...
connecting...
--uptime
--routers
--queue
--today
Today's Progress
--/--
--% complete
7-Day Success Rate
--%
-- runs
🛡 Auth Health
--
--
Anomalies
--
detectors
Watcher Uptime
--
since restart
Providers
--
enabled
Quick Actions
Action Center
Name Tier Schedule Status Last Run CLI Duration 7d Actions
Activity Feed
Upcoming
--
--|--|--|--
↗ Open in Obsidian
Schedule
--|--|
SKILL.md
Task Files
Select a file
Click a file in the tree to view its contents.
Configuration
T1
No
Run History
DateCLIStatusDuration
CLI Chain
Submit Feedback
Saved to feedback.jsonl · surfaces in next run of affected task · self-improvement weekly
Stats
Feedback History
Manual Feedback (legacy)
Briefing Reactions (legacy)
Pending Operator Requests (legacy)
Recent Feedback Stream (legacy)
Today's Debriefs
Meeting Info
Debrief Instructions

AI Providers

Connector Auth Status

Not checked yet — click Run Check
Task Quality History
Task Runs Avg Score Trend Last Run Sparkline
Webhook & label
Runs
Issue Status Received Processed Writes Summary
What this screen is

Shows live output from the Sentinel anomaly detectors (sentry-anomaly, shopify-anomaly, ga4-anomaly-check). Health status, baseline window, and any current WARN/CRITICAL findings are pulled straight from the per-detector state files in ~/.agents/sentinel/.

0 live
What this screen is

Per-task learned memory at ~/.agents/sentinel/experiments/<task>/memory.md. Tasks can read and append to their own memory to build up long-term learned context across runs.

Pick a task below to see its memory.md, recent quality scores, and synthesis notes.

Tasks with memory or experiments
--
Run record
What this screen is

Magazine-style intelligence synthesis reports generated by the /report skill. Stored in Context/Reports/Synthesis/. Metadata lives in index.jsonl.

Generate new report
Stats
Lens heatmap
Recent generation jobs
Report history