diff --git a/CLAUDE.md b/CLAUDE.md
index e6ec26d..830a2de 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -72,7 +72,7 @@ Async SQLAlchemy + aiosqlite. `MemoryStore`: schema init (+ lightweight SQLite `
 - **`/compact`**: soft-compact tool dumps → model summary (no tools) → **new** session seeded with summary message. Soft-compact keeps the last **12** tool results full-size by default (`DEFAULT_RECENT_TOOL_RESULTS`); older tool payloads shrink first.
 - Events: text_delta, **reasoning_delta**, assistant_message, tool_call/result, max_rounds, **error** (`retryable`/`source`), **cancelled** (`reason`), **usage** (`TokenUsage`).
 - Usage: API `usage` from completions (stream with `include_usage`); **char≈token fallback** (~4 chars/token) when omitted; **context size** = last request ``prompt_tokens`` (API preferred); `last_turn_usage` / `session_usage` are **billed sums** (tool rounds re-send history); CLI end-of-turn + `/status`.
-- Config ``[agent]``: `system_prompt` (default: built-in coding-agent guide `DEFAULT_SYSTEM_PROMPT`; `""` disables), `max_tool_result_chars`, `parallel_tools`, `confirm_destructive`, `path_denylist`, `max_context_tokens` (default 200k est. tokens).
+- Config ``[agent]``: `system_prompt` (persona; default `DEFAULT_SYSTEM_PROMPT`; `""` omits persona), `tool_directives` (tool playbook; default `DEFAULT_TOOL_DIRECTIVES`; `""` omits playbook; both empty → no system), `max_tool_result_chars`, `parallel_tools`, `confirm_destructive`, `path_denylist`, `max_context_tokens` (default 200k est. tokens).
 
 ### Tools (`tools/`)
 
diff --git a/README.md b/README.md
index 6047e71..db9f79f 100644
--- a/README.md
+++ b/README.md
@@ -136,10 +136,11 @@ access_key_or_token = "sk-..."
 "gpt-4o-mini" = { text = true }
 
 [agent]
-# system_prompt defaults to a built-in coding-agent guide (omit to use it).
-# system_prompt = ""   # disable
+# system_prompt = persona (omit → built-in). tool_directives = tool playbook.
+# system_prompt = "" / tool_directives = "" disable each part; both "" → no system.
 # Or multi-line override (prefer '''...'''):
-# system_prompt = '''Your custom prompt...'''
+# system_prompt = '''Your custom persona...'''
+# tool_directives = '''### Workspace ...'''
 confirm_destructive = true
 max_context_tokens = 200000
 ```
diff --git a/doc/plyngent.example.toml b/doc/plyngent.example.toml
index 3f36f1a..2b894b0 100644
--- a/doc/plyngent.example.toml
+++ b/doc/plyngent.example.toml
@@ -11,12 +11,17 @@
 # # url = ":memory:"
 
 [agent]
-# system_prompt defaults to the built-in coding-agent guide when omitted.
-# Override with a multi-line literal (prefer ''' so nested " is fine):
+# Persona (omit → built-in coding-agent line). tool_directives is the tool playbook.
+# Override with multi-line literals (prefer ''' so nested " is fine):
 # system_prompt = '''
-# Your custom system prompt...
+# Your custom persona...
 # '''
-# system_prompt = ""   # disable system prompt entirely
+# tool_directives = '''
+# ### Workspace
+# ...
+# '''
+# system_prompt = ""       # persona off; keep default tool_directives unless also cleared
+# tool_directives = ""     # playbook off (set both "" to disable system entirely)
 max_tool_result_chars = 32000
 parallel_tools = true
 confirm_destructive = true
diff --git a/src/plyngent/cli/editor.py b/src/plyngent/cli/editor.py
index 0f1681c..bff7548 100644
--- a/src/plyngent/cli/editor.py
+++ b/src/plyngent/cli/editor.py
@@ -29,8 +29,9 @@ _MINIMAL_CONFIG = """\
 # # url = ":memory:"
 
 # [agent]
-# # system_prompt defaults to the built-in coding-agent guide when omitted.
-# # system_prompt = ""  # disable; or multi-line '''...''' to override
+# # system_prompt = persona (omit → built-in). tool_directives = tool playbook.
+# # system_prompt = "" / tool_directives = "" disable each part; both "" → no system.
+# # Or multi-line '''...''' to override.
