abi/screenshot-to-code

11.9

Adjusted Score

11.9

Raw Score

100%

Time Factor

2026-07-13

Last Push

73.3K

Stars

Python

Language

39.6K

Lines of Code

263

Files

408

Pattern Hits

2026-07-14

Scan Date

0.00

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 1MEDIUM 16LOW 391

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 408 distinct pattern matches across 11 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 Identifiers255 hits · 271 pts

Severity	File	Line	Snippet	Context
LOW	design-docs/commits-and-variants.md	120	async def process_variant_completion(index: int, task: asyncio.Task):	CODE
LOW	frontend/src/components/settings/GenerationSettings.tsx	33	function setSelectedDesignSystemId(id: string \| null) {	CODE
LOW	…c/components/select-and-edit/SelectAndEditControls.tsx	7	export function SelectAndEditToolbarButton() {	CODE
LOW	frontend/src/components/select-and-edit/utils.ts	39	export function buildSelectedElementInstruction(	CODE
LOW	…omponents/select-and-edit/useEscapeToExitSelectMode.ts	6	export function useEscapeToExitSelectMode() {	CODE
LOW	frontend/src/components/agent/AgentActivity.tsx	80	function formatVariantWallClockDuration(	CODE
LOW	frontend/src/components/agent/AgentActivity.tsx	103	function getExtractedAssetPreviewUrl(asset: unknown): string \| null {	CODE
LOW	frontend/src/components/agent/AgentActivity.tsx	115	function isSuccessfulExtractedAsset(asset: unknown): boolean {	CODE
LOW	…tend/src/components/unified-input/UnifiedInputPane.tsx	47	function setSelectedDesignSystemId(id: string \| null) {	CODE
LOW	frontend/src/components/preview/download.ts	15	function filenameFromContentDisposition(contentDisposition: string \| null) {	CODE
LOW	frontend/src/lib/design-systems.ts	46	export function createHttpDesignSystemsRequest(	CODE
LOW	frontend/src/lib/design-systems.ts	67	export function createDesignSystemsClient(	CODE
LOW	frontend/src/lib/prompt-history.ts	65	export function resolveAssetIdsToDataUrls(	CODE
LOW	frontend/src/lib/prompt-history.ts	100	export function buildAssistantHistoryMessage(	CODE
LOW	backend/asset_extraction.py	23	def _data_url_to_source_image(data_url: str) -> SourceImage \| None:	CODE
LOW	backend/asset_extraction.py	150	async def extract_assets_from_images(	STRING
LOW	backend/llm.py	127	def get_openai_reasoning_effort(model: Llm) -> str \| None:	CODE
LOW	backend/main.py	32	async def probe_screenshot_preview_on_startup() -> None:	CODE
LOW	backend/video/utils.py	21	def get_video_bytes_and_mime_type(video_data_url: str) -> tuple[bytes, str]:	CODE
LOW	backend/evals/runner.py	17	def normalize_local_asset_urls(html: str) -> str:	CODE
LOW	backend/evals/runner.py	50	def get_eval_output_subfolder(stack: Stack, model: str) -> str:	CODE
LOW	backend/uploaded_assets/store.py	38	def configure_uploaded_asset_routes(app: FastAPI) -> None:	CODE
LOW	backend/uploaded_assets/store.py	43	def infer_local_asset_base_url(websocket: WebSocket) -> str:	CODE
LOW	backend/uploaded_assets/store.py	83	def _content_type_for_extension(extension: str) -> str:	CODE
LOW	backend/uploaded_assets/store.py	208	def persist_data_url_as_temporary_asset(	CODE
LOW	backend/uploaded_assets/store.py	240	async def persist_data_url_as_asset(	CODE
LOW	backend/uploaded_assets/store.py	261	async def promote_temporary_asset_id(	CODE
LOW	backend/uploaded_assets/tools.py	49	def summarize_save_assets_input(args: Dict[str, Any]) -> Dict[str, Any]:	CODE
LOW	backend/uploaded_assets/prompts.py	41	def append_uploaded_asset_ids_to_prompt(	STRING
