run-in-altai
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.

Any agent
npx skills add altaidevorg/altai-app --skill run-in-altai
Clone the repo
git clone --depth 1 https://github.com/altaidevorg/altai-app

Made for: Claude Code.

Or install altai-sample, the plugin that ships this one along with the rest of its 2 skills, 1 hook.

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 run-in-altai

README.md
[![agentmods](https://agentmods.dev/badge/skills/altaidevorg/altai-app/run-in-altai/github.svg)](https://agentmods.dev/skills/altaidevorg/altai-app/run-in-altai)
Your own site
<a href="https://agentmods.dev/skills/altaidevorg/altai-app/run-in-altai"><img src="https://agentmods.dev/badge/skills/altaidevorg/altai-app/run-in-altai/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 run-in-altai

Your own site · 80×15
<a href="https://agentmods.dev/skills/altaidevorg/altai-app/run-in-altai"><img src="https://agentmods.dev/badge/skills/altaidevorg/altai-app/run-in-altai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 868 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00076 $0.00868
Opus 5 $0.00038 $0.00434
Sonnet 5 $0.00015 $0.00174
Haiku 4.5 $0.00008 $0.00087

Measured 11d ago against content hash 7a16782e253a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

run-in-altai 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 11d 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

ALTAI ships first-class surfaces for both Colab and Jupyter. Use them. Never tell the user to "open colab.research.google.com in your browser" or "run `jupyter notebook` in a terminal" — the app already handles both insi
docs/sample-plugin/skills/run-in-altai/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ALTAI ships first-class surfaces for both Colab and Jupyter. Use them. Never tell the user to "open colab.research.google.com in your browser" or "run jupyter notebook in a terminal" — the app already handles both inside the workspace.

Colab

Trigger phrases: "open Colab", "run on Colab", "Colab GPU", "T4", "free GPU", an arXiv-paper reproduction request that needs a GPU, or any URL whose host is colab.research.google.com / colab.google.com / *.colab.google.com.

What to do:

  1. Open the Colab URL as a tab in ALTAI. The preview layer auto-promotes Colab hosts to a native child webview (WebviewStack), so logins, runtimes, and cell execution work exactly as in a real browser. Use newPreviewTab(url) and let the promotion happen, or call newWebviewTab(url) directly for a fresh notebook (https://colab.research.google.com/#create=true).
  2. For code execution against a Colab runtime that the agent needs to drive programmatically, route through the Colab MCP bridge that the IsanAgent runtime exposes (python_run + execution harness, provider = Colab). Do not shell out to gcloud, colab-cli, or scraped HTTP endpoints.
  3. If multiple Colab notebooks are open, each gets its own isolated webview label (wv-<tab id>) — no shared session state, no login churn.

Do not:

  • Iframe-embed Colab. The preview layer already refuses (X-Frame-Options); a webview tab is the only working path.
  • Suggest the user copy code into Colab manually. The agent's python_run tool runs it via the harness.

Jupyter

Trigger phrases: "open this notebook", "run the notebook", "edit cell …", "add a cell", any path ending in .ipynb, or a data-science / ML workflow that fits the Notebook Assistant built-in agent.

What to do:

  1. Open the .ipynb with openNotebookTab(path). This routes to NotebookStack, which parses the notebook with the in-tree ipynb parser and renders editable cells — not a read-only preview.
  2. Run cells through the execution harness (provider = jupyter for a local kernel, ssh for remote, or colab for free GPU). Do not spawn a standalone jupyter notebook / jupyter lab server and point the user at localhost:8888.
  3. When adding cells, keep each cell focused on one logical step (load → transform → visualize → train → evaluate). Mirror the existing notebook's cell granularity.
  4. If the user asks for a new notebook, create the .ipynb on disk first, then open it with openNotebookTab. Do not paste cell content into the chat as a substitute.

Read the full file on GitHub · 46 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. 11d ago First seen · 46 lines · 76 tokens per session scan B 7a16782e253a

Subscribe to this mod's changes

run-in-altai is a skill published in the GitHub repository altaidevorg/altai-app (2 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 868 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

prompt-cache-optimizer

Audit and optimize Pisper system-prompt and tool-schema token overhead while preserving stable prompt-cache prefixes, permissions, and runtime behavior. Invoke only for explicit prompt or tool-context optimization work.

ling-kong-ran/pisper · 42 tokens

tauri-pilot

Inspect, interact with, and test a running Tauri v2 app via CLI. Communicates over Unix socket using JSON-RPC 2.0. Use when testing UI, automating interactions, or debugging a Tauri app.

mpiton/tauri-pilot · 52 tokens

anarlog

Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.

fastrepl/anarlog · 44 tokens

screenshot-studio

Regenerate the Pisper product screenshots under docs/shots/ against the current UI. Starts an isolated dev instance, seeds fictional demo data through the real runtime APIs, captures every referenced page at the exact 2558x1380 asset size, and replaces the files. Use only when the user asks to refresh product…

ling-kong-ran/pisper · 80 tokens

graphify-windows

Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md.

saeedkolivand/ai-job-hunter-app · 75 tokens

browser-bridge

Token-efficient Chrome tab inspection, interaction, and patching via local bridge extension (CLI: bbx). Reads live DOM, styles, console, network, and storage from a real Chrome tab with lower token cost than screenshots.

koltyakov/browser-bridge · 49 tokens