update(mcp, docs): playwright MCP at project scope + browser-drive block in CLAUDE.md; reach-edu pointer bump

The browser-drive-verification rollout's augment-it half: Playwright MCP
lands in the committed .mcp.json (loads next session), the canonical
browser-drive block lands in CLAUDE.md, and clients/reach-edu advances
to the Aspen-Socratic inputs commit.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UvYzx7vDWeafnkAi2nEQeb

Author: mpstaton

.mcp.json

@@ -2,6 +2,14 @@
   "mcpServers": {
     "surrealdb": {
       "command": "${CLAUDE_PROJECT_DIR:-.}/scripts/mcp-surrealdb.sh"
+    },
+    "playwright": {
+      "type": "stdio",
+      "command": "npx",
+      "args": [
+        "@playwright/mcp@latest"
+      ],
+      "env": {}
     }
   }
-}
+}

CLAUDE.md

@@ -2,3 +2,27 @@
 For additional context about technologies to be used, project structure,
 shell commands, and other important information, read the current plan
 <!-- SPECKIT END -->
+
+<!-- lossless:browser-drive:start -->
+## Browser-drive verification (Playwright MCP + Claude Chrome)
+
+Agents verify UI work by driving a real browser BEFORE asking a human to walk the surface. Two tiers:
+
+- **Codified (default): Playwright MCP** — navigate/click/type, accessibility-tree snapshots, DOM assertions; headless-capable, runs unwatched. Wire it per repo at **project scope** (config lands in the committed `.mcp.json`):
+
+  ```bash
+  claude mcp add -s project playwright -- npx @playwright/mcp@latest
+  ```
+
+- **Interactive: `claude --chrome`** (or `/chrome` → enable by default) — Claude drives the operator's real Chrome while they watch; screenshots/GIFs + console and network logs.
+
+Rules that make it safe and cheap:
+
+1. Newly added MCP servers load in the **next** session, not the current one (same rule as skills symlinks).
+2. Prefer **accessibility snapshots over screenshots** — raster is token-expensive; use it only for visual questions (layout, theme).
+3. Browser-driven **reads are unrestricted; writes only against the repo's designated safe target** — never mint test entities in shared/canonical data.
+4. The drive's click-path is **named in the phase plan before implementation**; a drive that lives only in a session transcript is not codified.
+5. A browser drive proves the buttons **work**; the human walk-through still judges whether the surface is **usable**. It augments the human rung, never replaces it.
+
+Full pattern: `context-v/blueprints/Browser-Drive-Verification-For-Agent-Sessions.md` at the anchor monorepo root (kit rollout draft: `ai-labs/context-vigilance-kit/context-v/blueprints/`). Loop integration proven in `ai-labs/augment-it/context-v/loops/`.
+<!-- lossless:browser-drive:end -->