Finishing work changedbuild-with-claude/prompt-engineering/prompting-claude-fable-5-2
Nearest release: v2.1.321, 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+1added
Lines−1removed
From line
163
where the diff opens
First seen
9 Nov 2026
this site's first read of the page
Recorded edits3to this page, all time
The whole hunk
from line 163, old and new numbered
/
from line 163
163163
164164* **Standing instructions to delegate:** Lines that push work to subagents can sit in system prompts, skills, and agent files. Read those files before you migrate. If, in your tests, the model starts more subagents than your tasks need, remove the lines you no longer need. See [Set expectations for subagents](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#set-expectations-for-subagents).
165165* **A token budget that your harness writes into the prompt:** Some harnesses tell the model in the prompt how many tokens the task may use and how many are left. The size of that budget changes how much Claude Fable 5.2 spends. In Anthropic’s testing on coding tasks at `high` and `xhigh` effort, removing a large budget lowered cost, with equivalent performance. Test your tasks without the budget. This finding is about text in the prompt, not the API’s [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets), a beta feature that the testing didn’t cover.
166* **Harness code that edits earlier turns:** If your harness changes the system prompt, the tools, or an earlier message between requests, the thinking blocks that follow the changed point in the history become invalid. By default, the Messages API then rejects the request, and the Message Batches API drops those blocks. To have the Messages API drop them too, set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"` (beta, `thinking-binding-controls-2026-08-01` header). In Anthropic’s testing, when earlier thinking was dropped on every turn, the model thought again and used more output tokens. That is the worst case, and the increase depends on how often your harness edits earlier turns. Keep the history append-only, so that no thinking is dropped, and measure output tokens on your own tasks before you rely on `"drop_block"`. See [What the API does with an invalid block](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#mismatch-behavior) and [Make changes without editing the prefix](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#replace-prefix-edits).
166* **Harness code that edits earlier turns:** Claude Fable 5.2 uses [preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking). If your harness changes the system prompt, the tools, or an earlier message between requests, the thinking blocks that follow the changed point in the history become invalid. By default, the Messages API then rejects the request, and the Message Batches API drops those blocks. To shorten the history without this error, use [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing), or [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) that keeps no earlier turns after the summary. To have the Messages API drop the blocks too, set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"` (beta, `thinking-binding-controls-2026-08-01` header). In Anthropic’s testing, when earlier thinking was dropped on every turn, the model thought again and used more output tokens. That is the worst case, and the increase depends on how often your harness edits earlier turns. Apart from compaction and context editing, keep the history append-only. That keeps the cache hit rate high, and no thinking is dropped. Measure output tokens on your own tasks before you rely on `"drop_block"`. See [What the API does with an invalid block](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#mismatch-behavior) and [Make changes without editing the prefix](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#replace-prefix-edits).
167167* **The “treat that answer as done” lines:** [Prompting Claude Opus 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#thinking-instructions-in-chat-system-prompts) offers two sentences for chat system prompts. They tell the model to treat an earlier answer as done and to focus its thinking on the new message. In Anthropic’s testing at `high` effort, these sentences reduced Claude Fable 5.2’s thinking on follow-up questions, but the model also became far less likely to point out mistakes in its earlier answers. Leave these lines out where you want the model to keep re-examining its earlier answers. Elsewhere, test whether the model still points out its own mistakes before you adopt the lines.
168168* **Instructions to think less:** Claude Fable 5.1 usually follows a line such as “answer directly without deliberating.” In Anthropic’s testing, such a line didn’t stop Claude Fable 5.2 from thinking at `medium` and above. Remove these lines and lower the effort level, as described in [Calibrate effort](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#calibrate-effort).
169169* **Style rules for writing:** Claude Fable 5.2 follows style rules closely, so a hard limit such as “one instruction per sentence, in 20 words or fewer” can make its prose choppy. Remove the rules you no longer need before you add the text in [Make reports easy to follow](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-2#make-reports-easy-to-follow).
No line in this hunk matches that.