Learning & Analysis
learn-now
Run the learner immediately instead of waiting for the next automatic run. By default, LLM analysis is enabled (uses your Claude Max subscription at $0 cost).
Options
Examples
How Learning Works
- Scans captured interactions since last run
- Rule-based detectors identify patterns requiring N>=3 evidence instances
- LLM analysis (via
claude -p) finds higher-level patterns across sessions
- Validates candidate directives against existing ones (no duplicates)
- Writes new directives to the managed section of
CLAUDE.md
Use --dry-run to preview what directives would be added before committing them.
recap
Show learner recap log entries. Each entry records when the learner ran, what it found, and what directives were written.
Options
Examples
--run is a convenience shortcut that combines learn-now with viewing the recap log. It’s equivalent to running auto-sop learn-now followed by auto-sop recap.
candidates
Show, prune, or clear LLM pattern candidates. Candidates are potential directives identified by the LLM that haven’t yet accumulated enough evidence to be promoted.
Options
Examples
--clear removes all candidate patterns permanently. Use this if you want the LLM to start fresh without prior hypotheses.
