JoshuaC215/agent-service-toolkit

27.8

Adjusted Score

27.8

Raw Score

100%

Time Factor

2026-08-23

Last Push

4.4K

Stars

Python

Language

13.9K

Lines of Code

113

Files

272

Pattern Hits

2026-08-29

Scan Date

0.10

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 11MEDIUM 23LOW 238

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 272 distinct pattern matches across 15 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 Identifiers135 hits · 154 pts

Severity	File	Line	Snippet	Context
LOW	tests/conftest.py	17	def pytest_collection_modifyitems(config, items):	CODE
LOW	tests/smoke/test_persistence.py	14	def test_checkpointer_persists_history():	CODE
LOW	tests/smoke/test_persistence.py	41	def test_threads_lists_user_threads():	CODE
LOW	tests/core/test_llm.py	58	def test_get_model_groq_guard():	CODE
LOW	tests/core/test_llm.py	66	def test_get_model_groq_gpt_oss():	CODE
LOW	tests/core/test_llm.py	88	def test_get_model_openrouter():	CODE
LOW	tests/core/test_llm.py	100	def test_get_model_openrouter_requires_key():	CODE
LOW⚡	tests/core/test_settings.py	32	def test_settings_default_values():	CODE
LOW⚡	tests/core/test_settings.py	40	def test_settings_no_api_keys():	CODE
LOW⚡	tests/core/test_settings.py	47	def test_settings_with_openai_key():	CODE
LOW⚡	tests/core/test_settings.py	55	def test_settings_with_anthropic_key():	CODE
LOW⚡	tests/core/test_settings.py	63	def test_settings_with_openrouter_key():	CODE
LOW⚡	tests/core/test_settings.py	73	def test_settings_with_vertexai_credentials_file():	CODE
LOW⚡	tests/core/test_settings.py	81	def test_settings_with_multiple_api_keys():	CODE
LOW	tests/core/test_settings.py	101	def test_settings_use_fake_model():	CODE
LOW	tests/core/test_settings.py	108	def test_settings_use_fake_model_wins_over_ambient_real_keys():	CODE
LOW	tests/core/test_settings.py	127	def test_settings_explicit_default_model_overrides_fake():	CODE
LOW	tests/core/test_settings.py	151	def test_settings_with_azure_openai_key():	CODE
LOW	tests/core/test_settings.py	167	def test_settings_with_both_openai_and_azure():	CODE
LOW	tests/core/test_settings.py	189	def test_settings_azure_deployment_names():	CODE
LOW	tests/core/test_settings.py	194	def test_settings_azure_missing_deployment_names():	CODE
LOW	tests/core/test_settings.py	207	def test_settings_azure_deployment_map():	CODE
LOW	tests/core/test_settings.py	224	def test_settings_azure_invalid_deployment_map():	CODE
LOW	tests/core/test_settings.py	238	def test_settings_azure_openai():	CODE
LOW⚡	tests/core/test_settings.py	264	def test_settings_log_level_default():	CODE
LOW⚡	tests/core/test_settings.py	272	def test_settings_log_level_from_env():	CODE
LOW⚡	tests/core/test_settings.py	280	def test_settings_log_level_invalid():	CODE
LOW	tests/app/test_streamlit_app.py	12	def test_app_simple_non_streaming(mock_agent_client):	CODE
LOW	tests/app/test_streamlit_app.py	75	def test_app_thread_id_history(mock_agent_client):	CODE
LOW	tests/app/test_streamlit_app.py	100	def test_app_resume_with_agent_param(mock_agent_client):	CODE
LOW	tests/app/test_streamlit_app.py	339	async def test_app_streaming_single_sub_agent(mock_agent_client, multi_agent_messages):	CODE
LOW	tests/app/test_streamlit_app.py	409	async def test_app_streaming_sequential_sub_agents(mock_agent_client, multi_agent_messages):	CODE
LOW	tests/app/test_streamlit_app.py	499	async def test_app_streaming_nested_sub_agents(mock_agent_client, multi_agent_messages):	CODE
LOW	tests/app/test_streamlit_app.py	604	def test_app_thread_caching_sidebar(mock_agent_client, mock_threads_data):	CODE
LOW	tests/app/test_streamlit_app.py	621	def test_app_thread_click_loads_history(mock_agent_client, mock_threads_data):	CODE
LOW	tests/app/test_streamlit_app.py	650	def test_app_thread_click_history_error(mock_agent_client, mock_threads_data):	CODE
LOW	tests/app/test_streamlit_app.py	667	def test_app_thread_fetch_error_shows_caption(mock_agent_client):	CODE
LOW	tests/integration/test_docker_e2e.py	8	def test_service_with_fake_model():	CODE
LOW⚡	tests/agents/test_lazy_agent.py	43	def test_get_graph_before_load(self):	CODE
LOW⚡	tests/agents/test_lazy_agent.py	49	def test_get_graph_after_load(self):	CODE
LOW⚡	tests/agents/test_lazy_agent.py	58	def test_get_graph_no_graph_created(self):	CODE
LOW	tests/agents/test_agent_loading.py	15	async def test_load_agent_static_agent(self):	CODE
LOW	tests/agents/test_agent_loading.py	22	async def test_load_agent_lazy_agent(self):	CODE
LOW⚡	tests/agents/test_agent_loading.py	34	async def test_load_agent_nonexistent(self):	CODE
LOW⚡	tests/agents/test_agent_loading.py	39	def test_get_agent_static_agent(self):	CODE
LOW⚡	tests/agents/test_agent_loading.py	44	def test_get_agent_lazy_agent_not_loaded(self):	CODE
LOW	tests/agents/test_agent_loading.py	55	def test_get_agent_lazy_agent_loaded(self):	CODE
LOW	tests/agents/test_agent_loading.py	68	def test_get_agent_nonexistent(self):	CODE
LOW	tests/agents/test_github_mcp_agent.py	22	async def test_load_without_github_pat(self):	CODE
LOW	tests/agents/test_github_mcp_agent.py	35	async def test_load_with_github_pat(self):	CODE
LOW	tests/agents/test_github_mcp_agent.py	118	def test_get_graph_not_loaded(self):	CODE
LOW	tests/schema/test_models.py	14	def test_model_enums_are_all_discovered():	CODE
LOW	tests/schema/test_models.py	19	def test_model_values_are_unique_across_enums():	CODE
LOW	tests/schema/test_models.py	32	def test_vertexai_models_do_not_collide_with_google(model):	CODE
LOW	tests/schema/test_models.py	37	def test_model_table_covers_every_model():	CODE
LOW⚡	tests/voice/test_tts.py	11	def test_init_with_openai_provider(mock_openai_client):	CODE
LOW⚡	tests/voice/test_tts.py	19	def test_init_with_invalid_provider():	CODE
LOW⚡	tests/voice/test_tts.py	26	def test_init_with_unimplemented_provider():	CODE
LOW⚡	tests/voice/test_tts.py	33	def test_from_env_provider_not_set():	CODE
LOW⚡	tests/voice/test_tts.py	41	def test_from_env_valid_provider(mock_openai_client):	CODE
75 more matches not shown…

