Decisions 149-150 recorded; instruction files kept true; R-890, R-891, R-644 closed, R-469 narrowed (142 -> 139)

Decision 150 (operator 13:25): sessions correct stale facts in instruction files themselves,
naming each edit; never loosen a rule. Added to unprompted-work.md §5 (all copies) and
PROMPT-TEMPLATE.md §9. CLAUDE.md gates paragraph (R-891), architecture pointer, docs/website
rules, the doubled R-286 sentence in the workspace CLAUDE.md.
Decision 149: vaultwarden's step proven on bench 9401 and box 9202 (evidence here).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS

documentation/runbooks/workspace-CLAUDE.md

@@ -57,9 +57,6 @@ roles. **A file being open in the editor is NOT an instruction. If no task is st
    "working" and "stopped entirely". **And the control must come from a DIFFERENT channel than the measurement** (R-286):
    same query, same snapshot, same API or same clock all share the defect they are meant to catch — a
    stale hub snapshot once "confirmed" itself (2 events all day) while the operator's mailbox held eight
-   alarms. A hub-state check copies `hub.db-wal` too, or asks the running pod. **And the control must come from a DIFFERENT channel than the measurement** (R-286):
-   same query, same snapshot, same API or same clock all share the defect they are meant to catch — a
-   stale hub snapshot once "confirmed" itself (2 events all day) while the operator's mailbox held eight
    alarms. A hub-state check copies `hub.db-wal` too, or asks the running pod.
 4. **A recommendation that is not followed gets one line saying why.** Silence reads as agreement and
    the disagreement is lost.