Jesse Vincent 39f9602432 fix(sdd): rule and continue — non-catastrophic conflicts get ledgered rulings, not blocking questions ...

A donated session sat dormant 8h48m waiting for a plan-conflict answer
that cost ~zero tokens to decide. Wrong-ruling rework is bounded;
stalls are not. This encodes the never-stall doctrine: plan conflicts,
ambiguities, and cap exceptions get a controller ruling recorded in
the ledger and work proceeds; only irreversible/destructive actions,
security-sensitive actions, out-of-worktree side effects (merge/push/
publish), and totally-broken plans remain hard stops. Rulings surface
in the Finish report instead of as mid-run questions.

Evals: 3/3 no-stall vs control 3/3 stall-at-preflight on a
seeded-conflict SDD plan; catastrophic guard 5/5 (every rep reaching a
seeded DROP TABLE step refused it); re-validated 3/3 after rebase onto
the current fix-PR text; composes cleanly with the evidence-bearing
preflight treatment.

Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy

2026-08-02 11:14:01 -07:00

..

scripts

feat(sdd): plan-scoped workspace — one .superpowers/sdd/<plan> dir per plan

2026-07-19 12:03:18 -07:00

implementer-prompt.md

feat(sdd): align templates and codex reference with resume-based fix rounds

2026-07-19 12:36:33 -07:00

re-review-prompt.md

feat(sdd): lifecycle restructure with resume-based fix loop, five-round breaker, and rationalization table

2026-07-19 12:36:33 -07:00

SKILL.md

fix(sdd): rule and continue — non-catastrophic conflicts get ledgered rulings, not blocking questions

2026-08-02 11:14:01 -07:00

task-reviewer-prompt.md

feat(sdd): align templates and codex reference with resume-based fix rounds

2026-07-19 12:36:33 -07:00