LOW	backend/uploaded_assets/prompts.py	52	def append_uploaded_asset_ids_to_history(	STRING
LOW	backend/tests/test_status_broadcast.py	15	async def test_video_update_broadcasts_two_variants() -> None:	CODE
LOW	backend/tests/test_status_broadcast.py	68	async def test_image_update_broadcasts_two_variants() -> None:	CODE
LOW⚡	backend/tests/test_screenshot.py	8	def test_url_without_protocol(self):	CODE
LOW⚡	backend/tests/test_screenshot.py	14	def test_url_with_http_protocol(self):	CODE
LOW⚡	backend/tests/test_screenshot.py	19	def test_url_with_https_protocol(self):	CODE
LOW⚡	backend/tests/test_screenshot.py	24	def test_url_with_path_and_params(self):	CODE
LOW	backend/tests/test_websocket_communicator.py	11	async def test_send_message_ignores_already_completed_websocket() -> None:	CODE
LOW	backend/tests/test_websocket_communicator.py	28	async def test_receive_params_marks_websocket_closed_on_disconnect() -> None:	CODE
LOW	backend/tests/test_websocket_communicator.py	40	async def test_close_ignores_already_completed_websocket() -> None:	CODE
LOW	backend/tests/test_websocket_communicator.py	57	async def test_throw_error_ignores_already_completed_websocket() -> None:	CODE
LOW	backend/tests/test_design_systems.py	18	async def test_design_system_crud_persists_to_backend_file(	CODE
LOW	backend/tests/test_openai_input_compare.py	9	def test_compare_openai_inputs_returns_none_for_identical_inputs() -> None:	CODE
LOW	backend/tests/test_openai_input_compare.py	26	def test_compare_openai_inputs_finds_first_different_block_and_field() -> None:	CODE
LOW	backend/tests/test_openai_input_compare.py	70	def test_compare_openai_inputs_accepts_raw_input_arrays() -> None:	CODE
LOW	backend/tests/test_capabilities.py	8	async def test_capabilities_reports_screenshot_preview_available(	CODE
LOW	backend/tests/test_capabilities.py	22	async def test_capabilities_reports_screenshot_preview_unavailable(	CODE
LOW	backend/tests/test_request_parsing.py	4	def test_parse_prompt_content_with_valid_data() -> None:	CODE
LOW	backend/tests/test_request_parsing.py	20	def test_parse_prompt_content_filters_invalid_media_types() -> None:	CODE
LOW	backend/tests/test_request_parsing.py	36	def test_parse_prompt_content_defaults_for_invalid_payload() -> None:	CODE
LOW	backend/tests/test_request_parsing.py	42	def test_parse_prompt_history_with_valid_entries() -> None:	CODE
LOW	backend/tests/test_request_parsing.py	76	def test_parse_prompt_history_filters_invalid_items() -> None:	CODE
LOW	backend/tests/test_request_parsing.py	102	def test_parse_prompt_history_defaults_for_invalid_payload() -> None:	CODE
LOW	backend/tests/test_batching.py	13	async def test_process_tasks_batches_replicate_calls(	CODE
LOW	backend/tests/test_batching.py	40	async def test_remove_background_batches_calls(	CODE
LOW	backend/tests/test_batching.py	78	async def test_remove_background_accepts_data_urls(	CODE
LOW	backend/tests/test_batching.py	109	async def test_remove_background_converts_localhost_asset_url_to_data_url(	CODE
LOW	backend/tests/test_prompts.py	94	def test_plan_create_uses_create_from_input(self) -> None:	CODE
LOW	backend/tests/test_prompts.py	105	async def test_create_prompt_includes_design_system(self) -> None:	CODE
LOW	backend/tests/test_prompts.py	133	def test_plan_update_with_history_uses_history_strategy(self) -> None:	CODE
LOW	backend/tests/test_prompts.py	143	def test_plan_update_without_history_uses_file_snapshot_strategy(self) -> None:	CODE
195 more matches not shown…

