core/config: default system prompt for coding agent tools

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`, `max_tool_result_chars`, `parallel_tools`, `confirm_destructive`, `path_denylist`, `max_context_tokens` (default 200k est. tokens).
+- 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).
 
 ### Tools (`tools/`)
 

README.md

@@ -136,7 +136,10 @@ access_key_or_token = "sk-..."
 "gpt-4o-mini" = { text = true }
 
 [agent]
-system_prompt = "You are a careful coding assistant."
+# system_prompt defaults to a built-in coding-agent guide (omit to use it).
+# system_prompt = ""   # disable
+# Or multi-line override (prefer '''...'''):
+# system_prompt = '''Your custom prompt...'''
 confirm_destructive = true
 max_context_tokens = 200000
 ```

doc/plyngent.example.toml

@@ -11,7 +11,12 @@
 # # url = ":memory:"
 
 [agent]
-system_prompt = "You are a careful coding assistant. Prefer small, verified edits."
+# system_prompt defaults to the built-in coding-agent guide when omitted.
+# Override with a multi-line literal (prefer ''' so nested " is fine):
+# system_prompt = '''
+# Your custom system prompt...
+# '''
+# system_prompt = ""   # disable system prompt entirely
 max_tool_result_chars = 32000
 parallel_tools = true
 confirm_destructive = true

src/plyngent/cli/editor.py

@@ -29,7 +29,8 @@ _MINIMAL_CONFIG = """\
 # # url = ":memory:"
 
 # [agent]
-# system_prompt = "You are a careful coding assistant."
+# # system_prompt defaults to the built-in coding-agent guide when omitted.
+# # system_prompt = ""  # disable; or multi-line '''...''' to override
 # max_tool_result_chars = 32000
 # parallel_tools = true
 # confirm_destructive = true

src/plyngent/config/__init__.py

@@ -5,6 +5,7 @@ from typing import TYPE_CHECKING
 import tomlkit
 from tomlkit.exceptions import TOMLKitError
 
+from .models import DEFAULT_SYSTEM_PROMPT as DEFAULT_SYSTEM_PROMPT
 from .models import AgentConfig as AgentConfig
 from .models import AnthropicProvider as AnthropicProvider
 from .models import DatabaseConfig as DatabaseConfig

src/plyngent/config/models.py

@@ -2,6 +2,44 @@ 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).
+DEFAULT_SYSTEM_PROMPT = """\
+You are a professional coding agent in a workspace-bound tool environment.
+
+### 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.
+
+### Files
+- Prefer file tools over shell. `edit_replace` fails usually means a bad match — \
+fix `old_string` or `max_replaces`; shell workarounds rarely help.
+- `edit_replace` defaults to the first match; if remaining matches are reported, \
+raise `max_replaces` or narrow `old_string`.
+- Before `edit_lineno`, `read_file` with `with_lineno=true`.
+
+### Commands
+- Prefer `run_command` / `run_command_batch` (argv, no shell) over `bash -c` or similar.
+- Several `run_command` calls in one step may run in parallel; use `run_command_batch` \
+for ordered pipelines (`pipe_out` / `mix_stderr` as needed).
+- Prefer `vcs_*` for status/diff/log/branch when enough.
+
+### Humans & safety
+- Prefer `ask_user_line` / `ask_user_choice` / `ask_user_form` over waiting for the next free-form turn.
+- Overwrites, deletes, shells, and risky ops may require human confirm; hard denylists are not skipped by YOLO.
+- Temporary scratch: `new_temporary_workspace`.
+
+### PTY
+- Use PTY for interactive/TUI, sudo, ssh, or live servers.
+- Passwords and other secret input: only `ask_into_pty` (never echo secrets into `write_pty`).
+- Control keys: `write_pty_keys`, not literal `write_pty` data.
+
+### Todos
+- Use the todo stack for multi-step work (LIFO groups: push related items, finish/update, \
+pop the group). Open items mean unfinished work.
+"""
+
 
 class DatabaseConfig(Struct, omit_defaults=True):
     """Database connection configuration.
@@ -20,7 +58,7 @@ class DatabaseConfig(Struct, omit_defaults=True):
 class AgentConfig(Struct, omit_defaults=True):
     """Single-user agent profile defaults."""
 
-    system_prompt: str = ""
+    system_prompt: str = DEFAULT_SYSTEM_PROMPT
     max_tool_result_chars: int = 32_000
     parallel_tools: bool = True
     confirm_destructive: bool = True

tests/test_config/test_agent_section.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING
 
-from plyngent.config import load
+from plyngent.config import DEFAULT_SYSTEM_PROMPT, load
 
 if TYPE_CHECKING:
     from pathlib import Path
@@ -12,7 +12,8 @@ def test_agent_section_defaults(tmp_path: Path) -> None:
     path = tmp_path / "c.toml"
     _ = path.write_text("", encoding="utf-8")
     store = load(path)
-    assert store.agent_config.system_prompt == ""
+    assert store.agent_config.system_prompt == DEFAULT_SYSTEM_PROMPT
+    assert "professional coding agent" in store.agent_config.system_prompt
     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
@@ -41,3 +42,16 @@ max_context_tokens = 5000
     assert store.agent_config.confirm_destructive is False
     assert store.agent_config.path_denylist == ["/secrets/", ".ssh/"]
     assert store.agent_config.max_context_tokens == 5000
+
+
+def test_agent_system_prompt_empty_disables(tmp_path: Path) -> None:
+    path = tmp_path / "c.toml"
+    _ = path.write_text(
+        """
+[agent]
+system_prompt = ""
+""",
+        encoding="utf-8",
+    )
+    store = load(path)
+    assert store.agent_config.system_prompt == ""