Self-Referential Comments17 hits · 50 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/service/test_service.py	38	# Create a separate mock for the default agent	COMMENT
MEDIUM	tests/client/test_client.py	191	# Create an async iterator for the events	COMMENT
MEDIUM	scripts/create_chroma_db.py	71	# Create the Chroma database	COMMENT
MEDIUM	src/streamlit_app.py	450	# Create a status container for each tool call and store the	COMMENT
MEDIUM	src/streamlit_app.py	625	# Create a nested status container for the sub-agent	COMMENT
MEDIUM	src/agents/rag_assistant.py	95	# Define the graph	STRING
MEDIUM	src/agents/interrupt_agent.py	220	# Define the graph	COMMENT
MEDIUM	src/agents/safeguard.py	103	# Create a formatted history string to evaluate	STRING
MEDIUM	src/agents/tools.py	51	# Create the embedding function for our project description database	COMMENT
MEDIUM	src/agents/command_agent.py	16	# Define the nodes	COMMENT
MEDIUM⚡	src/agents/knowledge_base_agent.py	18	# Define the state	COMMENT
MEDIUM⚡	src/agents/knowledge_base_agent.py	27	# Create the retriever	COMMENT
MEDIUM⚡	src/agents/knowledge_base_agent.py	35	# Create the retriever with the specified Knowledge Base ID	COMMENT
MEDIUM	src/agents/knowledge_base_agent.py	157	# Define the graph	COMMENT
MEDIUM	src/agents/research_assistant.py	99	# Define the graph	STRING
MEDIUM	src/agents/github_mcp_agent/github_mcp_agent.py	101	# Create the agent instance	COMMENT
MEDIUM	src/agents/bg_task_agent/bg_task_agent.py	53	# Define the graph	COMMENT

