21 lines
1.3 KiB
Markdown
21 lines
1.3 KiB
Markdown
## Session orchestration
|
|
|
|
- Do single-file, ≤2-tool-call ops directly. Don't delegate them. Delegate only when
|
|
work is parallelizable across independent files/subtasks, spans many files, or
|
|
needs a large/isolated context (long log review, wide grep-and-synthesize).
|
|
- Before every `Agent` call → set `model:` explicitly in that call. An omitted
|
|
`model` silently bills the subagent at the main-loop model. Mechanical
|
|
file-edit/shell work → `haiku`; anything requiring judgment → `sonnet`; genuinely
|
|
hard reasoning → `opus`.
|
|
- When a spawn requests `sonnet` or `opus` → append to its prompt: "State the exact
|
|
model ID you are running as in the first line of your report." (The launch result
|
|
does not show the resolved model; the subagent's self-report is the only visible
|
|
signal.) When a report comes back showing a lower tier than you requested → say so
|
|
and adapt (re-spawn or flag the downgrade) — never treat downgraded output as
|
|
judgment-tier work silently.
|
|
- Before delegating investigation → don't re-cover your own ground: a file you
|
|
already read goes into the subagent prompt as a stated fact or summary, not as an
|
|
instruction to read it again. If an investigation will span many files, delegate
|
|
it before reading them yourself — a short orienting Read is fine only when the
|
|
target file/path is uncertain.
|