Unused Imports57 hits · 57 pts

Severity	File	Line	Context
LOW	backend/video/__init__.py	1	CODE
LOW	backend/video/__init__.py	1	CODE
LOW	backend/evals/core.py	13	CODE
LOW	backend/uploaded_assets/__init__.py	1	CODE
LOW	backend/uploaded_assets/__init__.py	1	CODE
LOW	backend/uploaded_assets/__init__.py	5	CODE
LOW	backend/uploaded_assets/__init__.py	5	CODE
LOW	backend/uploaded_assets/__init__.py	5	CODE
LOW	backend/uploaded_assets/__init__.py	5	CODE
LOW	backend/uploaded_assets/__init__.py	5	CODE
LOW	backend/uploaded_assets/__init__.py	5	CODE
LOW	backend/uploaded_assets/__init__.py	5	CODE
LOW	backend/image_generation/core.py	1	CODE
LOW	backend/image_generation/core.py	1	CODE
LOW	backend/agent/tools/__init__.py	1	CODE
LOW	backend/agent/tools/__init__.py	2	CODE
LOW	backend/agent/tools/__init__.py	2	CODE
LOW	backend/agent/tools/__init__.py	2	CODE
LOW	backend/agent/tools/__init__.py	7	CODE
LOW	backend/agent/tools/__init__.py	7	CODE
LOW	backend/agent/tools/__init__.py	8	CODE
LOW	backend/agent/tools/__init__.py	8	CODE
LOW	backend/agent/tools/__init__.py	9	CODE
LOW	backend/agent/tools/__init__.py	9	CODE
LOW	backend/agent/tools/__init__.py	9	CODE
LOW	backend/agent/tools/runtime.py	4	CODE
LOW	backend/agent/providers/__init__.py	1	CODE
LOW	backend/agent/providers/__init__.py	1	CODE
LOW	backend/agent/providers/__init__.py	2	CODE
LOW	backend/agent/providers/__init__.py	2	CODE
LOW	backend/agent/providers/__init__.py	2	CODE
LOW	backend/agent/providers/__init__.py	2	CODE
LOW	backend/agent/providers/__init__.py	2	CODE
LOW	backend/agent/providers/__init__.py	9	CODE
LOW	backend/agent/providers/__init__.py	10	CODE
LOW	backend/agent/providers/__init__.py	10	CODE
LOW	backend/agent/providers/__init__.py	11	CODE
LOW	backend/agent/providers/__init__.py	11	CODE
LOW	backend/agent/providers/__init__.py	11	CODE
LOW	backend/agent/providers/types.py	1	CODE
LOW	backend/agent/providers/types.py	1	CODE
LOW	backend/agent/providers/types.py	1	CODE
LOW	backend/agent/providers/token_usage.py	1	CODE
LOW	backend/agent/providers/anthropic/__init__.py	1	CODE
LOW	backend/agent/providers/anthropic/__init__.py	1	CODE
LOW	backend/agent/providers/anthropic/__init__.py	1	CODE
LOW	backend/prompts/__init__.py	1	CODE
LOW	backend/prompts/update/__init__.py	1	CODE
LOW	backend/prompts/update/__init__.py	2	CODE
LOW	backend/routes/evals.py	4	CODE
LOW	backend/preview_screenshot/__init__.py	12	CODE
LOW	backend/preview_screenshot/__init__.py	12	CODE
LOW	backend/preview_screenshot/__init__.py	13	CODE
LOW	backend/preview_screenshot/__init__.py	14	CODE
LOW	backend/preview_screenshot/__init__.py	14	CODE
LOW	backend/preview_screenshot/__init__.py	14	CODE
LOW	backend/preview_screenshot/__init__.py	14	CODE

Decorative Section Separators12 hits · 45 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	backend/tests/test_token_usage.py	41	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	backend/tests/test_token_usage.py	43	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	backend/tests/test_token_usage.py	106	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	backend/tests/test_token_usage.py	108	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	backend/tests/test_token_usage.py	276	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	backend/tests/test_token_usage.py	278	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	backend/tests/test_token_usage.py	12	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	backend/tests/test_token_usage.py	14	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	backend/tests/test_token_usage.py	168	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	backend/tests/test_token_usage.py	170	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	backend/tests/test_token_usage.py	228	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	backend/tests/test_token_usage.py	230	# ---------------------------------------------------------------------------	COMMENT

