The reflexes worth wearing in

A reflex is a primitive you’ve stopped narrating to yourself. Here are the ones that pay off most on a tool that lives in both a GUI editor and a terminal.

Choose a posture: Plan, then build

The single highest-leverage reflex is the posture switch. You met it in the modes chapter: use the mode picker, or the shortcut configured for your installation, to move from Ask to a Plan-like custom posture and then Agent. Cursor’s UI and shortcuts change, so verify the current control instead of memorising one chord.

The reflex isn’t the keystroke - it’s reaching for the posture before you type, not after a run has already gone somewhere you didn’t want. The tell is the shape of the change in front of you. A contained fix in a file you own goes straight to Agent. A change that reaches past the file in front of you - a shared module, a schema, anything a half-dozen things depend on - gets a Plan-like posture first, without you deciding to. The person who’s merely installed Cursor leaves it in Agent and hopes. The person who’s good with it feels which posture the task is asking for before the first word.

The split-model trick from the modes chapter is part of this reflex too: Cursor 2.0 lets you create the plan with one model and build it with another, so when a task is worth planning, plan it with a frontier reasoning model and hand the written-down plan to a faster one to build. The plan is an editable markdown artifact, so the builder needs the plan, not the planner’s reasoning context.

Tab vs Agent vs @-pin: three tools for three moments

You met all three early. The reflex is using the cheapest one that fits, without thinking about which.

Tab is for the keystrokes you were already going to make. Inline completion that predicts your next edit and is accepted with the Tab key. When you already know exactly what you’re typing and just want it faster, you don’t open a chat - you let Tab finish the line.
Agent chat is for the work you’d rather describe than type. When the outcome is clear but the keystrokes aren’t, you hand it a brief and review the diff.
@-pinning is the exception, not the default. Since Cursor 2.0 the agent self-gathers context without needing you to manually attach it - it greps and reads to find what it needs, so you rarely have to point, with @-mentions still there as a manual override. The reflex is to let it self-gather first, and reach for an @-tag only when you can see it guessed wrong: it’s reading the wrong file, missing the one that matters, or working a large repo where retrieval lands somewhere unhelpful. Pin to correct a miss, not as a ritual before every prompt.

Model posture as a habit

The reflex from the models chapter is to default to Auto and reach for a stronger model only where the reasoning pays. Auto lets Cursor select models that balance intelligence, cost efficiency, and reliability. What it costs depends on your plan, model, routing mode, and current usage policy, so check the live picker and usage dashboard rather than treating Auto as a universal discount. For the bulk of budgetcli work - a CRUD endpoint, a docstring, a fixture, a rename - Auto is still the right first choice.

You break that default deliberately, not by accident. The categorisation rules engine - the one piece of budgetcli where a wrong design call is expensive to undo - is where you might hand-pick a stronger reasoning model or enable MAX Mode if the current model supports it. MAX expands context and can change billing, so read the current pricing and model details before using it. The habit is: Auto for everyday, a stronger model where reasoning genuinely pays, and back to Auto when the hard part is done.

Cost awareness

Billing is plan- and release-dependent. Treat the live Cursor pricing page and your usage dashboard as authoritative; don’t assume that Auto, Composer, pinned models, or MAX always map to one universal pool. Make expensive or long-context choices deliberately, and verify the cost before using them repeatedly.

Those four reflexes settle your posture, your engine, and your spend. What they don’t settle is where a given task should run - and Cursor gives you four places to put it. Next: choosing the surface.