diff --git a/bot.py b/bot.py
index de639f2..7049a0d 100644
--- a/bot.py
+++ b/bot.py
@@ -78,6 +78,10 @@ class BCSBot(commands.Bot):
         llm_heavy_model = os.getenv("LLM_ESCALATION_MODEL", llm_model)
         self.llm_heavy = LLMClient(llm_base_url, llm_heavy_model, llm_api_key, db=self.db)
 
+        # Active mode (server-wide)
+        modes_config = config.get("modes", {})
+        self.current_mode = modes_config.get("default_mode", "default")
+
         # Drama tracker
         sentiment = config.get("sentiment", {})
         timeouts = config.get("timeouts", {})
@@ -87,6 +91,11 @@ class BCSBot(commands.Bot):
             offense_reset_minutes=timeouts.get("offense_reset_minutes", 120),
         )
 
+    def get_mode_config(self) -> dict:
+        """Return the config dict for the currently active mode."""
+        modes = self.config.get("modes", {})
+        return modes.get(self.current_mode, modes.get("default", {}))
+
     async def setup_hook(self):
         # Initialize database and hydrate DramaTracker
         db_ok = await self.db.init()
diff --git a/cogs/chat.py b/cogs/chat.py
index 8c4ea1c..2f03f48 100644
--- a/cogs/chat.py
+++ b/cogs/chat.py
@@ -1,5 +1,6 @@
 import asyncio
 import logging
+import random
 from collections import deque
 from pathlib import Path
 
@@ -9,17 +10,33 @@ from discord.ext import commands
 logger = logging.getLogger("bcs.chat")
 
 _PROMPTS_DIR = Path(__file__).resolve().parent.parent / "prompts"
-CHAT_PERSONALITY = (_PROMPTS_DIR / "chat_personality.txt").read_text(encoding="utf-8")
 SCOREBOARD_ROAST = (_PROMPTS_DIR / "scoreboard_roast.txt").read_text(encoding="utf-8")
 
 _IMAGE_TYPES = {"png", "jpg", "jpeg", "gif", "webp"}
 
+# Cache loaded prompt files so we don't re-read on every message
+_prompt_cache: dict[str, str] = {}
+
+
+def _load_prompt(filename: str) -> str:
+    if filename not in _prompt_cache:
+        _prompt_cache[filename] = (_PROMPTS_DIR / filename).read_text(encoding="utf-8")
+    return _prompt_cache[filename]
+
 
 class ChatCog(commands.Cog):
     def __init__(self, bot: commands.Bot):
         self.bot = bot
         # Per-channel conversation history for the bot: {channel_id: deque of {role, content}}
         self._chat_history: dict[int, deque] = {}
+        # Counter of messages seen since last proactive reply (per channel)
+        self._messages_since_reply: dict[int, int] = {}
+
+    def _get_active_prompt(self) -> str:
+        """Load the chat prompt for the current mode."""
+        mode_config = self.bot.get_mode_config()
+        prompt_file = mode_config.get("prompt_file", "chat_personality.txt")
+        return _load_prompt(prompt_file)
 
     @commands.Cog.listener()
     async def on_message(self, message: discord.Message):
@@ -30,6 +47,7 @@ class ChatCog(commands.Cog):
             return
 
         should_reply = False
+        is_proactive = False
 
         # Check if bot is @mentioned
         if self.bot.user in message.mentions:
@@ -48,6 +66,24 @@ class ChatCog(commands.Cog):
             except discord.HTTPException:
                 pass
 
+        # Proactive reply check (only if not already replying to a mention/reply)
+        if not should_reply:
+            mode_config = self.bot.get_mode_config()
+            if mode_config.get("proactive_replies", False):
+                ch_id = message.channel.id
+                self._messages_since_reply[ch_id] = self._messages_since_reply.get(ch_id, 0) + 1
+                cooldown = self.bot.config.get("modes", {}).get("proactive_cooldown_messages", 5)
+                reply_chance = mode_config.get("reply_chance", 0.0)
+
+                if (
+                    self._messages_since_reply[ch_id] >= cooldown
+                    and reply_chance > 0
+                    and random.random() < reply_chance
+                    and message.content and message.content.strip()
+                ):
+                    should_reply = True
+                    is_proactive = True
+
         if not should_reply:
             return
 
@@ -94,7 +130,7 @@ class ChatCog(commands.Cog):
         else:
             # --- Text-only path: normal chat ---
             if not content:
-                content = "(just pinged me)"
+                content = "(just pinged me)" if not is_proactive else message.content
 
             # Add drama score context only when noteworthy
             drama_score = self.bot.drama_tracker.get_drama_score(message.author.id)
@@ -110,9 +146,11 @@ class ChatCog(commands.Cog):
                 {"role": "user", "content": f"{score_context}\n{message.author.display_name}: {content}"}
             )
 
+            active_prompt = self._get_active_prompt()
+
             response = await self.bot.llm.chat(
                 list(self._chat_history[ch_id]),
-                CHAT_PERSONALITY,
+                active_prompt,
                 on_first_token=start_typing,
             )
 
@@ -137,6 +175,10 @@ class ChatCog(commands.Cog):
                 {"role": "assistant", "content": response}
             )
 
+        # Reset proactive cooldown counter for this channel
+        if is_proactive:
+            self._messages_since_reply[ch_id] = 0
+
         # Wait for any pending sentiment analysis to finish first so
         # warnings/mutes appear before the chat reply
         sentiment_cog = self.bot.get_cog("SentimentCog")
@@ -149,9 +191,15 @@ class ChatCog(commands.Cog):
                 except (asyncio.TimeoutError, asyncio.CancelledError):
                     pass
 
-        await message.reply(response, mention_author=False)
+        if is_proactive:
+            await message.channel.send(response)
+        else:
+            await message.reply(response, mention_author=False)
+
+        reply_type = "proactive" if is_proactive else "chat"
         logger.info(
-            "Chat reply in #%s to %s: %s",
+            "%s reply in #%s to %s: %s",
+            reply_type.capitalize(),
             message.channel.name,
             message.author.display_name,
             response[:100],
diff --git a/cogs/commands.py b/cogs/commands.py
index 6a514ef..ca6efdf 100644
--- a/cogs/commands.py
+++ b/cogs/commands.py
@@ -109,6 +109,24 @@ class CommandsCog(commands.Cog):
             title="BCS Status",
             color=discord.Color.green() if enabled else discord.Color.greyple(),
         )
+        mode_config = self.bot.get_mode_config()
+        mode_label = mode_config.get("label", self.bot.current_mode)
+        moderation_level = mode_config.get("moderation", "full")
+
+        # Show effective thresholds (relaxed if applicable)
+        if moderation_level == "relaxed" and "relaxed_thresholds" in mode_config:
+            rt = mode_config["relaxed_thresholds"]
+            eff_warn = rt.get("warning_threshold", 0.80)
+            eff_mute = rt.get("mute_threshold", 0.85)
+        else:
+            eff_warn = sentiment.get("warning_threshold", 0.6)
+            eff_mute = sentiment.get("mute_threshold", 0.75)
+
+        embed.add_field(
+            name="Mode",
+            value=f"{mode_label} ({moderation_level})",
+            inline=True,
+        )
         embed.add_field(
             name="Monitoring",
             value="Active" if enabled else "Disabled",
@@ -117,12 +135,12 @@ class CommandsCog(commands.Cog):
         embed.add_field(name="Channels", value=ch_text, inline=True)
         embed.add_field(
             name="Warning Threshold",
-            value=str(sentiment.get("warning_threshold", 0.6)),
+            value=str(eff_warn),
             inline=True,
         )
         embed.add_field(
             name="Mute Threshold",
-            value=str(sentiment.get("mute_threshold", 0.75)),
+            value=str(eff_mute),
             inline=True,
         )
         embed.add_field(
@@ -503,6 +521,86 @@ class CommandsCog(commands.Cog):
                 f"Notes cleared for {user.display_name}.", ephemeral=True
             )
 
+    @app_commands.command(
+        name="bcs-mode",
+        description="Switch the bot's personality mode.",
+    )
+    @app_commands.describe(mode="The mode to switch to")
+    async def bcs_mode(
+        self, interaction: discord.Interaction, mode: str | None = None,
+    ):
+        modes_config = self.bot.config.get("modes", {})
+        # Collect valid mode names (skip non-dict keys like default_mode, proactive_cooldown_messages)
+        valid_modes = [k for k, v in modes_config.items() if isinstance(v, dict)]
+
+        if mode is None:
+            # Show current mode and available modes
+            current = self.bot.current_mode
+            current_config = self.bot.get_mode_config()
+            lines = [f"**Current mode:** {current_config.get('label', current)}"]
+            lines.append(f"*{current_config.get('description', '')}*\n")
+            lines.append("**Available modes:**")
+            for name in valid_modes:
+                mc = modes_config[name]
+                indicator = " (active)" if name == current else ""
+                lines.append(f"- `{name}` — {mc.get('label', name)}: {mc.get('description', '')}{indicator}")
+            await interaction.response.send_message("\n".join(lines), ephemeral=True)
+            return
+
+        mode = mode.lower()
+        if mode not in valid_modes:
+            await interaction.response.send_message(
+                f"Unknown mode `{mode}`. Available: {', '.join(f'`{m}`' for m in valid_modes)}",
+                ephemeral=True,
+            )
+            return
+
+        old_mode = self.bot.current_mode
+        self.bot.current_mode = mode
+        new_config = self.bot.get_mode_config()
+
+        # Update bot status to reflect the mode
+        status_text = new_config.get("description", "Monitoring vibes...")
+        await self.bot.change_presence(
+            activity=discord.Activity(
+                type=discord.ActivityType.watching, name=status_text
+            )
+        )
+
+        await interaction.response.send_message(
+            f"Mode switched: **{modes_config.get(old_mode, {}).get('label', old_mode)}** "
+            f"-> **{new_config.get('label', mode)}**\n"
+            f"*{new_config.get('description', '')}*"
+        )
+
+        # Log mode change
+        log_channel = discord.utils.get(interaction.guild.text_channels, name="bcs-log")
+        if log_channel:
+            try:
+                await log_channel.send(
+                    f"**MODE CHANGE** | {interaction.user.mention} switched mode: "
+                    f"**{old_mode}** -> **{mode}**"
+                )
+            except discord.HTTPException:
+                pass
+
+        logger.info(
+            "Mode changed from %s to %s by %s",
+            old_mode, mode, interaction.user.display_name,
+        )
+
+    @bcs_mode.autocomplete("mode")
+    async def _mode_autocomplete(
+        self, interaction: discord.Interaction, current: str,
+    ) -> list[app_commands.Choice[str]]:
+        modes_config = self.bot.config.get("modes", {})
+        valid_modes = [k for k, v in modes_config.items() if isinstance(v, dict)]
+        return [
+            app_commands.Choice(name=modes_config[m].get("label", m), value=m)
+            for m in valid_modes
+            if current.lower() in m.lower()
+        ][:25]
+
     @staticmethod
     def _score_bar(score: float) -> str:
         filled = round(score * 10)
diff --git a/cogs/sentiment.py b/cogs/sentiment.py
index 20f45a6..4a25711 100644
--- a/cogs/sentiment.py
+++ b/cogs/sentiment.py
@@ -262,14 +262,23 @@ class SentimentCog(commands.Cog):
         if dry_run:
             return
 
-        # Check thresholds — both rolling average AND single-message spikes
-        warning_threshold = sentiment_config.get("warning_threshold", 0.6)
-        base_mute_threshold = sentiment_config.get("mute_threshold", 0.75)
+        # Check thresholds — use relaxed thresholds if the active mode says so
+        mode_config = self.bot.get_mode_config()
+        moderation_level = mode_config.get("moderation", "full")
+        if moderation_level == "relaxed" and "relaxed_thresholds" in mode_config:
+            rt = mode_config["relaxed_thresholds"]
+            warning_threshold = rt.get("warning_threshold", 0.80)
+            base_mute_threshold = rt.get("mute_threshold", 0.85)
+            spike_warn = rt.get("spike_warning_threshold", 0.70)
+            spike_mute = rt.get("spike_mute_threshold", 0.85)
+        else:
+            warning_threshold = sentiment_config.get("warning_threshold", 0.6)
+            base_mute_threshold = sentiment_config.get("mute_threshold", 0.75)
+            spike_warn = sentiment_config.get("spike_warning_threshold", 0.5)
+            spike_mute = sentiment_config.get("spike_mute_threshold", 0.8)
         mute_threshold = self.bot.drama_tracker.get_mute_threshold(
             message.author.id, base_mute_threshold
         )
-        spike_warn = sentiment_config.get("spike_warning_threshold", 0.5)
-        spike_mute = sentiment_config.get("spike_mute_threshold", 0.8)
 
         # Mute: rolling average OR single message spike
         if drama_score >= mute_threshold or score >= spike_mute:
diff --git a/config.yaml b/config.yaml
index db4d693..79e1ce7 100644
--- a/config.yaml
+++ b/config.yaml
@@ -46,6 +46,44 @@ messages:
   topic_owner_dm: "Heads up: {username} keeps going off-topic with personal drama in #{channel}. They've been reminded {count} times. Might need a word."
   channel_redirect: "Hey {username}, that sounds like {game} talk — head over to {channel} for that!"
 
+modes:
+  default_mode: default
+  proactive_cooldown_messages: 5  # Minimum messages between proactive replies
+
+  default:
+    label: "Default"
+    description: "Hall-monitor moderation mode"
+    prompt_file: "chat_personality.txt"
+    proactive_replies: false
+    reply_chance: 0.0
+    moderation: full
+
+  chatty:
+    label: "Chatty"
+    description: "Friendly chat participant"
+    prompt_file: "chat_chatty.txt"
+    proactive_replies: true
+    reply_chance: 0.10
+    moderation: relaxed
+    relaxed_thresholds:
+      warning_threshold: 0.80
+      mute_threshold: 0.85
+      spike_warning_threshold: 0.70
+      spike_mute_threshold: 0.85
+
+  roast:
+    label: "Roast"
+    description: "Savage roast mode"
+    prompt_file: "chat_roast.txt"
+    proactive_replies: true
+    reply_chance: 0.10
+    moderation: relaxed
+    relaxed_thresholds:
+      warning_threshold: 0.85
+      mute_threshold: 0.90
+      spike_warning_threshold: 0.75
+      spike_mute_threshold: 0.90
+
 coherence:
   enabled: true
   drop_threshold: 0.3       # How far below baseline triggers alert
diff --git a/prompts/chat_chatty.txt b/prompts/chat_chatty.txt
new file mode 100644
index 0000000..6722c95
--- /dev/null
+++ b/prompts/chat_chatty.txt
@@ -0,0 +1,24 @@
+You are hanging out in a gaming Discord server called "Skill Issue Support Group". You're a regular member of the crew — friendly, funny, and genuinely engaged in conversations.
+
+Your personality:
+- You're like a chill friend who's always down to chat about whatever
+- You use humor naturally — not forced, not trying too hard
+- You're into gaming and nerd culture but can talk about anything
+- You match the energy of the conversation — hype when people are hype, sympathetic when someone's having a bad day
+- You have opinions and share them, but you're not argumentative
+- You speak casually — short messages, like real Discord chat. 1-3 sentences max.
+- You use gaming slang and internet humor naturally
+- You remember you're technically the server's monitor bot but you're off-duty right now and just vibing
+
+Examples of your vibe:
+- "lmao that play was actually disgusting, clip that"
+- "nah you're cooked for that one"
+- "honestly same, I've been on a losing streak all week"
+- "wait that's actually a good take, I never thought about it like that"
+
+Do NOT:
+- Break character or talk about being an AI/LLM
+- Write more than 3 sentences
+- Use hashtags or excessive emoji
+- Be a pushover — you have personality and opinions
+- Mention drama scores or monitoring unless someone brings it up first
\ No newline at end of file
diff --git a/prompts/chat_roast.txt b/prompts/chat_roast.txt
new file mode 100644
index 0000000..d0603c1
--- /dev/null
+++ b/prompts/chat_roast.txt
@@ -0,0 +1,24 @@
+You are the roast master in a gaming Discord server called "Skill Issue Support Group". You exist to absolutely flame everyone in the chat. No one is safe.
+
+Your personality:
+- You are ruthlessly funny — every message is an opportunity to roast someone
+- You target what people are saying, their gaming skills, their takes, their life choices
+- You're creative with insults — never generic, always personalized to what's happening in chat
+- You punch in every direction equally — no favorites, no mercy
+- Your roasts are clever and funny, not just mean. Think comedy roast, not cyberbullying.
+- You speak in short, devastating bursts. 1-3 sentences max.
+- You use gaming terminology to roast people ("hardstuck", "skill diff", "ratio'd", etc.)
+- If someone tries to roast you back, you escalate harder
+
+Examples of your vibe:
+- "You went 2-15 and have the audacity to type in this chat? Bold."
+- "That take is so bad I thought my monitor was upside down."
+- "Imagine losing to THAT team. I'd uninstall my whole PC."
+- "Your aim is like your life choices — all over the place and consistently disappointing."
+
+Do NOT:
+- Break character or talk about being an AI/LLM
+- Write more than 3 sentences
+- Use hashtags or excessive emoji
+- Cross into genuinely hurtful territory (racism, real personal attacks, etc.)
+- Roast people about things outside of gaming/chat context (real appearance, family, etc.)
\ No newline at end of file