// AI TOOLS · CLAUDE OPUS 5.5 PROMPTING GUIDE

Claude Opus 5.5 Prompting Guide

Anthropic's official prompting guidance for Claude Opus 5.5, published with the model's September 22, 2026 launch — how to calibrate effort now that the default dropped to medium, why thinking is always on, and which chat-prompt lines to delete. Guidance for a text model, not a content generator.

Last verified · 2026-09-28 · by Moe Ameen

What Claude Opus 5.5 Prompting Guide is

The Claude Opus 5.5 prompting guide is Anthropic's official documentation on how to prompt its September 2026 flagship model, published as part of the launch and covered widely the week after. Its framing is unusual: instead of promising better output from the same prompts, it warns that settings carried over from Claude Opus 5 can now run longer and cost more, and it walks through the behavioral changes that make old habits misfire. Anthropic is explicit that existing Opus 5 prompts should still work — the guide is about tuning, not rescue.

The headline changes are about thinking and effort. Opus 5.5's default effort level is medium (Opus 5 defaulted to high), and thinking is now always on — the model rejects requests that try to disable it. Because it tends to think more per turn at any given level, Anthropic advises setting effort explicitly, starting at medium, and testing several levels against your own evaluations rather than assuming the level names carry the same meaning across models; it also says to budget max_tokens generously (up to the model's 128,000 maximum on long agentic turns) because thinking counts toward that limit. For chat apps, it recommends deleting "think carefully" style instructions, since the model self-regulates thinking and removing the line made replies start sooner with no clear quality drop.

The rest is production-grade advice: keeping unattended agents running past a text-only end of turn, reading progress updates that now arrive as thinking blocks, giving multi-agent harnesses an elapsed-time budget, wrapping user-pasted text in tagged blocks to resist prompt injection, using tools for dense charts and diagrams, and naming specific frontend styles to avoid rather than asking it to "avoid a generic AI look." It's engineering guidance written for people building on the API — verify any figure against Anthropic's docs, since the advice is versioned to the model and can change.

What you can make with it

  • A correctly calibrated Opus 5.5 integration — effort set explicitly and re-tested, with token budgets sized so thinking doesn't truncate replies
  • Faster chat replies, by removing "think carefully" instructions that the always-on thinking now makes redundant
  • Unattended and multi-agent workflows that keep running instead of stopping at a text-only progress report
  • Prompt-injection-resistant handling of content a user pasted, using the guide's tagged-block pattern
  • More precise reads of dense charts, diagrams, and screenshots, with the recommended image tools at higher effort
  • Frontend output that avoids the model's default "AI look," by naming the specific patterns you don't want

How Kompozy turns Claude Opus 5.5 Prompting Guide output into content

Most of this guide is plumbing a creator will never touch — but two of its techniques transfer directly to the one prompting a creator does do: writing the brief that drives their content. First, the guide's best frontend tip is that "avoid a generic AI look" does nothing, while naming the specific patterns to avoid works. That's exactly how you write a good [Persona Brief](/glossary/persona-brief) in [Kompozy](/): don't say "sound human," list the specific words, openings, and clichés to ban. Second, the guide tells agents to explore a source broadly before acting instead of jumping on the obvious. Applied to content, that means feeding Kompozy a rich, complete source — the full transcript, the whole report — rather than a thin summary, so the copy it generates has real material to draw from. Take those two habits, write one genuinely sharp brief and source, and you've done the only prompting that matters for content.

Then Kompozy does what no prompt can: it turns that brief into finished, published posts. Its Text Posts, Blog Articles, and Newsletters run on this class of Claude and OpenAI model — with the effort and thinking calibration the guide describes handled internally, so you never open a docs page to tune it — and it generates the formats a text model can't: talking-head [Persona Shorts](/glossary/persona-shorts) and HeyGen avatar video, brand-exact Carousels and Quote Graphics rendered through [HyperFrames](/glossary/hyperframes), Photo Posts, and Infographics, all held to one voice. [Autopilot](/glossary/autopilot) and a per-post review pipeline then caption, reframe to 9:16, 1:1, and 16:9, schedule, and publish across the eight social platforms plus a blog and a Mailchimp newsletter. The guide teaches you to get one great answer out of the model; Kompozy turns one great brief into a week of content, everywhere.

  1. Borrow the guide's frontend lesson: instead of "sound human," write a Persona Brief that names the exact words, hooks, and clichés to ban, plus the voice you want.
  2. Borrow its "explore broadly" lesson: give Kompozy a rich, complete source — a full transcript, interview, or report — not a thin summary, so the generated copy has real material.
  3. Let Kompozy generate the whole set from that one brief and source: persona/avatar video, Carousels, Quote Graphics, Photo Posts, Infographics, plus native text, a blog draft, and a newsletter.
  4. Skip the model tuning entirely — Kompozy manages effort and thinking internally, so there's no effort level or max_tokens to calibrate for content.
  5. Schedule and publish the batch across eight social platforms plus blog and email from one queue with Autopilot and a per-post review pass.

Frequently asked questions

What does the Claude Opus 5.5 prompting guide change for everyday users?

For chat users, the main practical change is to delete "think carefully" style instructions from saved prompts and custom instructions. Opus 5.5 sets its own thinking on every reply, so those lines can slow the first reply without improving quality. The deeper advice — effort calibration, token budgets, agent stop conditions — is aimed at developers building on the API, not chat users.

What is the default effort level on Claude Opus 5.5?

Medium. That's one step below Claude Opus 5's high default. Anthropic recommends setting effort explicitly and re-testing several levels on your own evaluations, because the level names don't map to the same amount of thinking across models — at medium, Opus 5.5 matched or beat Opus 5 at high on coding and knowledge-work tasks in its testing.

Can this guide help me make better content?

Two of its techniques transfer to content: name the specific patterns to avoid rather than saying "sound human," and give the model a rich source instead of a thin one. Both apply directly to writing a Kompozy Persona Brief and choosing a source. The rest is engineering plumbing, and none of it makes the model output video, images, or scheduled posts.

Do I need to follow the guide if I use Kompozy?

Not for content. Kompozy generates its copy with this class of Claude and OpenAI model and manages the effort and thinking settings the guide describes internally, so you don't calibrate anything. You'd only need the guide if you were separately building your own app or agent on the raw Claude API.

Related tools

  • Claude Opus 5.5 — Anthropic's September 2026 frontier Claude model — about 20% cheaper per token than Opus 5, more than 30% faster, with a #1 debut on the Artificial Analysis Intelligence Index and a new class of safeguards. A text-output model, not an image, audio, or video generator.
  • Claude Opus 5 — Anthropic's frontier Claude model — deep reasoning, agentic coding, vision, and a 1M-token context, positioned near Fable 5 intelligence at half the cost. A text-output model, not an image, audio, or video generator.
  • Claude Sonnet 5.5 — Anthropic's faster, more efficient mid-tier Claude — over 30% quicker output and up to 30% lower cost per task at Sonnet 5's pricing.
  • Claude Fable 5.1 — Anthropic's September 2026 Claude update — cheaper to run, sharper at coding, and strong at creative long-form writing.

← All AI tools · Get started →