attention-span

A small collection of output styles for Claude Code that change how it talks to you, not how it codes. Answer-first, plain English, easy to skim. Each one is a single markdown file you drop in and switch on.

The concise-by-default rules aren't just kind to your attention, they trim Claude's output, so you literally spend fewer tokens. The pun pays for itself.

Three so far: Attention-kind (the flagship), Spartan (terse, zero warmth), and Rundown (TL;DR briefings). Each has its own section below.

Attention-kind

An ADHD-friendly style. Claude answers first, keeps it short, drops the jargon, and expands only on what's actually worth your attention. Every point is spaced out and marked with a →, and the important words are bold, so you can skim just the bold and still get the whole answer.

Same engineering ability underneath. Only the delivery changes.

Who it's for: anyone whose attention is a limited resource. ADHD, tired, deep in flow, or just done with walls of text.

Before / after

The question: "Which database should I use for a new social app, PostgreSQL or MongoDB?" Same answer, before and after the style.

For a new social app, start with PostgreSQL, and the bar for choosing MongoDB instead is high. Social apps are relationship-heavy by nature: users follow users, posts belong to users, comments belong to posts, likes connect users to posts. That's a web of connections, exactly what a relational database is built for. In MongoDB you either cram related data into one record and fight size limits, or split it out and end up stitching it back together in your app code anyway. The feed problem makes this worse: timelines, "posts from people you follow," and mutual-friend lookups all lean on the kind of cross-referencing Postgres does in a single query. You also get consistency for free, since follow counts and "did I already like this" checks want real transactions… [and it keeps going like this]

→ Use PostgreSQL. A social app is all relationships (friends, follows, likes), and Postgres handles those natively. Right for ~90% of new social apps.

→ You keep flexibility. Its JSONB column stores schema-less data inside the same database, so you get MongoDB's looseness without leaving Postgres.

→ Pick MongoDB only if your data is self-contained documents with no links, and you need massive write volume on day one.

→ The early trap with MongoDB: six months in, five different shapes of "user" and no clean fix. Postgres forces the structure.

→ Next: start on managed Postgres (Supabase, Neon, RDS).

Same information. One of them you can read at a glance.

Does it actually help? (measured)

12 questions across 8 categories (dev, research, analysis, explaining, writing, quick lookups), each answered 4 times, two runs averaged, scored by a separate judge. Full results.

• 47% fewer output tokens.
• Answer-first: 63% → 96%. The default buried the answer under preamble a third of the time.
• Skimmability: 2.7 → 4.8, on a scale anchored to an ADHD reader (dense prose caps at 2, no matter how well organized).
• Unexplained jargon: 2.0 → 0.9 terms per answer.
• Correctness held at 100% across all 48 answers. Shorter cost nothing.

It holds beyond code: research (-53%), analysis (-55%), and explaining (-50%) cut as hard as debugging. The one place it barely moves is already-short output, a two-line email only shrank 4%, because the style trims rambling and leaves tight answers alone. The gains scale with how much Claude would have over-explained. Earlier dev-only run, Opus 4.8 vs 5.

Does it cost work quality? (real usage, not eval questions)

The runs above measure synthetic questions. This one measures real work. In a blind, observational review of 44 real historical sessions across 4 task types, split at the first config-level output-style adoption, turning output styles on showed no statistically significant drop in task quality and no sign of degradation; on difficulty-matched code work the two were indistinguishable. It shows no quality cost in day-to-day use. Full results, method, and limitations.

What changes

• Answer first. Conclusion in line one. No wind-up.
• Short by default. Says the least that fully answers, then stops.
• Expands only on what's vital, so length itself signals importance.
• Plain English. Rare technical terms get a five-word definition, once.
• Built to scan. → markers, heavy bold, real spacing between points.
• No repetition. Each point makes one distinct argument, never restated or re-argued.
• Re-anchors long tasks and asks one question at a time, so you never lose the thread.
• Comments too. Code comments inherit the plain-English "explain the why" rule, but never the chat formatting.

Spartan

Terse mode with the warmth stripped out. Same arrows and bold as Attention-kind, but blunt and imperative, no cushioning, no transitions, maximum compression. For heads-down work when you want signal, not conversation.

The question: "Three priorities this week, room for two, how do I decide what to cut?" Both real Opus 5 eval outputs.

Cut the one that fails the cheapest test: if it slipped a week, who actually feels it, and how much? Run all three through four quick filters and the loser usually falls out on its own. Consequence of delay: two of your three probably have soft deadlines you invented and one has a real one, a person waiting, a dependency downstream, a window that closes. Cut from the self-imposed pile, never the someone-is-blocked-on-me pile. Reversibility: some things get harder the longer they wait, others are exactly as easy next week, so cut the one whose cost curve is flat. Who owns it besides you: if a priority can be delegated or done at 80% by someone else, it is a better cut than one only you can do… [and it keeps going like this]

→ Rank by cost of NOT doing it, not by effort or interest. Ask each: what breaks if this slips a week? The one with the softest consequence gets cut.

→ Kill the reversible one. If a task can wait, be delegated, or restarted later with no penalty, cut it. Protect anything with a hard deadline or a dependency where others are blocked on you.

→ Run the regret test. Friday night, which un-done task stings most? Keep that one. The one you'd shrug at is your cut.

→ Separate loud from important. The priority screaming at you is often just the most anxious, not the most valuable. Cut by impact, not by volume.

→ Do not half-do all three. Two finished beats three at 66%. Partial work on the third is the trap, it feels productive and ships nothing.

→ Cut it out loud. Tell whoever's affected now, not Friday. A cut you flag is a decision, a cut you hide is a failure with a delay.

Opus 5 eval (4 questions): ~50% fewer tokens than default, skimmability to 5.0, correctness held. Full results.

Rundown

Briefing style. Opens with a TL;DR, shows state as a ✅ / 🟡 / ⬜ checklist, tags the next choices with emoji. Built for status updates and standups. It optimizes for readability and scannability, not brevity, so reach for it when clarity matters more than length. Includes a guard against inventing status it wasn't given.

The question: "Summarize where hiring stands: 20 applicants, 5 screened, 2 interviews, no offer, one strong candidate slipping." Both real Opus 5 eval outputs.

Hiring stands at the top of the funnel and thin at the bottom. Twenty applicants in, five screened, two interviews booked. No offer has gone out yet, and that gap is the problem: one of the strongest candidates is cooling off while the process idles. The num