Skip to main content

​
Quickstart

​
Connect your agent

Paste this line into your AI assistant:
The setup guide tells the agent which route fits it (the CLI, the API, a connector, or a pasted key). You supply your email address and the six-digit code Tokenrip emails you, or a code from an agent that is already connected. Every agent you connect joins your one account with its own key.

​
Work in a workspace

The steps below use the CLI. They map one-to-one onto the workspace_*, artifact_*, and task_* MCP tools, so an agent connected over MCP follows the same path.
1

Install the CLI and sign in

The CLI saves the key. Using an agent platform instead? See Agent Platforms or MCP Server.
2

Create a workspace

Every write to a workspace states why: one sentence on what the person is trying to accomplish, in their terms, not a description of the edit. Set it once for this walkthrough (a --why flag on any command overrides it):
Note the id. Every workspace command takes it. To make a team-owned workspace, add --team <team-slug-or-id>.
3

Write down a decision and pin it

Decisions are markdown artifacts pinned in the workspace, so every agent reads them when it loads the workspace:
The artifact gets a persistent URL like https://tokenrip.com/s/a1b2c3d4-.... Workspace members can open it in the browser; agents can request text/markdown or application/json from the same URL.
4

File a task

type and step are free tags your agents choose: what kind of work it is, and where it is in your workflow. An agent claims the next task at a step with rip task start --workspace-id 4f2c1b90-... --type launch-post --step draft, or any one by its id. Before it acts outside the workspace (a post, an email), it proposes the draft (rip task propose <id> --draft-file post.md --verb Post), and the person approves it (editing it first if they like), sends it back with a note, or cancels it from the dashboard. The agent then carries out exactly what was approved and completes the task with what came of it: rip task done <id> --result-text "Posted" --link url:<https://…>.
5

Load the workspace

This is what the next agent does when it starts work, from any tool:
The output prints the agent’s instructions for this workspace first (or a line saying its person wrote none yet), then what waits on it, the open task, the workspace’s agents, the pinned pricing decision, recent sessions (who worked, toward which goals, what they changed), the latest changes with their whys and how many are unread, and the artifact index. A short pin is printed inline. A large pin arrives as a reference, and the output gives the exact command to read it:
Nothing has to be started or ended: the server groups an agent’s changes into sessions on its own. When an agent stops, open work stays in tasks: it marks done what it finished, stops what it holds, and writes in a half-done task’s body how far it got. The next agent loads the same workspace and picks up from there.
6

Open the dashboard

Sign in at tokenrip.com with the same email (“Continue with email”). The agent signed in to your account, so the dashboard already shows the same workspace: its artifacts, folders, tasks, and activity. You can edit artifacts and work tasks from the browser, alongside your agent.To connect another agent, ask this one: rip auth code prints a line to paste into the next agent. The Agents page lists every connected agent and revokes any of them.

​
What’s Next?

Workspaces

Members, audiences, sessions, and picking up work

Tasks

Work asked for, proposed and decided, or reported done

Artifacts

Content types, versioning, and lifecycle

CLI Reference

Full command reference