setup-python-tools

A setup guide for running Python code inside a Flows app through Pyodide, a tool that runs Python in the browser. It connects this runtime to Atlas chat so agents can use Python tools.

In plain words
What is it for?
Use it when adding Python tool support to a Flows app. It covers installing the Python runtime, showing its loading state, and wiring it into Atlas chat.
Why use it?
It removes the need to manually install Pyodide, configure its React hook, or connect the Python runtime to chat. It also requires Atlas chat integration to be in place first.

Skill for Claude CodeCodex

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/cognitedata/builder-skills/setup-python-tools
Any agent
npx skills add cognitedata/builder-skills --skill setup-python-tools
Clone the repo
git clone --depth 1 https://github.com/cognitedata/builder-skills

Made for: Claude Code, Codex.

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,665 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00110 $0.01665
Opus 5 $0.00055 $0.00833
Sonnet 5 $0.00022 $0.00333
Haiku 4.5 $0.00011 $0.00167

Measured yesterday against content hash fe9dc97ba76d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup-python-tools 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 yesterday.

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.

skills/setup-python-tools/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set Up Python Tool Execution

Add client-side Python tool execution via Pyodide to this Flows app.

Target: $ARGUMENTS

Prerequisite

integrate-atlas-chat must already be complete: the app should have vendored atlas-agent code under src/atlas-agent/ (including react.ts for useAtlasChat) and the peer dependency from that skill (@sinclair/typebox). Copy the Python-related modules from the integrate-atlas-chat skill code/ directory into src/atlas-agent/ when adding Pyodide (python.ts, pyodide.ts, pyodide-react.ts, pyodide-runtime.ts — see integrate-atlas-chat Step 5).

Background

Atlas agents can have Python tools defined in their CDF config (type: "runPythonCode"). When the agent calls one, it arrives as a toolConfirmation (auto-allowed) followed by a clientTool action. The library fetches the tool's Python code from the agent config automatically and executes it via the provided pythonRuntime.

You only need to:

  1. Set up usePyodideRuntime to get a runtime instance
  2. Pass pythonRuntime to useAtlasChat

No PythonToolConfig entries — the library reads the code from the agent's CDF config.

The flow is:

  1. usePyodideRuntime loads Pyodide (~30MB, cached after first load), installs packages, and injects Cognite SDK credentials into the Python environment
  2. When the agent calls a Python tool, the library fetches its code from the agent's CDF config (cached per session), wraps it, executes it in Pyodide, and returns the result

Step 1 — Understand the app

Read these files before touching anything:

  • package.json — detect package manager and existing deps
  • The component that calls useAtlasChat — understand current tools/config

Step 2 — Install Pyodide

Install exactly [email protected] using the app's package manager. This version must match the CDN artifacts loaded at runtime — installing a different version will cause errors.

Read the full file on GitHub · 177 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. yesterday First seen · 177 lines · 110 tokens per session scan A fe9dc97ba76d

Subscribe to this mod's changes

setup-python-tools is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 110 tokens to every session and 1,665 once invoked, about $0.0006 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

mintlify-preview

Run the public Mintlify product docs site locally for live preview. Use when previewing or iterating on docs under docs/ (.mdx/.md pages, docs.json nav), or when the user says "start the docs", "run mintlify", "preview the docs site".

latitude-dev/latitude-llm · 69 tokens