marimo

marimo is a skill for Claude Code, Codex from fmind/dot. It costs 41 tokens per session (1,017 once invoked), scanned A, original, MIT.

A guide for creating and checking reactive Python notebooks and apps with marimo, where changing one cell can rerun cells that depend on it.

In plain words
What is it for?
Use it to edit notebooks with live reload, run marimo apps, manage cell reactivity, and perform strict checks or targeted fixes.
Why use it?
It helps preserve notebook dependencies and cell structure while catching syntax, dependency, and diagnostic problems before they affect the app.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex; mentions OpenCode.

Good fit Use it to edit notebooks with live reload, run marimo apps, manage cell reactivity, and perform strict checks or targeted fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fmind/dot/marimo
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 fmind/dot --skill marimo
Clone the repo
git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, Codex.

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 marimo

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/marimo/github.svg)](https://agentmods.dev/skills/fmind/dot/marimo)
Your own site
<a href="https://agentmods.dev/skills/fmind/dot/marimo"><img src="https://agentmods.dev/badge/skills/fmind/dot/marimo/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 marimo

Your own site · 80×15
<a href="https://agentmods.dev/skills/fmind/dot/marimo"><img src="https://agentmods.dev/badge/skills/fmind/dot/marimo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,017 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00041 $0.01017
Opus 5 $0.00020 $0.00508
Sonnet 5 $0.00008 $0.00203
Haiku 4.5 $0.00004 $0.00102

Measured today against content hash 8e3d31d9e6fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

marimo scanned grade A 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 today.

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.

Makes network callslowCapability

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

Pairing scripts require `bash`, `curl`, and `jq` plus authority to execute code in the selected notebook. Review scripts and any harness permission entries through the [vendor-skill policy](../agent-project/references/ve
skills/marimo/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

marimo

Use marimo for reactive Python notebooks and apps; configure agent pairing and harness workflows, and install upstream skills through agent-project.

Workflow

  1. Inspect the environment: use marimo --version and the installed command help; prefer uv run marimo when the project declares marimo. Preserve the notebook's dependency model, including existing PEP 723 metadata.
  2. Edit with disk reload: marimo edit --watch notebook.py lets the running notebook reload agent edits. Keep the default loopback host and token authentication; cell execution can access local files, network services, and credentials.
  3. Respect reactivity: each global name belongs to one cell; use _name for cell-local intermediates. Preserve @app.cell structure and make side effects deliberate because dependent cells can rerun after upstream edits.
  4. Check before fixing: marimo check --strict notebook.py reports notebook diagnostics and fails on warnings. Apply marimo check --fix notebook.py only to the intended file, review the diff, then rerun the strict check. Fixes do not automatically repair every dependency or syntax problem; --unsafe-fixes can change behavior.
  5. Exercise behavior: run representative inputs and inspect outputs and exceptions in the notebook. Lint success alone does not prove cell execution, data correctness, or app behavior.
  6. Convert or export: use the commands below, review conversion diagnostics, and validate the result. HTML export executes the notebook unless an installed option says otherwise; outputs and source may contain private data. marimo run hides editing controls but still executes Python on the server.

Commands

marimo edit --watch notebook.py
marimo check --strict notebook.py
marimo run notebook.py
marimo convert notebook.ipynb -o notebook.py
marimo export html notebook.py -o notebook.html
marimo pair prompt --url http://127.0.0.1:2718 --with-token

Read the full file on GitHub · 53 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. today Changed · +1 lines 8e3d31d9e6fd
  2. 2d ago First seen · 52 lines · 41 tokens per session scan A 34a9379fccc5

Subscribe to this mod's changes

marimo is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,017 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.