An agentic skills framework & software development methodology that works.
E03: cheapest-tier implementers when plan carries complete code (transcription hypothesis)
Jesse Vincentcfe48c28acb1
diff --git a/skills/subagent-driven-development/SKILL.md b/skills/subagent-driven-development/SKILL.mdindex eb4623ab7..3514a05e2 100644--- a/skills/subagent-driven-development/SKILL.md+++ b/skills/subagent-driven-development/SKILL.md@@ -100,8 +100,10 @@ most expensive — which silently defeats this section.**Turn count beats token price.** Wall-clock and context cost scale with howmany turns a subagent takes, and the cheapest models routinely take 2-3× theturns on multi-step work — costing more overall. Use a mid-tier model as the-floor for implementers and reviewers; reserve the cheapest tier for-single-file mechanical fixes.+floor for reviewers and for implementers working from prose descriptions.+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):**- Touches 1-2 files with a complete spec → cheap model