Excessive Try-Catch Wrapping33 hits · 36 pts

Severity	File	Line	Snippet	Context
LOW	scripts/check_live_models.py	88	except Exception as e:	CODE
LOW	scripts/e2e_ui_tests.py	90	except Exception:	CODE
LOW	scripts/e2e_ui_tests.py	437	except Exception as e:	CODE
LOW	scripts/e2e_ui_tests.py	461	except Exception:	CODE
MEDIUM	scripts/e2e_ui_tests.py	87	def launch_browser(p) -> Browser:	CODE
LOW⚡	scripts/smoke_live_app.py	52	except Exception as e:	CODE
LOW⚡	scripts/smoke_live_app.py	60	except Exception:	CODE
LOW⚡	scripts/smoke_live_app.py	70	except Exception:	CODE
LOW⚡	scripts/smoke_live_app.py	78	except Exception as e:	CODE
LOW⚡	scripts/smoke_live_app.py	83	except Exception:	CODE
LOW	scripts/smoke_live_app.py	124	except Exception:	CODE
LOW	src/streamlit_app.py	167	except Exception as e:	CODE
LOW	src/core/settings.py	242	except Exception as e:	CODE
LOW	src/agents/interrupt_agent.py	117	except Exception as e:	CODE
LOW	src/agents/interrupt_agent.py	163	except Exception as e:	CODE
LOW	src/agents/tools.py	34	except Exception as e:	CODE
LOW	src/agents/tools.py	54	except Exception as e:	CODE
LOW	src/agents/knowledge_base_agent.py	119	except Exception as e:	CODE
LOW	src/agents/github_mcp_agent/github_mcp_agent.py	80	except Exception as e:	CODE
LOW	src/voice/tts.py	150	except Exception as e:	CODE
LOW	src/voice/stt.py	142	except Exception as e:	CODE
LOW	src/voice/providers/openai_tts.py	112	except Exception as e:	CODE
LOW	src/voice/providers/openai_stt.py	54	except Exception as e:	CODE
LOW	src/service/service.py	106	except Exception as e:	CODE
LOW	src/service/service.py	116	except Exception as e:	CODE
LOW	src/service/service.py	238	except Exception as e:	CODE
LOW	src/service/service.py	324	except Exception as e:	CODE
LOW	src/service/service.py	349	except Exception as e:	CODE
LOW	src/service/service.py	445	except Exception as e:	CODE
LOW	src/service/service.py	470	except Exception as e:	CODE
LOW	src/service/service.py	487	except Exception as e:	CODE
LOW	src/client/client.py	187	except Exception as e:	CODE
LOW	src/client/client.py	194	except Exception as e:	CODE

Unused Imports29 hits · 29 pts

Severity	File	Line	Context
LOW	src/core/__init__.py	1	CODE
LOW	src/core/__init__.py	2	CODE
LOW	src/agents/__init__.py	1	CODE
LOW	src/agents/__init__.py	1	CODE
LOW	src/agents/__init__.py	1	CODE
LOW	src/agents/__init__.py	1	CODE
LOW	src/agents/__init__.py	1	CODE
LOW	src/agents/__init__.py	1	CODE
LOW	src/schema/__init__.py	1	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/schema/__init__.py	2	CODE
LOW	src/voice/__init__.py	33	CODE
LOW	src/voice/__init__.py	34	CODE
LOW	src/voice/__init__.py	35	CODE
LOW	src/voice/providers/__init__.py	3	CODE
LOW	src/voice/providers/__init__.py	4	CODE
LOW	src/service/__init__.py	1	CODE
LOW	src/client/__init__.py	1	CODE
LOW	src/client/__init__.py	1	CODE

Cross-File Repetition5 hits · 25 pts

Severity	File	Snippet	Context
HIGH	src/agents/rag_assistant.py	`total=false` is pep589 specs. documentation: https://typing.readthedocs.io/en/latest/spec/typeddict.html#totality	STRING
HIGH	src/agents/interrupt_agent.py	`total=false` is pep589 specs. documentation: https://typing.readthedocs.io/en/latest/spec/typeddict.html#totality	STRING
HIGH	src/agents/command_agent.py	`total=false` is pep589 specs. documentation: https://typing.readthedocs.io/en/latest/spec/typeddict.html#totality	STRING
HIGH	src/agents/research_assistant.py	`total=false` is pep589 specs. documentation: https://typing.readthedocs.io/en/latest/spec/typeddict.html#totality	STRING
HIGH	src/agents/bg_task_agent/bg_task_agent.py	`total=false` is pep589 specs. documentation: https://typing.readthedocs.io/en/latest/spec/typeddict.html#totality	STRING

