Side-post in the keppt build-in-public series — an interlude before the Phase 1 implementation write-up lands.

While building Phase 1 of keppt , I ran a side experiment. Same architecture spec, two builds. One I curated over a day with Claude Code and Codex — plan first, tasks derived, agent-implemented per task, adversarial review, iterate. One I handed off to Factory.ai's Droid in their new Mission Control mode. Spec in, walk away, come back when the budget runs out.

Here is what came back.

the numbers

Curated (Claude Code + Codex) Autonomous (Droid Mission Control)

Wall-clock effort ~1 day ~4 hours autonomous

Source LOC 1,367 2,370

Test LOC 1,317 6,015

Test cases 69 339

Working CLI? yes no

LocalFileRepository.edit() real, CAS + audit stub, ignores edits

LocalFileRepository.search() real full-text + scope stub, returns []

Path-safety vectors 8 13

The autonomous build wrote 4.6× more test LOC than the curated build, with roughly five times as many test cases.…