Marimo Pair

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. During a session, you SHOULD NOT modify the associated .py file directly. File edits WILL NOT reach the active kernel or user, and the kernel may overwrite them on save. Use marimo._code_mode (cm) for notebook changes. Reading disk is fine, but prefer ctx.cells[...].code for current cell code.

The harness reports the absolute path to this SKILL.md. Resolve bundled scripts/... and reference/... paths from its parent directory, even when the current working directory is a notebook workspace. In command examples, replace /absolute/path/to/marimo-pair with that directory.

Required first kernel command

Start every code-mode session with this dedicated command:

bash /absolute/path/to/marimo-pair/scripts/execute-code.sh \
  --url http://localhost:2718 \
  -c "import marimo._code_mode as cm; help(cm)"

Follow this order for each kernel, including read-only tasks:

1. Run the inspection command once.
2. Wait for successful help(cm) output.
3. Then use cm.get_context() or another cm API in a later call.

Do not run task-specific cm code before the inspection command succeeds.

Connect to a Notebook

Use the bundled execute-code.sh from the reported skill directory or MCP (execute_code(...)) to run Python in a live marimo kernel.

execute-code.sh always takes --url. If the user provides a notebook URL, run the required inspection against it directly:

bash /absolute/path/to/marimo-pair/scripts/execute-code.sh \
  --url http://localhost:2718 \
  -c "import marimo._code_mode as cm; help(cm)"

After that command succeeds, pass task code with -c CODE, - for stdin, or a file path:

bash /absolute/path/to/marimo-pair/scripts/execute-code.sh \
  --url http://localhost:2718 - <<'PY'
import marimo._code_mode as cm

async with cm.get_context() as ctx:
    cid = ctx.create_cell("x = df.head()")
    ctx.run_cell(cid)
PY

If the user gives no URL, find or start a notebook. Look for a running server with bash /absolute/path/to/marimo-pair/scripts/discover-servers.sh, MCP list_sessions(), or local process context, and pass the url it reports to --url. With one notebook open, the script targets it automatically; with several, pass --file with the notebook's file key.

If no server is running and the user wants a notebook, start marimo with --no-token (and without --headless) so it auto-registers for discovery. The notebook UI must be open for execute-code to target it. The right invocation depends on context (project tooling, global install, sandbox mode). If the notebook file contains a PEP 723 # /// script header, it MUST be opened with --sandbox — otherwise marimo ignores the inline dependencies. See finding-marimo.md for the full decision tree and execution-context.md for selector resolution, scripts, MCP, and shell quoting.

Scratchpad Scope

execute-code evaluates Python in marimo's scratchpad: a temporary namespace with a shallow copy of the kernel globals. Notebook variables are available by name, but new top-level bindings and rebindings are discarded after each call. In-place mutations to notebook-owned objects can persist because those names still reference live objects.

Each call reports stdout and stderr from the scratchpad, plus console output from notebook cells it causes to run, including reactive descendants.

Ordinary Python

Use ordinary Python in the scratchpad to inspect variables, sample data, test transformations, probe APIs, check imports, and read widget state.

print(df.head())

x = 10
print(x)

Here df comes from notebook globals, while x is a scratchpad-local binding. x exists for this call only and WILL NOT be added to notebook globals.

Persist with cm

Top-level scratchpad assignments and rebindings are temporary. To persist work, including new variables, you MUST submit changes through marimo._code_mode (cm).

marimo._code_mode is a PRIVATE, UNSTABLE agent API (note the leading underscore). It exists for tools like this skill to drive a live kernel from the scratchpad. DO NOT import it from notebook cells, library code, or anything a user would run — methods can change or disappear across marimo versions and kernels. Treat every import marimo._code_mode as cm as scratchpad-only.

Open a code-mode context to queue notebook changes.

import marimo._code_mode as cm

async with cm.get_context() as ctx:
    cid = ctx.create_cell("x = df.head()")
    ctx.run_cell(cid)

The scratchpad supports top-level async code. Use async with directly; wrapping it in asyncio.run(...) is unnecessary and can conflict with the kernel's event loop.

After this block exits and the new cell runs, x is notebook state. Later scratchpad calls can read x by name. Code later in the same scratchpad call should read ctx.globals["x"], because the scratchpad namespace was copied before the cell ran.

Inside the context, queued mutation methods are synchronous. Call them directly; do not await them. Each call queues an operation for marimo to apply when the context exits normally. If the block raises, the queue is discarded.

On clean exit, marimo applies packages, validates and applies structural cell changes, runs queued cells, then may run dependents. Validation is only structural since queued cell runs can still error. create_cell and edit_cell change notebook structure only. Use run_cell to execute.

create_cell currently defaults to hide_code=True, which collapses the code editor in the UI. Pass hide_code=False if the user wants created cells to be visible without manually expanding them.