claudomator.git/docs/superpowers/specs, branch main

docs: add design spec for recursive arbitrated review (supersedes root-only fix loop)

2026-07-09T02:49:39+00:00

Replaces the story.RootTaskID re-pointing mechanism shipped in 2026-07-09-story-fix-and-reevaluate-loop.md with a uniform currentAttempt() resolution that works identically at every depth of a story's task tree, not just the root. Also corrects the 2026-07-08 spec's incorrect claim that Task.AcceptanceCriteria already exists.

docs: add design spec for recursive story decomposition

2026-07-08T08:20:13+00:00

Retro from the tasks-board build (see memory claudomator-sequential-orchestration-gap): claudomator has no native way to drive a stated intent through review-gated implementation to arbitrary depth -- that role was played by a human/chatbot controller hand-dispatching and re-dispatching all session. Design converged through several rejected drafts (a separate "chain mode" pipeline, a distinct Planner role) before landing on the actual shape: one role, one recursive decompose-or-evaluate mechanism, applied at every depth, with arbitrated multi-evaluator review running at every node instead of once at a story's outer level. Co-Authored-By: Claude Sonnet 5 Claude-Session: https://claude.ai/code/session_01VTUSAEKfsPc6WGDq45yPHD

docs: add design spec for unified Tasks board

2026-07-06T00:47:57+00:00

Adds a Tasks tab (Kanban board, 5 columns: Queue/Running/Ready/ Interrupted/Done) covering all tasks regardless of story association, with inline auto-tailing execution logs on every card. Mostly a revival/generalization of UI code removed in cc6b323, plus a generalization of the existing Running-tab log-stream mechanism to every column. Co-Authored-By: Claude Sonnet 5 Claude-Session: https://claude.ai/code/session_01VTUSAEKfsPc6WGDq45yPHD

docs: task checker agent and story ship gate design spec

2026-04-04T07:40:45+00:00

Co-Authored-By: Claude Sonnet 4.6