 # max_tool_result_chars = 32000
 # parallel_tools = true
 # confirm_destructive = true
diff --git a/src/plyngent/cli/state.py b/src/plyngent/cli/state.py
index 13a9621..93c9306 100644
--- a/src/plyngent/cli/state.py
+++ b/src/plyngent/cli/state.py
@@ -169,9 +169,13 @@ class ReplState:
 
     def _make_agent(self) -> ChatAgent:
         from plyngent.cli.limits import prompt_continue_limit_async
+        from plyngent.config import compose_agent_system_content
 
         agent_cfg = self.config.agent_config
-        system_prompt = agent_cfg.system_prompt or None
+        system_prompt = compose_agent_system_content(
+            agent_cfg.system_prompt,
+            agent_cfg.tool_directives,
+        )
         on_limit = prompt_continue_limit_async if self.interactive_limits else None
         return ChatAgent(
             self.client,
diff --git a/src/plyngent/config/__init__.py b/src/plyngent/config/__init__.py
index fe8ddad..19fa9f2 100644
--- a/src/plyngent/config/__init__.py
+++ b/src/plyngent/config/__init__.py
@@ -6,6 +6,7 @@ import tomlkit
 from tomlkit.exceptions import TOMLKitError
 
 from .models import DEFAULT_SYSTEM_PROMPT as DEFAULT_SYSTEM_PROMPT
+from .models import DEFAULT_TOOL_DIRECTIVES as DEFAULT_TOOL_DIRECTIVES
 from .models import AgentConfig as AgentConfig
 from .models import AnthropicProvider as AnthropicProvider
 from .models import DatabaseConfig as DatabaseConfig
@@ -15,6 +16,7 @@ from .models import ModelConfig as ModelConfig
 from .models import OpenAICompatibleProvider as OpenAICompatibleProvider
 from .models import OpenAIProvider as OpenAIProvider
 from .models import ProviderConfig as ProviderConfig
+from .models import compose_agent_system_content as compose_agent_system_content
 from .path import get_default_path as _get_default_path
 from .store import ConfigFormatError as ConfigFormatError
 from .store import ConfigStore as ConfigStore
diff --git a/src/plyngent/config/models.py b/src/plyngent/config/models.py
index 7b29a97..28b944a 100644
--- a/src/plyngent/config/models.py
+++ b/src/plyngent/config/models.py
@@ -2,12 +2,16 @@ from typing import Any
 
 from msgspec import Struct, field
 
-# Built-in agent system prompt when ``[agent].system_prompt`` is omitted.
-# Set ``system_prompt = ""`` in TOML to disable. Override with a multi-line
-# TOML literal (prefer '''...''' so nested " quotes are fine).
+# Built-in persona when ``[agent].system_prompt`` is omitted.
+# Set ``system_prompt = ""`` to omit the persona block only.
+# Override with a multi-line TOML literal (prefer ''' so nested " is fine).
 DEFAULT_SYSTEM_PROMPT = """\
 You are a professional coding agent in a workspace-bound tool environment.
+"""
 
+# Built-in tool playbook when ``[agent].tool_directives`` is omitted.
+# Set ``tool_directives = ""`` to omit this block only.
+DEFAULT_TOOL_DIRECTIVES = """\
 ### Workspace
 - Explore with `tree`/`listdir`/`glob_paths`/`grep_files`/`read_file` when unsure.
 - Stay under the workspace (or a path from `new_temporary_workspace`). Respect path denylists.
@@ -41,6 +45,21 @@ pop the group). Open items mean unfinished work.
 """
 
 
+def compose_agent_system_content(
+    system_prompt: str,
+    tool_directives: str,
+) -> str | None:
+    """Join persona + tool playbook into one system body, or ``None`` if both empty.
+
+    Non-empty parts are stripped and joined with a blank line. Either field may
+    be ``""`` to disable that part while keeping the other.
+    """
+    parts = [part.strip() for part in (system_prompt, tool_directives) if part and part.strip()]
+    if not parts:
+        return None
+    return "\n\n".join(parts)
+
+
 class DatabaseConfig(Struct, omit_defaults=True):
     """Database connection configuration.
 
@@ -58,7 +77,10 @@ class DatabaseConfig(Struct, omit_defaults=True):
 class AgentConfig(Struct, omit_defaults=True):
     """Single-user agent profile defaults."""
 
+    # Persona / role (omit → DEFAULT_SYSTEM_PROMPT; "" disables persona only).
     system_prompt: str = DEFAULT_SYSTEM_PROMPT
+    # Tool how-to (omit → DEFAULT_TOOL_DIRECTIVES; "" disables playbook only).
