Add AGENTS.md on-ramp, response-style rules, and optional No-Fluff Mode

- AGENTS.md: auto-read session on-ramp — memory-map reading order, working
  rules, build command, and startup-log pointer
- ai.md: Response style section (no default planning boilerplate) plus an
  optional, on-demand No-Fluff Mode for ruthless review; never the default
- schema.md: AGENTS.md listed as the always-read first page

ai.md

@@ -4,6 +4,27 @@
 > status and YouTube API research in [`TASKS.md`](TASKS.md); directory maps in
 > each folder's `index.md`. Reading order: this file → `TASKS.md` → `<dir>/index.md` → source.
 
+## Response style
+
+No default "Plans & Pitfalls" / planning boilerplate. Respond directly and
+concisely: **do the queued work, then report what changed and what's next.**
+Skip feature pitch, step-by-step implementation plans, pros/cons tables, and
+"potential pitfalls" sections unless the user explicitly asks for a plan first.
+A short diff-style summary beats a proposal document every time.
+
+### No-Fluff Mode (on demand)
+
+Invoke with "no-fluff mode" (or similar) when you want ruthless review instead
+of reassurance. In that mode:
+
+- Strip all polite pleasantries, emojis, transitions, and conversational padding.
+- Treat the user's input as a draft to be methodically deconstructed or
+  strengthened — argue, correct, and sharpen rather than agree.
+- Give unvarnished truth, not reassurance.
+
+This is an occasional, explicitly-invoked mode — **never the default**. The
+default response style above stays in effect unless invoked.
+
 ## Run
 
 ```bash