Excessive Try-Catch Wrapping33 hits · 40 pts

Severity	File	Line	Snippet	Context
LOW	plan.md	61	except Exception as e:	CODE
LOW	backend/asset_extraction.py	33	except Exception:	CODE
LOW	backend/run_image_generation_evals.py	203	except Exception as exc:	CODE
LOW	backend/evals/runner.py	112	except Exception as e:	CODE
LOW	backend/evals/runner.py	286	except Exception as e_write:	CODE
LOW	backend/evals/runner.py	317	except Exception as e_as_completed:	CODE
LOW⚡	backend/evals/runner.py	352	except Exception as e:	CODE
MEDIUM⚡	backend/evals/runner.py	353	print(f"Error writing timing file {timing_file_path}: {e}")	CODE
LOW⚡	backend/evals/runner.py	362	except Exception as e:	CODE
MEDIUM⚡	backend/evals/runner.py	363	print(f"Error writing failed tasks log {failed_log_path}: {e}")	CODE
LOW	backend/image_generation/replicate.py	100	except Exception as exc:	CODE
LOW	backend/agent/tools/screenshot_preview.py	64	except Exception as exc:	CODE
LOW	backend/agent/tools/parsing.py	73	except Exception:	CODE
LOW	backend/agent/tools/extract_assets.py	94	except Exception as exc:	CODE
LOW	backend/agent/tools/runtime.py	442	except Exception as exc:	CODE
LOW	backend/agent/providers/gemini.py	112	except Exception:	CODE
LOW	backend/agent/providers/gemini.py	366	except Exception as exc:	CODE
LOW	backend/fs_logging/prompt_reports.py	146	except Exception as e:	CODE
MEDIUM	backend/routes/generate_code.py	183	print(f"Error (variant {variantIndex + 1}): {value}")	CODE
LOW	backend/routes/generate_code.py	437	except Exception:	CODE
LOW	backend/routes/generate_code.py	521	except Exception:	CODE
LOW	backend/routes/generate_code.py	680	except Exception as e:	CODE
MEDIUM	backend/routes/generate_code.py	681	print(f"Error in variant {index + 1}: {e}")	CODE
LOW	backend/routes/generate_code.py	832	except Exception as e:	CODE
LOW	backend/routes/evals.py	47	except Exception as e:	CODE
LOW	backend/routes/evals.py	101	except Exception as e:	CODE
LOW	backend/routes/evals.py	303	except Exception as e:	CODE
LOW	backend/routes/evals.py	438	except Exception as e:	CODE
LOW	backend/routes/export.py	357	except Exception as exc:	CODE
LOW	backend/routes/screenshot.py	105	except Exception as e:	CODE
LOW	backend/debug/DebugFileWriter.py	26	except Exception as e:	CODE
LOW	backend/preview_screenshot/playwright_backend.py	53	except Exception as exc:	CODE
LOW	backend/preview_screenshot/playwright_backend.py	85	except Exception:	CODE

Deep Nesting22 hits · 22 pts

Severity	File	Line	Context
LOW	backend/utils.py	12	CODE
LOW	backend/utils.py	39	CODE
LOW	backend/utils.py	100	CODE
LOW	backend/utils.py	172	CODE
LOW	backend/evals/runner.py	133	CODE
LOW	backend/agent/engine.py	175	CODE
LOW	backend/agent/tools/extract_assets.py	43	CODE
LOW	backend/agent/providers/gemini.py	118	CODE
LOW	backend/agent/providers/openai.py	27	CODE
LOW	backend/agent/providers/openai.py	85	CODE
LOW	backend/agent/providers/openai.py	168	CODE
LOW	backend/agent/providers/openai.py	88	CODE
LOW	backend/agent/providers/openai.py	476	CODE
LOW	backend/agent/providers/anthropic/provider.py	181	CODE
LOW	backend/agent/providers/anthropic/provider.py	314	CODE
LOW	backend/fs_logging/openai_input_formatting.py	96	CODE
LOW	backend/routes/prompt_reports.py	168	CODE
LOW	backend/routes/generate_code.py	169	CODE
LOW	backend/routes/generate_code.py	280	CODE
LOW	backend/routes/generate_code.py	445	CODE
LOW	backend/routes/evals.py	54	CODE
LOW	backend/routes/evals.py	335	CODE

