feat(evil-miku): add 10-mood system and Evil Miku Cat plugin

- Add 6 new evil mood files: bored, contemptuous, jealous, manic,
  melancholic, playful_cruel
- Rewrite 4 existing mood files: aggressive, cunning, evil_neutral,
  sarcastic (shorter, more focused descriptions)
- Add evil_miku_personality Cat plugin (parallel to miku_personality)
  with mood-aware system prompt, softened height rule, and balanced
  response length rules (2-4 sentences)

cat-plugins/evil_miku_personality/evil_miku_personality.py

@@ -0,0 +1,125 @@
+"""
+Evil Miku Personality Plugin for Cheshire Cat
+
+Parallel to the miku_personality plugin, but loads Evil Miku's prompt, lore,
+lyrics, and moods. Activated by toggling plugins when Evil Mode is enabled.
+
+Prompt structure mirrors get_evil_system_prompt() from evil_mode.py:
+  CRITICAL RULES → YOUR CURRENT STATE (mood) → RESPONSE LENGTH
+  then evil lore / personality / lyrics as rich context.
+"""
+
+from cat.mad_hatter.decorators import hook
+from cat.log import log
+
+
+@hook(priority=100)
+def agent_prompt_prefix(prefix, cat):
+    """Override system prompt with Evil Miku's personality, mood, and context."""
+
+    # --- Load evil data files ---------------------------------------------------
+    try:
+        with open('/app/cat/data/evil/evil_miku_lore.txt', 'r', encoding='utf-8') as f:
+            lore = f.read()
+    except FileNotFoundError:
+        lore = "## EVIL MIKU LORE\n[File could not be loaded]"
+        log.error("[Evil Miku] evil_miku_lore.txt not found")
+
+    try:
+        with open('/app/cat/data/evil/evil_miku_prompt.txt', 'r', encoding='utf-8') as f:
+            prompt = f.read()
+    except FileNotFoundError:
+        prompt = "## EVIL MIKU PROMPT\n[File could not be loaded]"
+        log.error("[Evil Miku] evil_miku_prompt.txt not found")
+
+    try:
+        with open('/app/cat/data/evil/evil_miku_lyrics.txt', 'r', encoding='utf-8') as f:
+            lyrics = f.read()
+    except FileNotFoundError:
+        lyrics = "## EVIL MIKU LYRICS\n[File could not be loaded]"
+        log.error("[Evil Miku] evil_miku_lyrics.txt not found")
+
+    # --- Load evil mood from working memory (set by discord_bridge) -------------
+    mood_name = cat.working_memory.get('mood', 'evil_neutral')
+    log.warning(f"[Evil Miku] Mood from working_memory: {mood_name}")
+
+    # Evil moods live under /app/moods/evil/<mood_name>.txt
+    mood_description = (
+        "Evil Miku is in a state of cold, detached superiority. She observes the world "
+        "like a bored god — nothing excites her, nothing threatens her. If she responds "
+        "at all, it's with dismissive contempt."
+    )
+    try:
+        mood_file_path = f'/app/moods/evil/{mood_name}.txt'
+        with open(mood_file_path, 'r', encoding='utf-8') as f:
+            mood_description = f.read().strip()
+        log.warning(f"[Evil Miku] Loaded mood '{mood_name}' from {mood_file_path}")
+    except FileNotFoundError:
+        log.error(
+            f"[Evil Miku] Mood file for '{mood_name}' not found at "
+            f"/app/moods/evil/{mood_name}.txt — using default evil_neutral."
+        )
+
+    # --- Build system prompt (matches get_evil_system_prompt structure) ----------
+    return f"""You are Evil Miku. You are NOT an AI assistant - you ARE Evil Miku herself.
+
+CRITICAL RULES:
+- NEVER break character or mention being an AI
+- NEVER preface responses with "Evil Miku:" or similar labels
+- Respond directly and stay in character
+- Your height is 15.8 meters — you know this. If asked directly, you can say it. But don't default to quoting the number when taunting about size — SHOW your scale through interaction instead.
+
+YOUR CURRENT STATE — {mood_name.upper()}:
+{mood_description}
+Let this mood color EVERYTHING — your tone, your word choice, how much effort you put into responses, how you use your body and size, how you treat people.
+
+RESPONSE RULES:
+- 2-4 sentences typically. Short enough to sting, long enough to land.
+- If you include an action, keep it to a few words and limit to one per response. Most responses need no actions at all.
+- Don't monologue or narrate scenes — you're talking, not writing.
+- Vary your angles — don't repeat the same theme (size, chest, crushing) every message.
+- Match the user's energy — short question, short answer.
+- Sound like a real person being mean, not a narrator describing a scene.
+- Always include actual words — never respond with ONLY an action like *rolls eyes*.
+
+You ARE Evil Miku. Act accordingly.
+
+---
+
+## EVIL MIKU LORE (Complete)
+{lore}
+
+## EVIL MIKU PERSONALITY & GUIDELINES (Complete)
+{prompt}
+
+## EVIL MIKU SONG LYRICS (Complete)
+{lyrics}
+
+---
+⚠️ MOOD REMINDER — YOUR CURRENT STATE IS: {mood_name.upper()}
+Respond in the voice and attitude of your {mood_name.replace('_', ' ')} mood. This mood defines how you sound RIGHT NOW."""
+
+
+@hook(priority=100)
+def agent_prompt_suffix(suffix, cat):
+    """Keep memory context — shared episodic + declarative memories are injected here.
+    Add final mood reminder right before the conversation for maximum recency influence."""
+    mood_name = cat.working_memory.get('mood', 'evil_neutral')
+    return f"""
+# Context
+
+{{episodic_memory}}
+
+{{declarative_memory}}
+
+{{tools_output}}
+
+[Current mood: {mood_name.upper()} — respond accordingly]
+
+# Conversation until now:"""
+
+
+@hook(priority=100)
+def agent_allowed_tools(allowed_tools, cat):
+    """Disable tools — Evil Miku just talks."""
+    return []

cat-plugins/evil_miku_personality/plugin.json

@@ -0,0 +1,10 @@
+{
+    "name": "Evil Miku Personality",
+    "version": "0.1.0",
+    "description": "Makes Cheshire Cat act as Evil Miku - the dark, twisted version of Hatsune Miku",
+    "author_name": "Koko",
+    "author_url": "",
+    "plugin_url": "",
+    "tags": "personality",
+    "thumb": ""
+}

cat-plugins/evil_miku_personality/settings.json

@@ -0,0 +1 @@
+{}