Return the entire .ai-memory/ of the current repo as a Markdown document ready to drop into your LLM context. Call this before starting any task in this repo so you don't redo work other agents already verified.

Args: fact_limit: cap on number of facts (default 50, most recent first).

Record a structured fact you just verified about this codebase, so the next agent (or your next session) doesn't have to re-verify it.

Args: claim: the factual statement (one sentence). file: source file path (relative to repo root) that proves the claim. lines: line range like '42' or '42-50'. tool: name of tool used to verify ('grep', 'read', 'bash', etc.). command: exact command if reproducible. tags: optional tags for later filtering.

List recorded facts, optionally filtered. Useful when you want only facts relevant to a specific area before reading them.

Record a non-trivial decision made while working in this repo (architecture choice, trade-off, deprecation, etc.) as a markdown file under .ai-memory/decisions/.

Args: title: one-line headline of the decision. body: full markdown explanation — context, options considered, reasoning, who/when.

Append a one-line 'watch out for X' note to .ai-memory/gotchas.md. Use for surprises that wasted your time and might trip the next agent.