Getting the most out of Opus 5.5 in Claude and Claude Code

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...

Opus 5.5 works well with the way you already use Claude. A few things behave differently, though: it works for longer on its own, it tells you plainly what it did, and it thinks before every reply. This guide covers how to work with Opus 5.5 in Claude apps and Claude Code, including how to prompt the model, steer a long run, and check your results.

Three things to try in your first session with Opus 5.5: Hand over the whole task by defining what “done” looks like and when to stop and ask. Delete “think carefully” lines since Opus 5.5 already thinks before every reply. When a long run ends, read what it needs from you first.

How to ask: Say what “done” looks like, then let it run. Give the whole task in one message and name the finish line, like “the tests pass” or “every endpoint is migrated.” Opus 5.5 keeps going on long, multi-part work better than Opus 5 did. In Claude Code, for example: “Migrate the payment endpoints from the old client to the new one. Done means: every endpoint uses the new client, the old client is deleted, and the test suite passes. Stop and ask me only if a test fails for a reason you can’t explain.”

Stop telling it to “think hard”: Remove “think carefully,” “think step by step,” and similar lines from your prompts and saved instructions. Opus 5.5 always thinks before it replies, and it decides how much. In our testing in a chat product, removing a “think carefully” line made replies start sooner, with no clear drop in quality. For a quick answer to a simple question, say so: “Answer directly.” To change how much it thinks in Claude Code, change effort.

Add to a running task: If you remember something mid-run, you can type a follow-up while it works. Runs are longer now, so a restart costs more. In Claude Code, type the message and press Enter while Claude works, for example, “Also keep the old endpoint names as aliases.” For design work, name the styles you don’t want: When you ask for a page, an app, or an artifact, list the design habits you want left out. With no design direction, Opus 5.5 falls back on a few default styles. A general instruction like “avoid a generic look” mostly swaps one default for another. A list of specific patterns works much better. Name the patterns: “Build a personal website with placeholder content. Don’t use a cream or off-white background, italic accent words in headings, numbered “01 / 02 / 03” section labels, monospace labels, or pill-shaped buttons.” Then look at what it chose instead. If you don’t like that either, add it to the list and ask again.

Steering a long run in Claude Code: Tell it which stops you want. Put a short rule in your CLAUDE.md file about when to stop and ask, and when to keep going. Opus 5.5 keeps you posted as it works. On a long task, it sometimes stops to report instead of going on: a summary that names the next step without taking it, an offer to continue, or a list of choices that don’t block the work. It follows instructions that name these stops. Name the stops you want, too. Add this to CLAUDE.md, and edit it to fit your project: “When a step doesn’t need my input, keep going. Put status notes in the same message as your next action. Stop and ask only when you can’t continue without me, or before anything destructive: deleting data, force-pushing, or changing anyt...