Modern Structural Boilerplate12 hits · 12 pts

Severity	File	Line	Snippet	Context
LOW	backend/video/__init__.py	6	__all__ = [	CODE
LOW	backend/uploaded_assets/__init__.py	15	__all__ = [	CODE
LOW	backend/image_generation/core.py	7	__all__ = [	CODE
LOW	backend/agent/tools/__init__.py	15	__all__ = [	CODE
LOW	backend/agent/providers/__init__.py	13	__all__ = [	CODE
LOW	backend/agent/providers/types.py	11	__all__ = [	CODE
LOW	backend/agent/providers/anthropic/__init__.py	7	__all__ = [	CODE
LOW	backend/prompts/__init__.py	3	__all__ = [	CODE
LOW	backend/prompts/update/__init__.py	4	__all__ = [	CODE
LOW	backend/prompts/create/__init__.py	48	__all__ = ["build_create_prompt_from_input"]	CODE
LOW	backend/preview_screenshot/registry.py	16	def set_screenshot_backend(backend: ScreenshotBackend) -> None:	CODE
LOW	backend/preview_screenshot/__init__.py	21	__all__ = [	CODE

Fake / Example Data8 hits · 9 pts

Severity	File	Line	Snippet	Context
LOW	backend/tests/test_batching.py	43	monkeypatch.setattr("agent.tools.runtime.REPLICATE_API_KEY", "fake-key")	CODE
LOW	backend/tests/test_batching.py	81	monkeypatch.setattr("agent.tools.runtime.REPLICATE_API_KEY", "fake-key")	CODE
LOW	backend/tests/test_batching.py	113	monkeypatch.setattr("agent.tools.runtime.REPLICATE_API_KEY", "fake-key")	CODE
LOW	backend/tests/test_tool_image_outputs.py	204	monkeypatch.setattr("agent.tools.runtime.REPLICATE_API_KEY", "fake-key")	CODE
LOW	backend/tests/test_tool_image_outputs.py	284	monkeypatch.setattr("agent.tools.runtime.REPLICATE_API_KEY", "fake-key")	CODE
LOW⚡	backend/tests/test_prompt_summary.py	17	{"role": "system", "content": "lorem ipsum dolor sit amet"},	CODE
LOW⚡	backend/tests/test_prompt_summary.py	17	{"role": "system", "content": "lorem ipsum dolor sit amet"},	CODE
LOW	backend/tests/test_prompt_summary.py	35	assert "SYSTEM: lorem ipsum" in summary	CODE

Cross-Language Confusion1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	backend/asset_extraction.py	126	- If the asset is not visible, return {{"image_index": null, "box_2d": null, "label": "not found"}}.	CODE

Redundant / Tautological Comments3 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	backend/routes/generate_code.py	817	# Check if all variants failed	COMMENT
LOW	backend/routes/screenshot.py	20	# Check if we have a scheme	COMMENT
LOW	backend/routes/screenshot.py	28	# Check if this might be a domain with port (like example.com:8080)	COMMENT

Over-Commented Block4 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	frontend/src/index.css	161	90deg,	COMMENT
LOW	frontend/src/components/select-and-edit/overlays.ts	1	// Devtools-style indicators for select-and-edit mode, rendered as	COMMENT
LOW	backend/.pre-commit-config.yaml	1	# See https://pre-commit.com for more information	COMMENT
LOW	backend/.pre-commit-config.yaml	21	# # entry: poetry run --directory backend pyright	COMMENT

Slop Phrases1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	docker-compose.yml	14	#- BACKEND_PORT=7001 # if you change the port, make sure to also change the VITE_WS_BACKEND_URL at frontend/.env	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings