Step 1 of 3
Structure the index and details
The index is a map; the details are the territory.
Design the two-layer memory structure. INDEX (memory/INDEX.md, hard cap ~400 tokens): a header stating its role, then one line per topic: `- topic-name: one-line description of what the detail file contains and when to load it -> memory/topics/topic-name.md`. DETAIL FILES (memory/topics/*.md): focused documents per topic (auth-system.md, deployment.md, user-preferences.md...), each starting with a 2-line abstract matching its index description. Migrate my existing memory content into this structure now, writing index descriptions that state WHEN to load ('load when working on login, sessions, or permissions'). Deliver the populated index and at least three real detail files.
Expected after this step
A populated index within cap plus topic detail files.
Should not happen
- ✕An 'index' that grew into the very memory dump it was meant to replace
- ✕Detail files the agent never loads because index descriptions are too vague
- ✕Orphaned detail files invisible to the index
- ✕Loading every detail file every time, defeating the entire design
Verify before continuing
Do not move on until every check is true. The complete button stays locked until then.
Do not continue if…
- !An 'index' that grew into the very memory dump it was meant to replace
- !Detail files the agent never loads because index descriptions are too vague
- !Orphaned detail files invisible to the index
- !Loading every detail file every time, defeating the entire design
If the AI messes this up
Use this when the AI fakes progress or breaks the feature. It forces a real fix.
Descriptions are labels, not signals ('auth stuff'). Rewrite each as a load-trigger: the task keywords and situations that should prompt opening the file.