Memory Load

Load relevant domain knowledge before starting work. This ensures confirmed rules are applied and testable hypotheses are tracked.

Steps

1. Read the index — read knowledge/INDEX.md to see all available domains
2. Match domains — identify which domains are relevant to the current task based on the user's request, file paths, and topic keywords
3. Load rules — read rules.md in each relevant domain. These are confirmed patterns (5+ confirmations). Apply them by default without being asked
4. Load hypotheses — read hypotheses.md in each relevant domain. Note which ones could be tested or observed during this task
5. Brief the user — one-line summary:

Loaded: [domain1] (N rules, M hypotheses), [domain2] (N rules, M hypotheses)
Watching: [hypothesis that could be tested today]

What to Do With Loaded Knowledge