An agent is only as good as what it can see. Mains lets you attach precise context to a run — files, diffs, terminal output, a highlighted element, a linked ticket, a Sentry error — so the agent starts with exactly the material it needs instead of hunting for it.
Everything you attach appears as a chip in the workspace input and travels with your next message.
Adding Context
The fastest way is the context picker in the workspace input. It groups everything you can pull in:
| Section | What it attaches |
|---|
| Files | Any file from the workspace, by fuzzy path search |
| Issues | Tickets linked to the project, from your connected trackers |
| Skills | A skill to run |
| Plugins | A plugin capability |
| Commands | A provider slash command |
| Source | How |
|---|
| Diff | Send the workspace’s current change set — see the Diff Viewer |
| Browser selection | Highlight an element in the Browser Panel — screenshot + selector |
| Terminal output | Capture output from the built-in Terminal |
| Signals | A Sentry error with its stack trace |
Context Kinds
Under the hood each attachment is recorded against the run with a kind, so the agent receives structured material rather than a blob of text:
| Kind | Holds |
|---|
file | A file path and its contents |
selection | A selected region of code or a captured element |
diff | A change set |
git | A commit or branch reference |
terminal | Captured command output |
note | Freeform text you typed |
The Context Window Meter
Every attachment — and every turn of the conversation — spends tokens. The circular Context window indicator in the workspace shows how full the agent’s window is:
| State | Meaning |
|---|
| Green arc | Plenty of room |
| Amber | Nearing the auto-compact threshold |
| Red | The window is nearly full |
Attaching context is additive and reviewable — chips show exactly what the agent will receive, and you can remove any of them before sending. Nothing is sent until your next message.
