diff --git a/docs/agent-profile.md b/docs/agent-profile.md
index 2088d4f67..bc278d2da 100644
--- a/docs/agent-profile.md
+++ b/docs/agent-profile.md
@@ -34,6 +34,7 @@ Define the agent's role, responsibilities, and behavior here.
 - `model` (string): AI model to use
 - `permissionMode` (string, `claude_code` only): One of `"default"`, `"acceptEdits"`, `"plan"`, `"auto"`, `"bypassPermissions"`. When set, the `claude_code` provider passes `--permission-mode <value>` instead of `--dangerously-skip-permissions`. `cao launch --yolo` overrides this and forces bypass. See [Claude Code permission modes](https://code.claude.com/docs/en/permission-modes).
 - `native_agent` (string, `claude_code` only): Name of a native Claude Code agent (`~/.claude/agents/`). When set, the provider passes `--agent <name>` directly and skips system prompt / MCP config decomposition (thin-wrapper mode). See [Claude Code native agent routing](claude-code.md#native-agent-routing).
+- `claudeConfig` (object, `claude_code` only): Per-agent Claude Code knobs mapped to CLI flags at launch. `{"effort": "<low|medium|high|xhigh>"}` adds `--effort <level>` and `{"fallback_model": "<model>"}` adds `--fallback-model <model>`. Lets a profile set per-agent reasoning effort without relying on the machine-global `effortLevel` in `~/.claude/settings.json`. The Claude analog of `codexConfig`; the top-level `model` field still maps to `--model`.
 - `hermesProfile` (string, `hermes` only): Optional Hermes profile wrapper command CAO should launch instead of the default `hermes`, for example one created with `hermes profile alias test-worker`. This is intentionally separate from `codexProfile`: Codex consumes profile names via `codex --profile <name>`, while Hermes aliases are executable commands launched directly as `<alias> chat ...`. See [Hermes Provider](hermes.md).
 - `prompt` (string): Additional prompt text
 
diff --git a/src/cli_agent_orchestrator/models/agent_profile.py b/src/cli_agent_orchestrator/models/agent_profile.py
index 75a81b568..bb8a8ba20 100644
--- a/src/cli_agent_orchestrator/models/agent_profile.py
+++ b/src/cli_agent_orchestrator/models/agent_profile.py
@@ -51,3 +51,12 @@ class AgentProfile(BaseModel):
     # example one created by `hermes profile alias <profile>`). When omitted,
     # the Hermes provider launches the default `hermes` command.
     hermesProfile: Optional[str] = Field(default=None, min_length=1)
+
+    # Claude Code-only. Per-agent Claude Code knobs mapped to CLI flags at
+    # launch: {"effort": "<low|medium|high|xhigh>"} -> `--effort <level>` and
+    # {"fallback_model": "<model>"} -> `--fallback-model <model>`. Lets a
+    # profile set per-agent reasoning effort without relying on the
+    # machine-global `effortLevel` in ~/.claude/settings.json. This is the
+    # Claude analog of codexConfig for the codex provider; the top-level
+    # `model` field still maps to `--model`.
+    claudeConfig: Optional[Dict[str, Any]] = None
diff --git a/src/cli_agent_orchestrator/providers/claude_code.py b/src/cli_agent_orchestrator/providers/claude_code.py
index 7c406acf7..bdd0457ba 100644
--- a/src/cli_agent_orchestrator/providers/claude_code.py
+++ b/src/cli_agent_orchestrator/providers/claude_code.py
@@ -120,6 +120,21 @@ def _build_claude_command(self) -> str:
             if profile.model:
                 command_parts.extend(["--model", profile.model])
 
+            # Apply Claude Code-only per-agent knobs from claudeConfig:
+            #   effort         -> --effort <level>
+            #   fallback_model -> --fallback-model <model>
+            # Claude analog of codexConfig: per-agent reasoning effort without
+            # depending on the machine-global effortLevel in
+            # ~/.claude/settings.json.
+            claude_config = getattr(profile, "claudeConfig", None)
+            if isinstance(claude_config, dict):
+                effort = claude_config.get("effort")
+                if effort:
+                    command_parts.extend(["--effort", str(effort)])
+                fallback_model = claude_config.get("fallback_model")
+                if fallback_model:
+                    command_parts.extend(["--fallback-model", str(fallback_model)])
+
             # Add system prompt - escape newlines to prevent tmux chunking issues
             system_prompt = profile.system_prompt if profile.system_prompt is not None else ""
             system_prompt = self._apply_skill_prompt(system_prompt)
diff --git a/test/providers/test_claude_code_unit.py b/test/providers/test_claude_code_unit.py
index bab0e5145..9a1334b77 100644
--- a/test/providers/test_claude_code_unit.py
+++ b/test/providers/test_claude_code_unit.py
@@ -756,6 +756,55 @@ def test_build_command_omits_model_when_unset(self, mock_load):
         assert "--model" not in command
 
 
+class TestClaudeCodeProviderClaudeConfig:
+    """Tests that profile.claudeConfig maps to Claude Code CLI flags."""
+
+    @patch("cli_agent_orchestrator.providers.claude_code.load_agent_profile")
+    def test_build_command_appends_effort_from_claude_config(self, mock_load):
+        mock_profile = MagicMock()
+        mock_profile.model = None
+        mock_profile.system_prompt = None
+        mock_profile.mcpServers = None
+        mock_profile.permissionMode = None
+        mock_profile.claudeConfig = {"effort": "xhigh"}
+        mock_load.return_value = mock_profile
+
+        provider = ClaudeCodeProvider("tid", "sess", "win", "agent")
+        command = provider._build_claude_command()
+
+        assert "--effort xhigh" in command
+
+    @patch("cli_agent_orchestrator.providers.claude_code.load_agent_profile")
+    def test_build_command_appends_fallback_model_from_claude_config(self, mock_load):
+        mock_profile = MagicMock()
+        mock_profile.model = None
+        mock_profile.system_prompt = None
+        mock_profile.mcpServers = None
+        mock_profile.permissionMode = None
+        mock_profile.claudeConfig = {"fallback_model": "sonnet"}
+        mock_load.return_value = mock_profile
+
+        provider = ClaudeCodeProvider("tid", "sess", "win", "agent")
+        command = provider._build_claude_command()
+
+        assert "--fallback-model sonnet" in command
+
+    @patch("cli_agent_orchestrator.providers.claude_code.load_agent_profile")
+    def test_build_command_omits_effort_when_claude_config_absent(self, mock_load):
+        mock_profile = MagicMock()
+        mock_profile.model = None
+        mock_profile.system_prompt = None
+        mock_profile.mcpServers = None
+        mock_profile.permissionMode = None
+        mock_profile.claudeConfig = None
+        mock_load.return_value = mock_profile
+
+        provider = ClaudeCodeProvider("tid", "sess", "win", "agent")
+        command = provider._build_claude_command()
+
+        assert "--effort" not in command
+
+
 class TestClaudeCodeProviderPermissionMode:
 
     @patch("cli_agent_orchestrator.providers.claude_code.load_agent_profile")