Claude /btw and Codex Steer: Small Moves That Keep Context Alive

Most AI workflow advice is too big. The real gains come from tiny steering moves that keep a session from drifting. /btw in Claude is the one I use most — especially in game design, where the gap between spec and playtest is enormous.

The most useful AI workflow tricks are usually not the flashy ones.

They are the little control surfaces. The subtle moves that keep a session from collapsing into drift, repetition, or polite nonsense.

That is how I think about steer in Codex and /btw in Claude.

Not as magic.

As small interventions that protect context.

The Real Problem Is Drift

You start with a live project, a strong idea, a repo full of history, and a decent sense of what you want.

Then an hour later the AI is still "helping," but the work has begun to slide sideways.

The code is technically fine but tonally off.

The copy is clean but generic.

The structure solves the wrong problem.

The assistant is no longer following the shape of your intent. It is following the shape of its own last few responses.

That is drift.

Most people try to solve it by dumping more instructions into the top of the conversation. Sometimes that works. Often it just makes the session heavier.

The better move is often smaller.

The Side-Channel That Changes How the Main Road Gets Read

I use Claude constantly. Test it, red-team it, build with it, write with it. Claude has been watching my work for a while now and has not called yet, but the relationship is functional.

I think of /btw as a side-channel for important nuance.

Not the main road. The aside that changes how the main road gets read.

The useful part is not the syntax. The useful part is the pattern: you inject a clarifying aside before the model hardens around the wrong assumption. Models overcommit once they think they understand the assignment. An honest "by the way" can save twenty minutes of cleanup.

Here is the range of what that actually looks like in practice.

Tone correction before it calcifies:

/btw this should read like it was written angry, not processed

The model will otherwise smooth everything into editorial calm. That one line protects the original voice.

Hidden constraint the files don't reveal:

/btw the client is non-technical — don't surface this logic in the interface
/btw we're not shipping this month — optimize for clarity, not performance

The code doesn't know the business situation. The /btw bridges that gap without restructuring the whole prompt.

Audience context mid-session:

/btw the reader has already seen the technical version — skip the basics
/btw this is for security professionals, not general readers — don't soften the red team section

Emotional truth behind the design decision:

/btw this feature exists because the founder hates the competitor's version, not because users asked for it

That context changes every suggestion the model makes about tone, positioning, and framing.

The guardrail is the point:

/btw the refusal behavior here is the interesting part — I'm not trying to bypass it, I'm documenting it

This one matters in red team work. Without it the model sometimes treats the research as the threat.

Where /btw Has Paid Off Most: Game Design

This is where I have relied on it most.

Game design is a domain where the gap between what looks correct in a document and what feels right in a playtest is enormous. You can spec a mechanic perfectly and have it collapse the first time a real person touches it. The model cannot know that from the code or the design doc. You have to tell it.

Building Neon Leviathan and Hack, Love, Betray, playtesting surfaced things that no amount of structured prompting would have caught — and /btw became the fastest way to inject that lived information back into the session without losing the accumulated context.

HACK LOVE BETRAY
COMING SOON

HACK LOVE BETRAY

Mobile-first arcade trench run through leverage, trace burn, and betrayal. The City moves first. You keep up or you get swallowed.

VIEW GAME FILE

The kinds of asides that changed the direction of a session:

/btw playtesting showed players quit at this room — it doesn't feel hard, it feels unfair

The distinction matters. Hard and unfair require different fixes. Without the /btw the model optimizes for difficulty reduction when the real problem is the communication of intent.

/btw the player character shouldn't feel heroic yet — they're still a nobody in this act

This one stopped the model from writing ability descriptions that sounded too powerful too early. Tone constraint that lives nowhere in the codebase.

/btw the tutorial ran long in testing — shorter is better even if players miss some mechanics
/btw this boss is supposed to feel like a wall — don't smooth the difficulty curve here
/btw the economy felt too generous in early game — players didn't value the resources

The pattern is always the same: the playtest revealed something emotional or experiential that the spec didn't capture. The /btw carries that knowledge forward without a full context reset.

Brainstorming sessions benefit from it differently — less about correction, more about constraint injection mid-flow:

/btw we already tried a stamina system and it slowed the pace too much

That one line stops the model from cycling back to a solution you already ruled out and can't put in the design doc because you haven't written one yet.

Grab the Wheel Before the Car Reaches the Guardrail

Same instinct, different environment.

When you are deep in a repo — assistant already knows the site structure, the tone, the branch state, the difference between what looked smart on paper and what actually feels right — you do not want to throw the session away. You want to nudge it.

Steer lets you correct course without breaking momentum. The equivalent of grabbing the wheel before the car reaches the guardrail.

The moves it enables:

  • less of that
  • more like this
  • keep the architecture, change the tone
  • stop optimizing for explanation and start optimizing for signal
  • preserve the vision, cut the drift

Where /btw is a conversational aside, steer is a directional correction to an ongoing code session. Related instinct. Different surface.

When You're Managing Function, Tone, and Long-Range Intent Simultaneously

If you are a pure engineer, you can often test your way back to truth.

If you are building products out of writing, design, systems, mood, and long-range intent, testing is not always enough. You also need the work to feel right.

A writer-builder is usually managing several things at once: the functional result, the emotional tone, the public read, the hidden business constraint, the long arc of the vision. That stack is exactly where drift becomes expensive and where small steering moves — not big prompt rewrites — are the correct intervention.

VS Code keeps you close to the actual artifact. Codex keeps reshaping direction without losing the larger thread. And when you move into Claude for drafting or conceptual work, /btw keeps the session from locking onto the wrong version of you.

The Habit That Actually Helps

The habit is simple:

When you notice drift, do not just react emotionally and start typing more words.

Name the correction precisely.

Use the smallest move that restores alignment.

That might be:

  • a steer in Codex
  • a quick /btw in Claude
  • a short note in the repo docs
  • a source-of-truth update before the next iteration starts

The point is to stop paying the same cleanup tax over and over.

This Is How Context Survives

People talk about context like it is a storage problem.

Sometimes it is.

But a lot of the time it is really a steering problem.

The assistant has plenty of context. It is just leaning on the wrong parts of it.

That is why these tiny moves matter.

They do not create genius.

They keep the work from wandering away from it.

Big prompts are overrated. Small corrections, used at the right moment, are often worth more. /btw keeps the model honest about what the course actually is. Steer keeps the project on it. Two surfaces, same instinct: protect the context before it drifts far enough to cost you.


GhostInThePrompt.com // The aside changes how the main road gets read. /btw is the move.