Capture Knowledge

type = primary classification (what kind?); tags = cross-cutting topics (what about?).

Process

1. Receive Triage Output

Use triage's new items list as the capture scope:

New items from triage (→ capture):
- [item description] — no matching node
  Suggested relations: [[foo]], [[bar]] (shared tags: architecture)
- [item description] — no matching node
  Suggested relations: none

2. Decide node granularity

Not every triage item needs its own file. Before creating, ask: does this item have enough standalone substance to be useful on its own, or is it a detail of something larger?

• Own node: has a distinct title, multiple meaningful sentences, likely to be linked or searched independently
• Decisions always get their own node — even if brief. A decision is "chose X over Y because Z": the rationale makes it independently searchable and worth linking from other contexts. E.g., "chose JWT over session cookies because we need a stateless API" → type: decision node, not a footnote in the component doc.
• Fold into parent: a pure behavior detail, edge case, or implementation consequence of another item in the same batch (e.g., "returns 401 on invalid token" is a consequence of the JWT middleware, not a choice made with rationale)

The deciding criterion is not length but kind: a choice made with rationale → own node; a behavioral detail of an implementation → fold. When folding, capture the detail in the parent node's body. This keeps the graph navigable — thin stub nodes add noise without adding reach.

3. Create Node

For each new item that warrants its own node, create docs/{title-slug}.md:

---