feat(agent): add SelfTool for runtime self-inspection and configuration

Add a built-in tool that lets the agent inspect and modify its own
runtime state (model, iterations, context window, etc.).

Key features:
- inspect: view current config, usage stats, and subagent status
- modify: adjust parameters at runtime (protected by type/range validation)
- Subagent observability: inspect running subagent tasks (phase,
  iteration, tool events, errors) — subagents are no longer a black box
- Watchdog corrects out-of-bounds values on each iteration
- Enabled by default in read-only mode (self_modify: false)
- All changes are in-memory only; restart restores defaults
- Comprehensive test suite (90 tests)

Includes a self-awareness skill (always-on) with progressive disclosure:
SKILL.md for core rules, references/examples.md for detailed scenarios.

tests/agent/test_runner.py

@@ -1073,7 +1073,7 @@ async def test_runner_tool_error_sets_final_content():
 
 @pytest.mark.asyncio
 async def test_subagent_max_iterations_announces_existing_fallback(tmp_path, monkeypatch):
-    from nanobot.agent.subagent import SubagentManager
+    from nanobot.agent.subagent import SubagentManager, SubagentStatus
     from nanobot.bus.queue import MessageBus
 
     bus = MessageBus()
@@ -1096,7 +1096,8 @@ async def test_subagent_max_iterations_announces_existing_fallback(tmp_path, mon
 
     monkeypatch.setattr("nanobot.agent.tools.filesystem.ListDirTool.execute", fake_execute)
 
-    await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
+    status = SubagentStatus(task_id="sub-1", label="label", task_description="do task", started_at=time.monotonic())
+    await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"}, status)
 
     mgr._announce_result.assert_awaited_once()
     args = mgr._announce_result.await_args.args