simular-ai/Agent-S

50.5

Adjusted Score

50.5

Raw Score

100%

Time Factor

2026-08-01

Last Push

12.1K

Stars

Python

Language

22.2K

Lines of Code

109

Files

432

Pattern Hits

2026-08-02

Scan Date

1.20

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

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

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 131MEDIUM 43LOW 258

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 432 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.

Cross-File Repetition109 hits · 545 pts

Severity	File	Line	Snippet	Context
HIGH	gui_agents/s2/cli_app.py	0	get a single character from stdin without pressing enter	STRING
HIGH	gui_agents/s3/cli_app.py	0	get a single character from stdin without pressing enter	STRING
HIGH	gui_agents/s1/cli_app.py	0	get a single character from stdin without pressing enter	STRING
HIGH	gui_agents/s2_5/cli_app.py	0	get a single character from stdin without pressing enter	STRING
HIGH	gui_agents/s2/cli_app.py	0	handle ctrl+c signal for debugging during agent execution	STRING
HIGH	gui_agents/s3/cli_app.py	0	handle ctrl+c signal for debugging during agent execution	STRING
HIGH	gui_agents/s1/cli_app.py	0	handle ctrl+c signal for debugging during agent execution	STRING
HIGH	gui_agents/s2_5/cli_app.py	0	handle ctrl+c signal for debugging during agent execution	STRING
HIGH	gui_agents/s2/cli_app.py	0	show a platform-specific permission dialog and return true if approved.	STRING
HIGH	gui_agents/s3/cli_app.py	0	show a platform-specific permission dialog and return true if approved.	STRING
HIGH	gui_agents/s1/cli_app.py	0	show a platform-specific permission dialog and return true if approved.	STRING
HIGH	gui_agents/s2_5/cli_app.py	0	show a platform-specific permission dialog and return true if approved.	STRING
HIGH	gui_agents/s2/core/mllm.py	0	generate the next response based on previous messages	STRING
HIGH	gui_agents/s3/core/mllm.py	0	generate the next response based on previous messages	STRING
HIGH	gui_agents/s1/mllm/MultimodalAgent.py	0	generate the next response based on previous messages	STRING
HIGH	gui_agents/s2_5/core/mllm.py	0	generate the next response based on previous messages	STRING
HIGH	gui_agents/s2/core/knowledge.py	0	summarize the narrative experience for lifelong learning reflection args: trajectory: str: the narrative experience to b	STRING
HIGH	gui_agents/s2/agents/manager.py	0	summarize the narrative experience for lifelong learning reflection args: trajectory: str: the narrative experience to b	STRING
HIGH	gui_agents/s1/core/Manager.py	0	summarize the narrative experience for lifelong learning reflection args: trajectory: str: the narrative experience to b	STRING
HIGH	gui_agents/s2/memory/procedural_memory.py	0	your response should be formatted like this: (previous action verification) carefully analyze based on the screenshot if	STRING
HIGH	gui_agents/s3/memory/procedural_memory.py	0	your response should be formatted like this: (previous action verification) carefully analyze based on the screenshot if	STRING
HIGH	gui_agents/s2_5/memory/procedural_memory.py	0	your response should be formatted like this: (previous action verification) carefully analyze based on the screenshot if	STRING
HIGH	gui_agents/s2/memory/procedural_memory.py	0	you are an expert in graphical user interfaces. your task is to process a phrase of text, and identify the most relevant	STRING
HIGH	gui_agents/s2_5/memory/procedural_memory.py	0	you are an expert in graphical user interfaces. your task is to process a phrase of text, and identify the most relevant	STRING
HIGH	gui_agents/s3/memory/procedural_memory.py	0	you are an expert in graphical user interfaces. your task is to process a phrase of text, and identify the most relevant	STRING
HIGH	gui_agents/s2/agents/worker.py	0	predict the next action(s) based on the current observation.	STRING
HIGH	gui_agents/s3/agents/worker.py	0	predict the next action(s) based on the current observation.	STRING
HIGH	gui_agents/s1/core/Worker.py	0	predict the next action(s) based on the current observation.	STRING
HIGH	gui_agents/s2_5/agents/worker.py	0	predict the next action(s) based on the current observation.	STRING
HIGH	gui_agents/s2/agents/agent_s.py	0	generate next action prediction args: instruction: natural language instruction observation: current ui state observatio	STRING
HIGH	gui_agents/s3/agents/agent_s.py	0	generate next action prediction args: instruction: natural language instruction observation: current ui state observatio	STRING
HIGH	gui_agents/s1/core/AgentS.py	0	generate next action prediction args: instruction: natural language instruction observation: current ui state observatio	STRING
