prompting-claude-opus-5 changedbuild-with-claude/prompt-engineering/prompting-claude-opus-5
Nearest release: v2.1.281, published an hour before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+2added
Lines−6removed
From line
4
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits7to this page, all time
The whole hunk
from line 4, old and new numbered
/
from line 4
44description: Behavioral differences and prompting patterns for Claude Opus 5, covering response verbosity, agentic narration, task scoping, subagent delegation, self-correction, and output artifacts when thinking is disabled.
55---
66
7This guide covers the prompting patterns specific to Claude Opus 5. For the model's capabilities and API changes, see [What's new in Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/whats-new-opus-5). For techniques that apply across all current Claude models, see [Prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices).
7This guide covers the prompting patterns specific to Claude Opus 5. For the model's specifications, see [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5/overview). For techniques that apply across all current Claude models, see [Prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices).
88
99Claude Opus 5 is built for complex agentic coding and enterprise work, with particular strengths in long-horizon agentic tasks. It performs well out of the box on existing Claude Opus 4.8 prompts. The following patterns cover the behaviors that most often require tuning.
1010
11<Note>
12 For API changes when migrating from Claude Opus 4.8 (thinking on by default, and disabling thinking capped at `high` effort), see the [migration guide](https://platform.claude.com/docs/en/models/opus-5/migration-guide#migrating-from-claude-opus-4-8-to-claude-opus-5).
13</Note>
14
1511## Capability improvements
1612
1713Compared with Claude Opus 4.8, the improvements most relevant to prompting are:
from line 88
9288
9389## Running with thinking disabled
9490
95Claude Opus 5 runs with [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) on by default, and thinking can be disabled only at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below; see the [migration guide](https://platform.claude.com/docs/en/models/opus-5/migration-guide#migrating-from-claude-opus-4-8-to-claude-opus-5). With thinking disabled, two artifacts can occasionally appear in the model's visible output. The primary mitigation for both is to keep thinking enabled and control token cost with lower effort levels instead of disabling thinking: for most tasks, thinking enabled at `low` effort performs better than thinking disabled at similar cost.
91Claude Opus 5 runs with [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) on by default, and thinking can be disabled only at [effort](https://platform.claude.com/docs/en/build-with-claude/effort) `high` or below. A request that combines `thinking: {"type": "disabled"}` with effort `xhigh` or `max` returns a 400 error. With thinking disabled, two artifacts can occasionally appear in the model's visible output. The primary mitigation for both is to keep thinking enabled and control token cost with lower effort levels instead of disabling thinking: for most tasks, thinking enabled at `low` effort performs better than thinking disabled at similar cost.
9692
9793**Tool calls as text.** With thinking disabled, the model occasionally writes a tool call into its user-facing text instead of emitting a structured `tool_use` block. The turn completes normally and the call never runs, and in agentic loops the leaked text stays in the conversation history, so later turns are affected as well. This is most common on tool-heavy workloads such as search.
9894
No line in this hunk matches that.