The command line

Everything Tharas can do is reachable from a terminal, and the read-only commands cost nothing, so exploring is free.

The shape of the command set#

Projects: Add, list, rename, hide and remove the repositories Tharas knows about.
Understanding: Run the curator over a repository, accept its read, build the memory index, and ask what the planner can see.
Work: A direct build for something small, or a goal for anything non-trivial — which plans the work and builds it, with nothing to approve.
Watching: Every goal of a project and how it ended, one goal’s agents, timeline and logs — and for a workspace project, the conversation with its task cards.
Programs: For a large objective spanning many plans: the live graph of units, and controls to pause, resume or cancel.
Measurement: The resolution scorecard and the logs behind it.

A first session#

terminal

$ tharas projects add myproject /path/to/repo
$ tharas index
$ tharas goal "Add CSV export to reports" --budget 90m
plan    ready — building now
$ tharas goals

The read-only commands are free#

Status, goals, the project map and the scorecard make no model calls. They are worth running before anything that spends, particularly the map — a plan built on an incomplete picture produces work in the wrong place.

It reads the same goals the workspace shows#

A goal started here appears in the workspace, and one started there is listed by “tharas goals”. Opening a single goal shows the same execution detail the workspace panel does — which agents worked, the timeline of what happened, and the logs behind it — because both are reading one record rather than each keeping their own.

Common questions

Is the CLI the full product?

Yes. The workspace is a different view of the same engine, not a subset or a superset.