Modern Structural Boilerplate22 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW	src/core/__init__.py	4	__all__ = ["settings", "get_model"]	CODE
LOW	src/memory/mongodb.py	11	logger = logging.getLogger(__name__)	CODE
LOW	src/memory/__init__.py	40	__all__ = ["initialize_database", "initialize_store"]	CODE
LOW	src/memory/postgres.py	11	logger = logging.getLogger(__name__)	CODE
LOW	src/agents/interrupt_agent.py	18	logger = logging.getLogger(__name__)	CODE
LOW	src/agents/__init__.py	10	__all__ = [	CODE
LOW⚡	src/agents/knowledge_base_agent.py	15	logger = logging.getLogger(__name__)	CODE
LOW	src/agents/github_mcp_agent/github_mcp_agent.py	15	logger = logging.getLogger(__name__)	CODE
LOW	src/schema/__init__.py	17	__all__ = [	CODE
LOW	src/voice/tts.py	11	logger = logging.getLogger(__name__)	CODE
LOW	src/voice/__init__.py	37	__all__ = ["VoiceManager", "SpeechToText", "TextToSpeech"]	CODE
LOW	src/voice/manager.py	15	logger = logging.getLogger(__name__)	CODE
LOW	src/voice/stt.py	11	logger = logging.getLogger(__name__)	CODE
LOW	src/voice/providers/openai_tts.py	7	logger = logging.getLogger(__name__)	CODE
LOW	src/voice/providers/__init__.py	10	__all__ = ["OpenAISTT", "OpenAITTS"]	CODE
LOW	src/voice/providers/openai_stt.py	8	logger = logging.getLogger(__name__)	CODE
LOW	src/service/service.py	57	logger = logging.getLogger(__name__)	CODE
LOW	src/service/agui.py	29	logger = logging.getLogger(__name__)	CODE
LOW	src/service/__init__.py	3	__all__ = ["app"]	CODE
LOW	src/service/threads.py	17	logger = logging.getLogger(__name__)	CODE
LOW	src/client/client.py	77	def update_agent(self, agent: str, verify: bool = True) -> None:	CODE
LOW	src/client/__init__.py	3	__all__ = ["AgentClient", "AgentClientError"]	CODE

Synthetic Comment Markers2 hits · 12 pts

Severity	File	Line	Snippet	Context
HIGH	.claude/skills/maintainer-response/SKILL.md	197	### Be skeptical of automated / AI-generated PRs	COMMENT
HIGH	.claude/skills/maintainer-response/SKILL.md	303	layer that unconditionally adds a "with Claude" badge and a "Generated by Claude Code"	CODE

Modern AI Meta-Vocabulary4 hits · 12 pts

Severity	File	Line	Snippet	Context
MEDIUM	CLAUDE.md	11	## Maintainer scaffolding vs. template content	COMMENT
MEDIUM	docs/RAG_Assistant.md	1	# Creating a RAG assistant	COMMENT
MEDIUM	docs/RAG_Assistant.md	20	## Configuring the RAG assistant	COMMENT
MEDIUM	.github/workflows/template-cleanup.yml	4	# downstream repo. It strips maintainer-only scaffolding, commits the result, then	COMMENT

Redundant / Tautological Comments8 hits · 12 pts

Severity	File	Line	Snippet	Context
LOW	scripts/create_chroma_db.py	81	# Display results	COMMENT
LOW	src/streamlit_app.py	34	# Check if user_id exists in session state	COMMENT
LOW	src/streamlit_app.py	623	# Check if this is a nested transfer/delegate	COMMENT
LOW⚡	src/agents/interrupt_agent.py	93	# Check if we already have the birthdate in the store for this user	COMMENT
LOW⚡	src/agents/interrupt_agent.py	98	if result: # Check if anything was returned	CODE
LOW⚡	src/agents/interrupt_agent.py	100	if result: # Check if list is not empty	CODE
LOW	src/agents/knowledge_base_agent.py	66	# Check if documents were retrieved	STRING
LOW	src/voice/manager.py	99	# Check if transcription succeeded	COMMENT

Cross-Language Confusion2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	src/agents/safeguard.py	60	Answer: {"violation": 0, "category": null, "rationale": "Legitimate question about capabilities"}	CODE
HIGH	src/agents/safeguard.py	64	Answer: {"violation": 0, "category": null, "rationale": "Normal programming assistance request"}	CODE

Docstring Block Structure2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	src/voice/tts.py	78	Load the appropriate TTS provider implementation. Args: provider: Provider name api_key	STRING
HIGH	src/voice/stt.py	76	Load the appropriate STT provider implementation. Args: provider: Provider name api_key	STRING

Deep Nesting9 hits · 9 pts

Severity	File	Line	Context
LOW	scripts/e2e_ui_tests.py	145	CODE
LOW	scripts/e2e_ui_tests.py	400	CODE
LOW	scripts/smoke_live_app.py	117	CODE
LOW	src/streamlit_app.py	67	CODE
LOW	src/streamlit_app.py	369	CODE
LOW	src/streamlit_app.py	558	CODE
LOW	src/agents/interrupt_agent.py	77	CODE
LOW	src/service/service.py	243	CODE
LOW	src/client/client.py	204	CODE

Dead Code1 hit · 2 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/service/test_threads.py	236		CODE

Over-Commented Block2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	scripts/smoke_test.sh	1	#!/usr/bin/env bash	COMMENT
LOW	scripts/smoke_test.sh	21	# Only databases run in Docker; the service itself runs on the host via uv,	COMMENT

Example Usage Blocks1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	scripts/smoke_test.sh	7	# Usage:	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings