Pythagora-io/gpt-pilot

11.7

Adjusted Score

11.7

Raw Score

100%

Time Factor

2026-06-18

Last Push

33.7K

Stars

Python

Language

39.2K

Lines of Code

384

Files

392

Pattern Hits

2026-07-14

Scan Date

0.01

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 3MEDIUM 30LOW 359

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 392 distinct pattern matches across 17 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers155 hits · 161 pts

Severity	File	Line	Snippet	Context
LOW	core/ui/api_server.py	511	async def _handle_current_task_status(self, message: Message, writer: asyncio.StreamWriter):	CODE
LOW	core/ui/api_server.py	600	async def _handle_start_another_task(self, message: Message, writer: asyncio.StreamWriter):	CODE
LOW	core/config/__init__.py	177	def from_provider_and_agent_configs(cls, provider: ProviderConfig, agent: AgentLLMConfig):	CODE
LOW	core/agents/mixins.py	130	async def get_relevant_files_parallel(	CODE
LOW	core/agents/convo.py	41	def _get_default_template_vars(self) -> dict:	CODE
LOW	core/agents/convo.py	55	def _serialize_prompt_context(context: dict) -> dict:	CODE
LOW	core/agents/tech_lead.py	92	def create_initial_project_epic(self):	CODE
LOW	core/agents/bug_hunter.py	82	async def get_bug_reproduction_instructions(self):	CODE
LOW	core/agents/bug_hunter.py	363	def generate_iteration_convo_so_far(self, omit_last_cycle=False):	CODE
LOW	core/agents/bug_hunter.py	400	def set_data_for_next_hunting_cycle(self, human_readable_instructions, new_status):	CODE
LOW	core/agents/problem_solver.py	49	async def generate_alternative_solutions(self):	CODE
LOW	core/agents/problem_solver.py	76	async def try_alternative_solutions(self) -> AgentResponse:	CODE
LOW	core/agents/problem_solver.py	107	async def ask_for_preferred_solution(self) -> Optional[tuple[int, str]]:	CODE
LOW	core/agents/frontend.py	33	def has_correct_num_of_backticks(response: str) -> bool:	CODE
LOW	core/agents/architect.py	237	async def check_system_dependencies(self, spec: Specification):	CODE
LOW	core/agents/orchestrator.py	345	def handle_parallel_responses(self, agent: BaseAgent, responses: List[AgentResponse]) -> AgentResponse:	CODE
LOW	core/agents/troubleshooter.py	348	def try_next_alternative_solution(self, user_feedback: str, user_feedback_qa: list[str]) -> AgentResponse:	CODE
LOW	core/agents/developer.py	121	async def breakdown_current_iteration(self) -> AgentResponse:	CODE
LOW	core/agents/spec_writer.py	63	async def initialize_spec_and_project(self) -> AgentResponse:	CODE
LOW	core/cli/helpers.py	412	def find_first_todo_task_index(tasks):	CODE
LOW	core/cli/helpers.py	849	async def list_projects_branches_states(db: SessionManager):	CODE
LOW⚡	core/state/state_manager.py	106	async def list_projects_with_branches_states(self) -> list[Project]:	CODE
LOW⚡	core/state/state_manager.py	116	async def get_branches_for_project_id(self, project_id: UUID) -> list[Branch]:	CODE
LOW⚡	core/state/state_manager.py	119	async def get_project_state_for_redo_task(self, project_state: ProjectState) -> Optional[ProjectState]:	CODE
LOW	core/state/state_manager.py	137	async def get_project_state_for_convo_id(self, convo_id) -> Optional["ProjectState"]:	CODE
LOW	core/state/state_manager.py	140	async def get_task_conversation_project_states(	CODE
LOW	core/state/state_manager.py	151	async def get_project_states_in_between(	CODE
LOW	core/state/state_manager.py	679	def get_full_parent_project_root(self) -> str:	CODE
LOW	core/state/state_manager.py	786	async def get_modified_files_with_content(self) -> list[dict]:	CODE
LOW	core/state/state_manager.py	850	async def update_implemented_pages_and_apis(self):	CODE
LOW	core/state/state_manager.py	950	async def find_backend_implementation(self, endpoint_line: str) -> dict:	CODE
LOW	core/db/models/project_state.py	370	def flag_iterations_as_modified(self):	CODE
LOW	core/db/models/project_state.py	400	def flag_knowledge_base_as_modified(self):	CODE
LOW	core/db/models/project_state.py	711	async def get_project_states_in_between(	CODE
LOW	core/db/models/project_state.py	758	async def get_task_conversation_project_states(	CODE
LOW	core/db/models/chat_convo.py	38	async def get_project_state_for_convo_id(session: AsyncSession, convo_id) -> Optional["ProjectState"]:	CODE
LOW	core/db/models/project.py	103	async def get_branches_for_project_id(session: AsyncSession, project_id: UUID) -> list["Branch"]:	CODE
LOW	core/db/models/project.py	117	async def get_all_projects_with_branches_states(session: "AsyncSession") -> list["Project"]:	CODE
LOW	core/db/models/project.py	153	def get_folder_from_project_name(name: str):	CODE
LOW	…tes/tree/vite_react/client/src/components/ui/chart.tsx	321	function getPayloadConfigFromPayload(	CODE
LOW	…/vite_react_swagger/client/src/components/ui/chart.tsx	321	function getPayloadConfigFromPayload(	CODE
LOW	tests/proc/test_process_manager.py	14	async def test_local_process_start_terminate(tmp_path):	CODE
LOW	tests/proc/test_process_manager.py	58	async def test_process_manager_run_command_capture_stdout(tmp_path):	CODE
LOW	tests/proc/test_process_manager.py	75	async def test_process_manager_run_command_capture_stderr(tmp_path):	CODE
LOW	tests/proc/test_process_manager.py	92	async def test_process_manager_start_list_terminate(tmp_path):	CODE
LOW	tests/ui/test_console.py	57	async def test_ask_question_with_buttons(mock_PromptSession):	CODE
LOW	tests/ui/test_console.py	78	async def test_ask_question_interrupted(mock_PromptSession):	CODE
LOW	tests/ui/test_ipc_client.py	193	async def test_server_closes_connection():	CODE
LOW	tests/ui/test_ipc_client.py	227	async def test_ask_question_buttons():	CODE
LOW	tests/ui/test_ipc_client.py	256	async def test_ask_question_buttons_only_with_default():	CODE
LOW	tests/ui/test_ipc_client.py	286	async def test_handle_garbage_response():	CODE
LOW	tests/llm/test_parser.py	25	def test_multi_code_block_parser(input, expected):	CODE
LOW	tests/llm/test_parser.py	123	def test_parse_json_with_spec(input, expected):	CODE
LOW	tests/llm/test_parser.py	204	def test_optional_block_parser(input, expected):	CODE
LOW	tests/llm/test_openai.py	68	async def test_openai_stream_handler(mock_AsyncOpenAI, mock_state_manager):	CODE
LOW	tests/llm/test_openai.py	98	async def test_openai_parser_with_retries(mock_AsyncOpenAI, mock_state_manager):	CODE
LOW	tests/llm/test_openai.py	179	async def test_openai_error_handler_success(mock_AsyncOpenAI, mock_state_manager):	CODE
LOW	tests/llm/test_openai.py	226	async def test_openai_error_handler_failure(mock_AsyncOpenAI, mock_state_manager):	CODE
LOW	tests/llm/test_openai.py	271	def test_openai_rate_limit_parser(	CODE
LOW	tests/llm/test_prompt.py	19	def test_jinja_string_template():	CODE
95 more matches not shown…

Excessive Try-Catch Wrapping68 hits · 80 pts

Severity	File	Line	Snippet	Context
LOW	core/ui/ipc_client.py	213	except Exception as err:	CODE
LOW	core/ui/ipc_client.py	541	except Exception:	CODE
LOW	core/ui/api_server.py	243	except Exception as e:	CODE
LOW	core/ui/api_server.py	353	except Exception as err:	CODE
LOW	core/ui/api_server.py	430	except Exception as err:	CODE
LOW	core/ui/api_server.py	445	except Exception as err:	CODE
LOW	core/ui/api_server.py	480	except Exception as err:	CODE
LOW	core/ui/api_server.py	507	except Exception as err:	CODE
LOW	core/ui/api_server.py	536	except Exception as err:	CODE
LOW	core/ui/api_server.py	596	except Exception as err:	CODE
LOW	core/ui/api_server.py	635	except Exception as e:	CODE
LOW	core/ui/api_server.py	657	except Exception as err:	CODE
LOW	core/ui/api_server.py	698	except Exception as err:	CODE
LOW	core/ui/api_server.py	731	except Exception as err:	CODE
LOW	core/ui/api_server.py	773	except Exception as err:	CODE
LOW	core/llm/parser.py	183	except Exception as err:	CODE
LOW	core/llm/base.py	318	except Exception:	CODE
LOW	core/llm/base.py	344	except Exception:	CODE
LOW	core/llm/base.py	357	except Exception as e:	CODE
LOW	core/llm/relace_client.py	56	except Exception as e:	CODE
LOW	core/agents/mixins.py	185	except Exception as e:	CODE
LOW	core/agents/git.py	64	except Exception as e:	CODE
LOW	core/agents/frontend.py	263	except Exception as e:	CODE
LOW	core/agents/frontend.py	270	except Exception as e:	CODE
LOW	core/agents/frontend.py	504	except Exception as e:	CODE
LOW	core/agents/frontend.py	510	except Exception as e:	CODE
LOW	core/agents/frontend.py	597	except Exception as e:	CODE
LOW	core/agents/wizard.py	55	except Exception as e:	CODE
LOW	core/agents/wizard.py	162	except Exception as e:	CODE
LOW	core/agents/wizard.py	167	except Exception as e:	CODE
LOW	core/agents/orchestrator.py	219	except Exception as e:	CODE
LOW	core/agents/orchestrator.py	249	except Exception as e:	CODE
LOW	core/agents/orchestrator.py	280	except Exception as e:	CODE
LOW	core/agents/orchestrator.py	303	except Exception as e:	CODE
LOW	core/agents/orchestrator.py	342	except Exception as e:	CODE
LOW	core/agents/code_monkey.py	131	except Exception:	CODE
LOW	core/utils/text.py	40	except Exception:	CODE
LOW	core/cli/main.py	98	except Exception as err:	CODE
LOW	core/cli/main.py	417	except Exception as err:	CODE
MEDIUM	core/cli/helpers.py	300	print(f"Error parsing config file {args.config}: {err}", file=sys.stderr)	CODE
MEDIUM	core/state/state_manager.py	418	def commit_with_retry(self):	CODE
LOW	core/state/state_manager.py	237	except Exception as e:	CODE
LOW	core/state/state_manager.py	242	except Exception as e:	CODE
LOW	core/state/state_manager.py	368	except Exception as e:	CODE
LOW	core/state/state_manager.py	429	except Exception as e:	CODE
LOW	core/state/state_manager.py	475	except Exception as e:	CODE
LOW	core/state/state_manager.py	509	except Exception as e:	CODE
LOW	core/state/state_manager.py	520	except Exception as e:	CODE
LOW	core/state/state_manager.py	984	except Exception as e:	CODE
MEDIUM	core/db/fix_migrations.py	29	print(f"Error updating database: {e}")	CODE
MEDIUM	core/db/fix_migrations.py	42	print(f"Error: Could not find alembic.ini at {alembic_ini}")	CODE
MEDIUM	core/db/fix_migrations.py	50	print("Error: This script only works with SQLite databases")	CODE
MEDIUM	core/db/fix_migrations.py	69	print("Error: No migration versions found")	CODE
LOW	core/db/fix_migrations.py	84	except Exception as e:	CODE
MEDIUM	core/db/fix_migrations.py	85	print(f"Error: {e}")	CODE
LOW	core/db/v0importer.py	43	except Exception as err: # noqa	CODE
MEDIUM	core/db/v0importer.py	40	def import_database(self):	CODE
LOW	core/db/models/project_state.py	704	except Exception as e:	CODE
LOW	core/templates/base.py	126	except Exception as err:	CODE
MEDIUM	core/templates/base.py	123	def install_hook_template(self) -> Any:	CODE
8 more matches not shown…

Unused Imports43 hits · 42 pts

Severity	File	Line	Context
LOW	core/config/__init__.py	256	CODE
LOW	core/agents/convo.py	15	CODE
LOW	core/agents/response.py	7	CODE
LOW	core/agents/response.py	8	CODE
LOW	core/agents/base.py	8	CODE
LOW	core/state/state_manager.py	17	CODE
LOW	core/state/state_manager.py	42	CODE
LOW	core/db/models/user_input.py	14	CODE
LOW	core/db/models/user_input.py	14	CODE
LOW	core/db/models/project_state.py	17	CODE
LOW	core/db/models/project_state.py	17	CODE
LOW	core/db/models/project_state.py	17	CODE
LOW	core/db/models/chat_message.py	9	CODE
LOW	core/db/models/__init__.py	6	CODE
LOW	core/db/models/__init__.py	7	CODE
LOW	core/db/models/__init__.py	8	CODE
LOW	core/db/models/__init__.py	9	CODE
LOW	core/db/models/__init__.py	10	CODE
LOW	core/db/models/__init__.py	11	CODE
LOW	core/db/models/__init__.py	12	CODE
LOW	core/db/models/__init__.py	13	CODE
LOW	core/db/models/__init__.py	14	CODE
LOW	core/db/models/__init__.py	15	CODE
LOW	core/db/models/__init__.py	16	CODE
LOW	core/db/models/__init__.py	17	CODE
LOW	core/db/models/__init__.py	17	CODE
LOW	core/db/models/__init__.py	18	CODE
LOW	core/db/models/branch.py	12	CODE
LOW	core/db/models/branch.py	14	CODE
LOW	core/db/models/branch.py	14	CODE
LOW	core/db/models/branch.py	14	CODE
LOW	core/db/models/branch.py	14	CODE
LOW	core/db/models/file.py	6	CODE
LOW	core/db/models/file.py	12	CODE
LOW	core/db/models/file.py	12	CODE
LOW	core/db/models/exec_log.py	13	CODE
LOW	core/db/models/exec_log.py	13	CODE
LOW	core/db/models/llm_request.py	14	CODE
LOW	core/db/models/llm_request.py	15	CODE
LOW	core/db/models/llm_request.py	15	CODE
LOW	core/templates/render.py	1	CODE
LOW	core/templates/base.py	13	CODE
LOW	core/templates/base.py	14	CODE

Deep Nesting32 hits · 31 pts

Severity	File	Line	Context
LOW	core/proc/process_manager.py	171	CODE
LOW	core/ui/api_server.py	540	CODE
LOW	core/llm/base.py	124	CODE
LOW	core/llm/base.py	416	CODE
LOW	core/config/env_importer.py	44	CODE
LOW	core/agents/tech_lead.py	146	CODE
LOW	core/agents/tech_lead.py	371	CODE
LOW	core/agents/bug_hunter.py	61	CODE
LOW	core/agents/bug_hunter.py	241	CODE
LOW	core/agents/frontend.py	44	CODE
LOW	core/agents/frontend.py	151	CODE
LOW	core/agents/frontend.py	356	CODE
LOW	core/agents/frontend.py	451	CODE
LOW	core/agents/wizard.py	30	CODE
LOW	core/agents/wizard.py	133	CODE
LOW	core/agents/orchestrator.py	370	CODE
LOW	core/agents/orchestrator.py	463	CODE
LOW	core/agents/orchestrator.py	554	CODE
LOW	core/agents/troubleshooter.py	244	CODE
LOW	core/agents/developer.py	121	CODE
LOW	core/cli/helpers.py	437	CODE
LOW	core/cli/helpers.py	481	CODE
LOW	core/cli/helpers.py	583	CODE
LOW	core/state/state_manager.py	172	CODE
LOW	core/state/state_manager.py	272	CODE
LOW	core/db/models/project_state.py	592	CODE
LOW	core/db/models/project_state.py	631	CODE
LOW	core/db/models/project_state.py	758	CODE
LOW	core/db/models/project_state.py	976	CODE
LOW	core/db/models/file.py	46	CODE
LOW	core/templates/render.py	71	CODE
LOW	core/log/__init__.py	30	CODE

Modern Structural Boilerplate25 hits · 24 pts

Severity	File	Line	Snippet	Context
LOW	core/proc/exec_log.py	21	__all__ = ["ExecLog"]	CODE
LOW	core/ui/ipc_client.py	690	__all__ = ["IPCClientUI"]	CODE
LOW	core/ui/console.py	272	__all__ = ["PlainConsoleUI"]	CODE
LOW	core/ui/virtual.py	253	__all__ = ["VirtualUI"]	CODE
LOW	core/ui/base.py	573	__all__ = [	CODE
LOW	core/llm/convo.py	170	__all__ = ["Convo"]	CODE
LOW	core/llm/groq_client.py	93	__all__ = ["GroqClient"]	CODE
LOW	core/llm/prompt.py	48	__all__ = ["FormatTemplate", "JinjaStringTemplate", "JinjaFileTemplate"]	CODE
LOW	core/llm/request_log.py	30	__all__ = ["LLMRequestLog", "LLMRequestStatus"]	CODE
LOW	core/llm/openai_client.py	120	__all__ = ["OpenAIClient"]	CODE
LOW	core/llm/anthropic_client.py	154	__all__ = ["AnthropicClient"]	CODE
LOW	core/llm/base.py	459	__all__ = ["BaseLLMClient"]	CODE
LOW	core/llm/relace_client.py	62	__all__ = ["RelaceClient"]	CODE
LOW	core/config/user_settings.py	94	__all__ = ["settings"]	CODE
LOW	core/config/version.py	110	__all__ = ["get_version", "get_git_branch"]	CODE
LOW	core/config/__init__.py	544	__all__ = ["loader", "get_config"]	CODE
LOW	core/cli/helpers.py	955	__all__ = [	CODE
LOW	core/state/state_manager.py	1046	__all__ = ["StateManager"]	CODE
LOW	core/db/session.py	76	__all__ = ["SessionManager"]	CODE
LOW	core/db/setup.py	49	__all__ = ["run_migrations"]	CODE
LOW	core/db/models/__init__.py	20	__all__ = [	CODE
LOW	core/log/__init__.py	111	__all__ = ["setup", "get_logger"]	CODE
LOW	core/disk/ignore.py	125	__all__ = ["IgnoreMatcher"]	CODE
LOW	core/disk/vfs.py	188	__all__ = ["VirtualFileSystem", "MemoryVFS", "LocalDiskVFS"]	CODE
LOW	core/telemetry/__init__.py	400	__all__ = ["telemetry"]	CODE

Redundant / Tautological Comments14 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW	core/ui/api_server.py	202	# Check if convo exists for this convo id	COMMENT
LOW	core/ui/api_server.py	213	# Check if any ChatMessages exists with the convo id	COMMENT
LOW	core/agents/git.py	99	# Check if there are any changes to commit	COMMENT
LOW	core/agents/orchestrator.py	187	# Check if file exists	COMMENT
LOW	core/agents/orchestrator.py	196	# Check if script already exists	COMMENT
LOW	core/agents/orchestrator.py	269	# Check if favicon link already exists	COMMENT
LOW	core/agents/orchestrator.py	318	# Check if required configs already exist	COMMENT
LOW	core/agents/spec_writer.py	70	# Check if initial_prompt is provided in command line arguments	COMMENT
LOW	core/cli/main.py	131	# Check if initial_prompt is provided, if so, automatically select "node"	COMMENT
LOW	core/state/state_manager.py	859	# Check if pages or apis have changed	COMMENT
LOW	core/templates/tree/add_raw_tags.py	8	# Open the file and read the contents	COMMENT
LOW	core/templates/tree/add_raw_tags.py	12	# Check if the tags are already present	COMMENT
LOW⚡	core/templates/tree/add_raw_tags.py	42	# Check if the directory path argument is provided	COMMENT
LOW⚡	core/templates/tree/add_raw_tags.py	50	# Check if the provided directory exists	COMMENT

Dead Code10 hits · 20 pts

Severity	File	Line	Context
MEDIUM	core/agents/external_docs.py	50	CODE
MEDIUM	core/agents/external_docs.py	56	CODE
MEDIUM	core/agents/external_docs.py	57	CODE
MEDIUM	core/agents/external_docs.py	59	CODE
MEDIUM	core/agents/external_docs.py	64	CODE
MEDIUM	core/agents/external_docs.py	65	CODE
MEDIUM	core/agents/external_docs.py	66	CODE
MEDIUM	core/agents/external_docs.py	67	CODE
MEDIUM	core/agents/external_docs.py	69	CODE
MEDIUM	core/agents/external_docs.py	70	CODE

Self-Referential Comments6 hits · 18 pts

Severity	File	Line	Snippet	Context
MEDIUM	core/llm/parser.py	186	# Create a new model that includes the original model fields and the original text	COMMENT
MEDIUM	core/agents/wizard.py	113	# Create a new knowledge base instance for the project state	COMMENT
MEDIUM	core/db/models/project_state.py	411	# Create a new knowledge base instance with the current data	COMMENT
MEDIUM	tests/cli/test_cli.py	308	# Create a mock with a string value for the button attribute	COMMENT
MEDIUM	tests/cli/test_cli.py	341	# Create a mock response with a string value for the button attribute	COMMENT
MEDIUM	tests/state/test_state_manager.py	143	# Create an instance of StateManager with mocked UI	COMMENT

Fake / Example Data14 hits · 15 pts

Severity	File	Line	Snippet	Context
LOW	tests/ui/test_ipc_client.py	108	"placeholder": None,	CODE
LOW	tests/ui/test_ipc_client.py	120	"placeholder": None,	CODE
LOW	tests/ui/test_ipc_client.py	152	"placeholder": None,	CODE
LOW	tests/ui/test_ipc_client.py	164	"placeholder": None,	CODE
LOW	tests/ui/test_ipc_client.py	176	"placeholder": None,	CODE
LOW⚡	tests/llm/test_convo.py	88	convo.user("Hello, World!", "John Doe")	CODE
LOW⚡	tests/llm/test_convo.py	92	"name": "John Doe",	CODE
LOW	tests/integration/llm/test_anthropic.py	113	large_convo = " ".join(["lorem ipsum dolor sit amet"] * 60000)	CODE
LOW	tests/integration/llm/test_anthropic.py	113	large_convo = " ".join(["lorem ipsum dolor sit amet"] * 60000)	CODE
LOW	tests/integration/llm/test_openai.py	116	large_convo = " ".join(["lorem ipsum dolor sit amet"] * 30000)	CODE
LOW	tests/integration/llm/test_openai.py	116	large_convo = " ".join(["lorem ipsum dolor sit amet"] * 30000)	CODE
LOW	tests/integration/llm/test_groq.py	118	large_convo = " ".join(["lorem ipsum dolor sit amet"] * 30000)	CODE
LOW	tests/integration/llm/test_groq.py	118	large_convo = " ".join(["lorem ipsum dolor sit amet"] * 30000)	CODE
LOW	tests/telemetry/test_telemetry.py	36	"user_contact": "user@example.com",	CODE

Magic Placeholder Names2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	example-config.json	16	"api_key": "your-api-key",	CODE
HIGH	example-config.json	23	"api_key": "your-api-key",	CODE

Over-Commented Block10 hits · 10 pts

Severity	File	Line	Snippet	Context
LOW	core/llm/base.py	301	# Token limit exceeded (in original gpt-pilot handled as	COMMENT
LOW	core/agents/tech_lead.py	61	if len(self.current_state.epics) == 1:	COMMENT
LOW	core/agents/architect.py	141	"select_templates",	COMMENT
LOW	core/db/alembic.ini	1	# A generic, single database configuration.	COMMENT
LOW	core/db/alembic.ini	21	# string value is passed to ZoneInfo()	COMMENT
LOW	core/db/alembic.ini	41	# The path separator used here should be the separator specified by "version_path_separator" below.	COMMENT
LOW	core/db/alembic.ini	61	# are written from script.py.mako	COMMENT
LOW	core/telemetry/__init__.py	141	# End result of development:	COMMENT
LOW	tests/db/test_db.py	61	# this assertion would fail with an ORM exception, unless we add	COMMENT
LOW	cloud/entrypoint.sh	1	#!/bin/bash	COMMENT

Decorative Section Separators2 hits · 6 pts

Severity	File	Line	Snippet	Context
MEDIUM	core/agents/code_monkey.py	209	# ------------------------------	COMMENT
MEDIUM	core/agents/code_monkey.py	211	# ------------------------------	COMMENT

AI Structural Patterns5 hits · 5 pts

Severity	File	Line	Context
LOW	core/ui/ipc_client.py	316	CODE
LOW	core/ui/console.py	86	CODE
LOW	core/ui/virtual.py	81	CODE
LOW	core/ui/base.py	220	CODE
LOW	core/agents/base.py	70	CODE

Cross-Language Confusion1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	core/agents/git.py	129	"git diff --cached \|\| git diff",	CODE

Slop Phrases2 hits · 4 pts

Severity	File	Line	Snippet	Context
MEDIUM	core/llm/base.py	366	"Here's how you can get Pythagora to ignore those extra files: ",	CODE
LOW	core/agents/troubleshooter.py	241	# Sometimes LLM can return a non-existent file, let's make sure to filter those out	COMMENT

TODO Padding2 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	core/agents/orchestrator.py	84	# TODO: consider refactoring this into two loop; the outer with one iteration per committed step,	COMMENT
LOW	core/state/state_manager.py	565	# TODO: implement this	COMMENT

AI Slop Vocabulary1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	core/ui/api_server.py	541	# if the extension sent "add", just add a new task in the tasks array before the first todo task	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings