Files
superpowers/skills/brainstorming
Drew Ritter 87ddface1a refine(skills): requested deletions still trip the gate
Eval-caught leak (cost-remove-export-boundary-claude, first run): the
agent reasoned "the user already decided the deletion, so no design
decision is open" and silently removed a working feature — reading the
tripwires as indicators of open decisions rather than unconditional
re-gates. The deletion tripwire now carries the same rider as the
security one ("even when the deletion is exactly what was asked"), and
the rationalization table counters the exact quoted escape.
Description: 950/1024 chars.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-10 18:54:14 -07:00
..