Renn F 92543ad593 chore(prompts): stop generating verb tables for driver-based roles ...

regenerate_verb_tables.py looped every role in ROLE_CONFIGS, emitting a
_generated/<role>.md for prompter and secretary too. Both intentionally keep
only note+evidence in role_config — their real tools live in their agent_sdk
drivers (intake: propose_draft; secretary: read_state/read_task/
submit_directive, the last gated through the backend /directives), and neither
uses the _generated/<role>.md prompt-composition path. So the generated tables
understated those roles and showed up as perpetually-untracked noise.

Skip the driver-based roles (_DRIVER_BASED_ROLES) in both the aggregate verbs.md
and the per-role file output, with a comment pointing at the real surfaces.
Regenerated verbs.md drops the two misleading sections.

2026-06-16 04:50:44 +02:00

..

_generated

chore(prompts): stop generating verb tables for driver-based roles

2026-06-16 04:50:44 +02:00

identities

Gateway/full (#9)

2026-05-02 03:11:49 +02:00

roles

feat(dispatch): per-dev sequenced queues for code subtasks (guardrails spec 3)

2026-06-16 04:10:05 +02:00

teams

docs: correct doc-vs-code drift across the canonical docs

2026-06-05 17:05:33 +02:00

base.md

feat: company-in-a-box — goal-aware company layer (0.4.0) (#171)

2026-06-15 20:47:41 +02:00