feat: implement tweaks plan - modals, smart shell, spinner, /models, debug log, skills

Phase 1: Permission modal dialog, session resume modal, HistoryInput with
up/down arrow cycling, remove "You:" echo from chat log, LLM client cleanup
on unmount.

Phase 2: Smart shell auto-approve using allowed/denied command lists from
ToolsConfig, animated thinking spinner with live token count in status bar.

Phase 3: /models slash command (list + switch), CLI directory positional
argument, JSONL debug logger with rotation.

Phase 4: Skills system with SkillsManager, load_skill LLM tool, /skills
listing, skill invocation via slash commands, system prompt integration.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

app/tools/skills.py

@@ -0,0 +1,60 @@
+"""Load skill tool — allows the LLM to load skill instructions on demand."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any, ClassVar
+
+from pydantic import BaseModel, Field
+
+from app.models.config import AppConfig
+from app.models.tool_call import ToolResult, ToolResultStatus
+from app.services.skills import SkillsManager
+from app.tools.base import BaseTool
+
+
+class LoadSkillParams(BaseModel):
+    """Parameters for the load_skill tool."""
+
+    name: str = Field(description="Name of the skill to load")
+
+
+class LoadSkillTool(BaseTool):
+    """Load a skill's full instructions by name.
+
+    Use when a skill is relevant to the current task.
+    """
+
+    name: ClassVar[str] = "load_skill"
+    description: ClassVar[str] = (
+        "Load a skill's full instructions by name. "
+        "Use when a skill is relevant to the current task."
+    )
+    params_model: ClassVar[type[BaseModel]] = LoadSkillParams
+
+    def __init__(
+        self,
+        workspace_root: Path,
+        config: AppConfig,
+        skills_manager: SkillsManager,
+    ) -> None:
+        super().__init__(workspace_root, config)
+        self._skills = skills_manager
+
+    def execute(self, *, tool_call_id: str, **kwargs: Any) -> ToolResult:
+        skill_name: str = kwargs["name"]
+        content = self._skills.load_skill(skill_name)
+        if content is None:
+            available = [s.name for s in self._skills.list_skills()]
+            return ToolResult(
+                tool_call_id=tool_call_id,
+                tool_name=self.name,
+                status=ToolResultStatus.ERROR,
+                error=f"Unknown skill '{skill_name}'. Available: {available}",
+            )
+        return ToolResult(
+            tool_call_id=tool_call_id,
+            tool_name=self.name,
+            status=ToolResultStatus.SUCCESS,
+            output=content,
+        )