diff --git a/AGENTS.md b/AGENTS.md
index 543ca2f..0dcffa0 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -69,6 +69,46 @@ The Hermes loop orchestrator must:
 
 ---
 
+## QA Philosophy — File Issues, Don't Stay Quiet
+
+Every agent is a quality engineer. When you see something wrong, broken,
+slow, or missing — **file a Gitea issue**. Don't fix it silently. Don't
+ignore it. Don't wait for someone to notice.
+
+**Escalate bugs:**
+- Test failures → file with traceback, tag `[bug]`
+- Flaky tests → file with reproduction details
+- Runtime errors → file with steps to reproduce
+- Broken behavior on main → file IMMEDIATELY
+
+**Propose improvements — don't be shy:**
+- Slow function? File `[optimization]`
+- Missing capability? File `[feature]`
+- Dead code / tech debt? File `[refactor]`
+- Idea to make Timmy smarter? File `[timmy-capability]`
+- Gap between SOUL.md and reality? File `[soul-gap]`
+
+Bad ideas get closed. Good ideas get built. File them all.
+
+When the issue queue runs low, that's a signal to **look harder**, not relax.
+
+## Dogfooding — Timmy Is Our Product, Use Him
+
+Timmy is not just the thing we're building. He's our teammate and our
+test subject. Every feature we give him should be **used by the agents
+building him**.
+
+- When Timmy gets a new tool, start using it immediately.
+- When Timmy gets a new capability, integrate it into the workflow.
+- When Timmy fails at something, file a `[timmy-capability]` issue.
+- His failures are our roadmap.
+
+The goal: Timmy should be so woven into the development process that
+removing him would hurt. Triage, review, architecture discussion,
+self-testing, reflection — use every tool he has.
+
+---
+
 ## Agent Roster
 
 ### Build Tier
diff --git a/src/config.py b/src/config.py
index c27b17c..503d2a2 100644
--- a/src/config.py
+++ b/src/config.py
@@ -252,7 +252,7 @@ class Settings(BaseSettings):
 
     # ── MCP Servers ────────────────────────────────────────────────────
     # External tool servers connected via Model Context Protocol (stdio).
-    mcp_gitea_command: str = "gitea-mcp -t stdio"
+    mcp_gitea_command: str = "gitea-mcp-server -t stdio"
     mcp_filesystem_command: str = "npx -y @modelcontextprotocol/server-filesystem"
     mcp_timeout: int = 15
 
diff --git a/src/timmy/mcp_tools.py b/src/timmy/mcp_tools.py
index 66cc703..128c9b4 100644
--- a/src/timmy/mcp_tools.py
+++ b/src/timmy/mcp_tools.py
@@ -40,7 +40,7 @@ def _parse_command(command_str: str) -> tuple[str, list[str]]:
     """Split a command string into (executable, args).
 
     Handles ``~/`` expansion and resolves via PATH if needed.
-    E.g. ``"gitea-mcp -t stdio"`` → ``("/Users/x/go/bin/gitea-mcp", ["-t", "stdio"])``
+    E.g. ``"gitea-mcp-server -t stdio"`` → ``("/opt/homebrew/bin/gitea-mcp-server", ["-t", "stdio"])``
     """
     parts = command_str.split()
     executable = os.path.expanduser(parts[0])
diff --git a/tests/timmy/test_cli.py b/tests/timmy/test_cli.py
index f069048..83c5240 100644
--- a/tests/timmy/test_cli.py
+++ b/tests/timmy/test_cli.py
@@ -282,7 +282,7 @@ def test_repl_skips_empty_input():
         patch("timmy.session.chat") as mock_chat,
     ):
         mock_chat.return_value = "Response"
-        result = runner.invoke(app, ["repl"])
+        runner.invoke(app, ["repl"])
 
     # chat should only be called once (for "hello"), empty lines are skipped, exit breaks
     assert mock_chat.call_count == 1
diff --git a/tests/timmy/test_introspection.py b/tests/timmy/test_introspection.py
index c143947..c91989a 100644
--- a/tests/timmy/test_introspection.py
+++ b/tests/timmy/test_introspection.py
@@ -3,6 +3,7 @@
 from unittest.mock import MagicMock, patch
 
 import httpx
+import pytest
 
 
 def test_get_system_info_returns_dict():
@@ -163,6 +164,7 @@ class TestGetOllamaModelExactMatch:
 class TestRunSelfTests:
     """Tests for run_self_tests() — Timmy's self-verification tool."""
 
+    @pytest.mark.slow
     def test_returns_dict_with_expected_keys(self):
         """run_self_tests should return structured test results."""
         from timmy.tools_intro import run_self_tests