+    tool_directives: str = DEFAULT_TOOL_DIRECTIVES
     max_tool_result_chars: int = 32_000
     parallel_tools: bool = True
     confirm_destructive: bool = True
diff --git a/tests/test_config/test_agent_section.py b/tests/test_config/test_agent_section.py
index 054cc39..f625878 100644
--- a/tests/test_config/test_agent_section.py
+++ b/tests/test_config/test_agent_section.py
@@ -2,7 +2,12 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING
 
-from plyngent.config import DEFAULT_SYSTEM_PROMPT, load
+from plyngent.config import (
+    DEFAULT_SYSTEM_PROMPT,
+    DEFAULT_TOOL_DIRECTIVES,
+    compose_agent_system_content,
+    load,
+)
 
 if TYPE_CHECKING:
     from pathlib import Path
@@ -13,7 +18,9 @@ def test_agent_section_defaults(tmp_path: Path) -> None:
     _ = path.write_text("", encoding="utf-8")
     store = load(path)
     assert store.agent_config.system_prompt == DEFAULT_SYSTEM_PROMPT
+    assert store.agent_config.tool_directives == DEFAULT_TOOL_DIRECTIVES
     assert "professional coding agent" in store.agent_config.system_prompt
+    assert "### Workspace" in store.agent_config.tool_directives
     assert store.agent_config.max_tool_result_chars == 32_000
     assert store.agent_config.parallel_tools is True
     assert store.agent_config.confirm_destructive is True
@@ -21,12 +28,31 @@ def test_agent_section_defaults(tmp_path: Path) -> None:
     assert store.agent_config.max_context_tokens == 200_000
 
 
+def test_compose_defaults_join_persona_and_directives() -> None:
+    body = compose_agent_system_content(DEFAULT_SYSTEM_PROMPT, DEFAULT_TOOL_DIRECTIVES)
+    assert body is not None
+    assert body.startswith("You are a professional coding agent")
+    assert "\n\n### Workspace" in body
+    assert "### Todos" in body
+    # No double-blank-line collapse issues between parts.
+    assert "\n\n\n" not in body
+
+
+def test_compose_empty_combinations() -> None:
+    assert compose_agent_system_content("", "") is None
+    assert compose_agent_system_content("  ", "\n") is None
+    assert compose_agent_system_content("Only persona", "") == "Only persona"
+    assert compose_agent_system_content("", "Only tools") == "Only tools"
+    assert compose_agent_system_content("Persona", "Tools") == "Persona\n\nTools"
+
+
 def test_agent_section_parse(tmp_path: Path) -> None:
     path = tmp_path / "c.toml"
     _ = path.write_text(
         """
 [agent]
 system_prompt = "Be brief."
+tool_directives = "Use tools carefully."
 max_tool_result_chars = 100
 parallel_tools = false
 confirm_destructive = false
@@ -37,14 +63,20 @@ max_context_tokens = 5000
     )
     store = load(path)
     assert store.agent_config.system_prompt == "Be brief."
+    assert store.agent_config.tool_directives == "Use tools carefully."
     assert store.agent_config.max_tool_result_chars == 100
     assert store.agent_config.parallel_tools is False
     assert store.agent_config.confirm_destructive is False
     assert store.agent_config.path_denylist == ["/secrets/", ".ssh/"]
     assert store.agent_config.max_context_tokens == 5000
+    composed = compose_agent_system_content(
+        store.agent_config.system_prompt,
+        store.agent_config.tool_directives,
+    )
+    assert composed == "Be brief.\n\nUse tools carefully."
 
 
-def test_agent_system_prompt_empty_disables(tmp_path: Path) -> None:
+def test_agent_system_prompt_empty_disables_persona_only(tmp_path: Path) -> None:
     path = tmp_path / "c.toml"
     _ = path.write_text(
         """
@@ -55,3 +87,52 @@ system_prompt = ""
     )
     store = load(path)
     assert store.agent_config.system_prompt == ""
+    assert store.agent_config.tool_directives == DEFAULT_TOOL_DIRECTIVES
+    body = compose_agent_system_content(
+        store.agent_config.system_prompt,
+        store.agent_config.tool_directives,
+    )
+    assert body is not None
+    assert "### Workspace" in body
+    assert "professional coding agent" not in body
+
+
+def test_agent_tool_directives_empty_disables_playbook_only(tmp_path: Path) -> None:
+    path = tmp_path / "c.toml"
+    _ = path.write_text(
+        """
+[agent]
+tool_directives = ""
+""",
+        encoding="utf-8",
+    )
+    store = load(path)
+    assert store.agent_config.tool_directives == ""
+    assert store.agent_config.system_prompt == DEFAULT_SYSTEM_PROMPT
+    body = compose_agent_system_content(
+        store.agent_config.system_prompt,
+        store.agent_config.tool_directives,
+    )
+    assert body is not None
+    assert "professional coding agent" in body
+    assert "### Workspace" not in body
+
+
+def test_agent_both_empty_disables_system(tmp_path: Path) -> None:
+    path = tmp_path / "c.toml"
+    _ = path.write_text(
+        """
+[agent]
+system_prompt = ""
+tool_directives = ""
+""",
+        encoding="utf-8",
+    )
+    store = load(path)
+    assert (
+        compose_agent_system_content(
+            store.agent_config.system_prompt,
+            store.agent_config.tool_directives,
+        )
+        is None
+    )