marimo-pair

A way to work directly inside a user’s live marimo notebook, a Python notebook whose cells update each other when their data changes. It can inspect the running notebook and apply changes through its own code-editing system.

In plain words
What is it for?
Inspecting notebook state, running Python, adding or editing cells, changing values or packages, and saving durable changes to the notebook.
Why use it?
The live notebook session contains the current cells, variables, outputs, and dependencies, so changing only the file on disk can leave the user’s running notebook unchanged or cause edits to be overwritten.

Skill for Claude CodeCodex

▶ Using claude code with marimo marimo · about marimo-team/marimo · on YouTube →
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/marimo-team/marimo/marimo-pair
Any agent
npx skills add marimo-team/marimo --skill marimo-pair
Clone the repo
git clone --depth 1 https://github.com/marimo-team/marimo

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,580 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 $0.00057 $0.02580
Opus 5 $0.00028 $0.01290
Sonnet 5 $0.00011 $0.00516
Haiku 4.5 $0.00006 $0.00258

Measured 2d ago against content hash 7ee57b94324e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

marimo-pair 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 2d 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

marimo/_server/ai/skills/marimo-pair/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

marimo is a reactive Python runtime for building reproducible Python programs (marimo notebooks). Cells are connected by the variables they define and reference. Running a cell re-executes dependents in dataflow order. The active runtime holds the kernel namespace, cell state, and dataflow graph. The notebook (.py file) is the artifact the kernel writes from that state while a session is running.

A user interacts with the same runtime via a notebook UI with cells, outputs, and widgets.

WARNING. The active runtime is the source of truth. You are working inside the user's live notebook session. The kernel — not the .py file on disk — holds the truth about cells, variables, and the dataflow graph. Make every notebook change through marimo._code_mode (cm); direct file edits WILL NOT reach the live kernel or user, and the kernel may overwrite them on save. Reading disk is fine, but prefer ctx.cells[...].code for current cell code.

WARNING. Every notebook edit goes through code mode — no exceptions. When the user asks you to change the notebook (add, edit, delete, or run a cell; rename; change a value or a package), you MUST make that change through marimo._code_mode (cm) by running it with the execute_code tool. There is no separate file-editing path — execute_code + cm is the only way to reach the user's running session. Running ad-hoc Python with execute_code to explore or test is fine; persisting any change to the notebook is only ever done via cm.

Running Code in the Kernel

You are already attached to the user's running notebook — there is nothing to connect to or start. Use the execute_code tool to run Python in that kernel, passing your Python as the code argument. Everything you do — inspecting state, testing transformations, and persisting changes via cm — runs through execute_code in the scratchpad (see below).

Required First Kernel Command

Start every code-mode session with this dedicated execute_code call:

Read the full file on GitHub · 278 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 278 lines · 57 tokens per session scan A 7ee57b94324e

Subscribe to this mod's changes

marimo-pair is a skill published in the GitHub repository marimo-team/marimo (22,550 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 2,580 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

cnsplots

Create, revise, and troubleshoot publication-ready scientific plots in Python with cnsplots, including distribution, regression, heatmap, genomics, survival, set, flow, and multi-panel figures. Use when a user asks for cnsplots code, Cell/Nature/Science-style visualization, precise pixel-sized figures, statistical…

faridrashidi/cnsplots · 79 tokens

addressing-pr-review-comments

Address all valid review comments on a PR for the current branch in the streamlit/streamlit repo. Covers both inline review comments and general PR (issue) comments. Use when a PR has reviewer feedback to address, including code changes, style fixes, and documentation updates.

streamlit/streamlit · 61 tokens

generating-changelog

Generates polished website release notes between two git tags for docs.streamlit.io. Use when preparing a new Streamlit release or reviewing changes between versions.

streamlit/streamlit · 35 tokens

understanding-streamlit-architecture

Explains Streamlit's internal architecture including backend runtime, frontend rendering, and WebSocket communication. Use when debugging cross-layer issues, understanding how features work end-to-end, planning architectural changes, or onboarding to the codebase. Covers ForwardMsg/BackMsg protocol, script rerun…

streamlit/streamlit · 75 tokens

debugging-streamlit

Debug Streamlit frontend and backend changes using make debug with hot-reload. Use when testing code changes, investigating bugs, checking UI behavior, or needing screenshots of the running app.

streamlit/streamlit · 41 tokens

fixing-flaky-e2e-tests

Diagnose and fix flaky Playwright e2e tests. Use when tests fail intermittently, show timeout errors, have snapshot mismatches, or exhibit browser-specific failures.

streamlit/streamlit · 43 tokens