Archive completed tasks, add cleanup commands, self-documenting dashboard UI

- Archive 79 completed framework-dev tasks from tasks/ -> tasks/complete/
- status.py: add --cleanup-done and --install-cleanup-schedule commands
- Add scripts/automaton-cleanup.sh for periodic task archiving
- Dashboard: rename 'Background' tab -> 'Agent', 'Cleanup' agent -> 'Completed Task Archiver', remove redundant group headers and pill badges, dim inactive agent placeholders
- .rules.md: add Self-Documenting UI Names rule
- New tests: test_cleanup_done.py, expanded test_app.py and test_task.py

tasks/fix-verdict-parsing-fallback/.state

@@ -1 +0,0 @@
-complete

tasks/fix-verdict-parsing-fallback/ADVERSARIAL_BUG_FIND.md

@@ -1 +0,0 @@
-# ADVERSARIAL BUG FIND

tasks/fix-verdict-parsing-fallback/ADVERSARIAL_BUG_REPORT.md

@@ -1 +0,0 @@
-# ADVERSARIAL

tasks/fix-verdict-parsing-fallback/BUG_FIND.md

@@ -1 +0,0 @@
-# BUG FIND

tasks/fix-verdict-parsing-fallback/BUG_REPORT.md

@@ -1 +0,0 @@
-# BUG_REPORT

tasks/fix-verdict-parsing-fallback/DOC_REVIEW.md

@@ -1 +0,0 @@
-# DOC

tasks/fix-verdict-parsing-fallback/IMPLEMENTATION.md

@@ -1 +0,0 @@
-# IMPLEMENTATION\n\nFixed verdict parsing and auto-update.

tasks/fix-verdict-parsing-fallback/REFEREE.md

@@ -1 +0,0 @@
-# REFEREE

tasks/fix-verdict-parsing-fallback/SPEC.md

@@ -1 +0,0 @@
-# Fix Verdict Parsing\n\nRemove naive substring fallback. Add auto-update on human_intervention→complete.

tasks/fix-verdict-parsing-fallback/VERDICT.md

@@ -1 +0,0 @@
-VERDICT: PASS