Agents page: collapse anatomy into icon cards → pretty editable modal

The agent command center's BRAIN+SURFACE columns are now a grid of compact icon
cards (system prompt / how it operates / personality / skills / capabilities /
tools / memory / safety). Clicking a card opens a modal with the full content,
nicely formatted (markdown/persona/tags), editable for the four brain text files
(system_prompt, agent_md, persona, skills_md) and saved back to the .brain via
PATCH /api/claws/{id}/brain. Capabilities/tools/memory/safety render read-only
(tools keeps its Add affordance). LIVE column unchanged.

- frontend: new AnatomyGrid (icon cards + SectionModal); ClawCommandCenter swaps the
  two verbose columns for it; skills_md added to RawBrain types.
- backend: cm-brain skills_md() getter + skills_md in ClawBrainResponse so the skills
  editor pre-fills (avoids blank-overwrite).

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>

crates/cm-api/src/routes/claws.rs

@@ -151,6 +151,9 @@ pub struct ClawBrainResponse {
     /// AGENTS.md — "how I operate" (workflow/rules); folded into the live prompt.
     pub agent_md: Option<String>,
     pub personality: Option<String>,
+    /// The brain-pack narrative skills doc (`skills/skills_md`); editable source
+    /// for the skills section (the structured `skills` list is derived display).
+    pub skills_md: Option<String>,
     pub skills: Vec<BrainSkill>,
     pub tools: Vec<BrainTool>,
     /// Recent conversational memory chunks, newest first.
@@ -209,6 +212,7 @@ fn load_brain(agent: &Agent, skills: &[(String, String)]) -> ClawBrainResponse {
         system_prompt: brain.system_prompt(),
         agent_md: brain.agent_md(),
         personality: brain.personality(),
+        skills_md: brain.skills_md(),
         skills: skills_v,
         tools: tools_v,
         memory,