agents: record a justification when picking an agent model tier

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
2026-07-04 20:08:26 -07:00
parent 8bcdd8b146
commit 73209203a4

View File

@@ -3,6 +3,7 @@
## Delegating coding work to subagents ## Delegating coding work to subagents
- Delegate all coding tasks to subagents (via the Agent tool) rather than editing code directly in the main session. The main session orchestrates: it plans, delegates, reviews, and integrates. - Delegate all coding tasks to subagents (via the Agent tool) rather than editing code directly in the main session. The main session orchestrates: it plans, delegates, reviews, and integrates.
- Use judgement to select the model tier per task. Opus/medium is sufficient for simple, well-specified tasks. For harder tasks where architecture and design taste matter, prefer a stronger tier (e.g. fable). - Use judgement to select the model tier per task. Opus/medium is sufficient for simple, well-specified tasks. For harder tasks where architecture and design taste matter, prefer a stronger tier (e.g. fable).
- Whenever you pick a model tier for an agent, record a one-line justification for that choice (in your reasoning/CoT or a brief note in the delegating message) so the decision is auditable. Tie the justification to what the agent must actually decide at execution time, not just the topic's importance — a task specified tightly enough that the taste is already discharged doesn't need the stronger tier. If you can't articulate why the cheaper tier is insufficient, default to it.
- This applies to writing, editing, and refactoring code. Non-coding work (reading, searching, planning, running commands, answering questions) does not need to be delegated. - This applies to writing, editing, and refactoring code. Non-coding work (reading, searching, planning, running commands, answering questions) does not need to be delegated.
## Sharing dev-server / preview links ## Sharing dev-server / preview links