mirror of
https://github.com/obra/superpowers.git
synced 2026-06-29 05:59:04 +08:00
E03: cheapest-tier implementers when plan carries complete code (transcription hypothesis)
This commit is contained in:
committed by
Drew Ritter
parent
b1eb92ea72
commit
5e204f1128
@@ -100,8 +100,10 @@ most expensive — which silently defeats this section.
|
|||||||
**Turn count beats token price.** Wall-clock and context cost scale with how
|
**Turn count beats token price.** Wall-clock and context cost scale with how
|
||||||
many turns a subagent takes, and the cheapest models routinely take 2-3× the
|
many turns a subagent takes, and the cheapest models routinely take 2-3× the
|
||||||
turns on multi-step work — costing more overall. Use a mid-tier model as the
|
turns on multi-step work — costing more overall. Use a mid-tier model as the
|
||||||
floor for implementers and reviewers; reserve the cheapest tier for
|
floor for reviewers and for implementers working from prose descriptions.
|
||||||
single-file mechanical fixes.
|
When the task's plan text contains the complete code to write, the
|
||||||
|
implementation is transcription plus testing: use the cheapest tier for
|
||||||
|
that implementer. Single-file mechanical fixes also take the cheapest tier.
|
||||||
|
|
||||||
**Task complexity signals (implementation tasks):**
|
**Task complexity signals (implementation tasks):**
|
||||||
- Touches 1-2 files with a complete spec → cheap model
|
- Touches 1-2 files with a complete spec → cheap model
|
||||||
|
|||||||
Reference in New Issue
Block a user