Auggie CLI runs in the terminal. To use it for a signed-in browser task, verify three separate layers: the active agent can read Tabbit instructions, its process can run the local Tabbit CLI, and Tabbit can open the page in the intended profile. Augment’s public CLI docs describe interactive and print modes, but do not establish automatic /tabbit discovery.
Separate instructions from command access
Auggie’s documented entry point is auggie; automated workflows can use auggie --print. Public docs describe tool execution, but do not document Tabbit-specific skill discovery. Treat /tabbit as unverified in this client. Inspect the active session’s instructions. If they are missing, check whether the selected mode allows a local shell command. Model availability belongs to the Augment account and configuration; check it in Auggie before recommending a provider. See the Auggie CLI overview and CLI reference.
| Layer | What it supplies | What to check |
|---|---|---|
| Auggie instructions | The request and tool guidance | The active agent can read the installed Tabbit instructions |
| Local execution | Access to the Tabbit CLI launcher | The selected mode allows the named read-only command |
| Tabbit profile | The website session | The expected account can open the document |
Use a customer-doc review as the first useful case
Ask Auggie to read a customer document and create a named local draft with the page title, visible update date, and one sentence that needs review. Include the source URL. Stop before editing the source. This is a suggested workflow, not a verified Auggie-to-Tabbit integration test. Compare the draft in your regular Tabbit tab and hand it to the document owner.
Decision
Use Tabbit Browser and Tabbit CLI when the agent runs locally and has permission to use the launcher. If any layer is missing, keep Auggie on code work and let a person perform the browser step.
A small first check
Install Tabbit Browser, follow the Tabbit CLI quick start, sign into the target site yourself, and ask for a read-only task in a new Tabbit task tab. Keep working in your regular browser tabs while it runs.
Use the Tabbit instructions available to this agent. If unavailable, stop.
Open [exact authorized URL] in a separate task tab. Return the page title
and [one visible field]. Do not edit, submit, send, delete, or publish.| Check | Passing evidence | If it fails |
|---|---|---|
| Skill | The selected agent can read the installed Tabbit instructions | Check its skill discovery mechanism; do not assume /tabbit support |
| CLI | Local version or bounded diagnose command completes | Check shell access and local permissions |
| Site | Page title and visible field match a human check | Sign in manually in the intended Tabbit profile |
For related guidance, see Tabbit CLI guide, connect an agent to an existing browser, first browser-agent task checklist, browser MCP versus CLI, Codex setup example, agentic browser overview, web search versus browser control, and browser-agent security.
FAQ
Does the client automatically discover /tabbit?
Do not assume it does. Check whether the selected agent can discover the installed Tabbit instructions.
Does a successful CLI diagnosis mean the site is signed in?
No. It checks the launcher connection. Verify the exact page in the intended browser profile.
Can a remote agent use my local Tabbit session?
Only through a supported local handoff. A remote process cannot directly read your local browser profile.
What is a safe first task?
Read one authorized page and return a title plus a visible field. Stop before any write action.
Should the agent publish its draft?
No. Keep a named draft and review it against the source page before any change.