approvals
01Command
Write tool calls that wait for a person.
Command
Write tool calls that wait for a person.
Command
One question, routed to whoever can answer it.
Command
The brain is what you have read and kept: a folder of Markdown that px0 ingests into, indexes, and answers questions from. It can be px0's own brain/ folder or any folder of Markdown you already keep — including an Obsidian vault.
Command
A change is one atomic write across the store — a workflow build, a guideline the build wrote, a hand edit px0 noticed, a migration. It is the store's log of what happened and its unit of undo: changes shows each one, with a per-file diff, and reverts a whole change at once.
Command
Command "completion" from px0-ai/px0, covering px0 completion, shell (required), bash, zsh and fish.
Command
Read and write config.toml at the store root. Every key is validated against a schema before it is saved, so a typo or a bad value is refused rather than written.
Command
The daemon fires scheduled workflows and does the nightly housekeeping: a hand-edit checkpoint scan, a brain reindex, draining queued playlist ingests, log retention, and a weekly update check.
Command
Check that everything is wired up, and for anything that is not, print the exact command that fixes it. A red line you cannot act on is the whole complaint doctor exists to answer.
Command
Guidelines are Markdown files describing how you work — how you word a commit message, what your Go reviews check. Workflows inline them verbatim, so output comes back in your voice instead of the model's default.
Command
What your scheduled workflows produced, in a place you will actually look.
Command
Every command follows the same shape: a group naming the entity, then a verb acting on it.
Command
Scaffold a store: create the folder layout, write config.toml, install the starter workflows and guidelines, and take the first version snapshot.
Command
Expose the brain and the workflow list over the Model Context Protocol, so a coding agent can use them without being told how the CLI works.
Command
What px0 knows about you, as opposed to what you have read.
Command
Every execution — a workflow run, or a brain ask — is recorded: what triggered it, which tools it called, what it produced, and whether it succeeded. Records outlive their logs, so history stays inspectable after the logs age out.
Command
Whether anything needs attention, in one screen.
Command
The store as a whole: everything px0 knows, in one directory.
Command
Tools are the external app actions a workflow may call — send a Slack message, open a Linear issue, read a Google Sheet. Every toolkit currently routes through Composio, which brokers the authorization.
Command
Stop the daemon, remove its scheduler unit, delete the entire store, and uninstall the px0 package itself. This is the one command that removes px0 completely rather than changing what it does.
Command
Upgrade px0 in place, apply any pending store-schema migrations, and roll back if an upgrade goes wrong.
Command
What is installed, and whether it can run.
Command
A workflow is a Markdown file with YAML frontmatter describing a job px0 can run: its trigger, the tools it may call, the guidelines it inlines, and where its output goes. px0 interviews you for one and builds it.