Brain: inject identity into the live prompt + surface AGENTS.md in the command center

Gap 1 — the brain's identity sections were stored but UI-only. cm-runtime/brain.rs
`compose_system` now folds the brain's AGENTS.md ("## How I operate") + personality
into the live system prompt (after the Postgres-authoritative base, before skills +
memory; falls back to the brain's soul_md when the base is empty). Mirrors the
OpenClaw/ZeroClaw render order.

Mapping — expose `agent_md` on `GET /api/claws/{id}/brain` (ClawBrainResponse) and
render it as a collapsible "HOW I OPERATE · AGENTS.md" card in the command center's
BRAIN column (RawBrain gains agent_md; richBrain passes it through). So the section
that's now in the prompt is also visible in the UI.

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

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

@@ -148,6 +148,8 @@ pub struct ClawBrainResponse {
     /// Whether a `.brain` file already existed before this request.
     pub exists: bool,
     pub system_prompt: Option<String>,
+    /// AGENTS.md — "how I operate" (workflow/rules); folded into the live prompt.
+    pub agent_md: Option<String>,
     pub personality: Option<String>,
     pub skills: Vec<BrainSkill>,
     pub tools: Vec<BrainTool>,
@@ -205,6 +207,7 @@ fn load_brain(agent: &Agent, skills: &[(String, String)]) -> ClawBrainResponse {
     ClawBrainResponse {
         exists: existed,
         system_prompt: brain.system_prompt(),
+        agent_md: brain.agent_md(),
         personality: brain.personality(),
         skills: skills_v,
         tools: tools_v,