HIGH	gui_agents/s2_5/agents/agent_s.py	0	generate next action prediction args: instruction: natural language instruction observation: current ui state observatio	STRING
HIGH	gui_agents/s2/agents/grounding.py	0	import subprocess; import difflib; import pyautogui; import time; pyautogui.press('escape'); time.sleep(0.5); output = s	STRING
HIGH	gui_agents/s1/aci/LinuxOSACI.py	0	import subprocess; import difflib; import pyautogui; import time; pyautogui.press('escape'); time.sleep(0.5); output = s	STRING
HIGH	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	0	import subprocess; import difflib; import pyautogui; import time; pyautogui.press('escape'); time.sleep(0.5); output = s	STRING
HIGH	gui_agents/s2_5/agents/grounding.py	0	import subprocess; import difflib; import pyautogui; import time; pyautogui.press('escape'); time.sleep(0.5); output = s	STRING
HIGH	gui_agents/s3/agents/grounding.py	0	import subprocess; import difflib; import pyautogui; import time; pyautogui.press('escape'); time.sleep(0.5); output = s	STRING
HIGH	gui_agents/s2/agents/grounding.py	0	click on the element args: element_description:str, a detailed descriptions of which element to click on. this descripti	STRING
HIGH	gui_agents/s3/agents/grounding.py	0	click on the element args: element_description:str, a detailed descriptions of which element to click on. this descripti	STRING
HIGH	gui_agents/s2_5/agents/grounding.py	0	click on the element args: element_description:str, a detailed descriptions of which element to click on. this descripti	STRING
HIGH	gui_agents/s2/agents/grounding.py	0	import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});	STRING
HIGH	gui_agents/s3/agents/grounding.py	0	import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});	STRING
HIGH	gui_agents/s1/aci/LinuxOSACI.py	0	import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});	STRING
HIGH	gui_agents/s1/aci/MacOSACI.py	0	import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});	STRING
HIGH	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	0	import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});	STRING
HIGH	gui_agents/s2_5/agents/grounding.py	0	import pyautogui; pyautogui.click({x}, {y}, clicks={num_clicks}, button={repr(button_type)});	STRING
HIGH	gui_agents/s2/agents/grounding.py	0	switch to a different application that is already open args: app_code:str the code name of the application to switch to	STRING
HIGH	gui_agents/s3/agents/grounding.py	0	switch to a different application that is already open args: app_code:str the code name of the application to switch to	STRING
HIGH	gui_agents/s1/aci/LinuxOSACI.py	0	switch to a different application that is already open args: app_code:str the code name of the application to switch to	STRING
HIGH	gui_agents/s2_5/agents/grounding.py	0	switch to a different application that is already open args: app_code:str the code name of the application to switch to	STRING
HIGH	gui_agents/s2/agents/grounding.py	0	type text/unicode into a specific element args: element_description:str, a detailed description of which element to ente	STRING
HIGH	gui_agents/s2_5/agents/grounding.py	0	type text/unicode into a specific element args: element_description:str, a detailed description of which element to ente	STRING
HIGH	gui_agents/s3/agents/grounding.py	0	type text/unicode into a specific element args: element_description:str, a detailed description of which element to ente	STRING
HIGH	gui_agents/s2/agents/grounding.py	0	save facts, elements, texts, etc. to a long-term knowledge bank for reuse during this task. can be used for copy-pasting	STRING
HIGH	gui_agents/s3/agents/grounding.py	0	save facts, elements, texts, etc. to a long-term knowledge bank for reuse during this task. can be used for copy-pasting	STRING
HIGH	gui_agents/s1/aci/LinuxOSACI.py	0	save facts, elements, texts, etc. to a long-term knowledge bank for reuse during this task. can be used for copy-pasting	STRING
HIGH	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	0	save facts, elements, texts, etc. to a long-term knowledge bank for reuse during this task. can be used for copy-pasting	STRING
HIGH	gui_agents/s2_5/agents/grounding.py	0	save facts, elements, texts, etc. to a long-term knowledge bank for reuse during this task. can be used for copy-pasting	STRING
HIGH	gui_agents/s2/agents/grounding.py	0	drag from the starting description to the ending description args: starting_description:str, a very detailed description	STRING
49 more matches not shown…

Excessive Try-Catch Wrapping105 hits · 170 pts

Severity	File	Line	Snippet	Context
LOW	gui_agents/s2/agents/worker.py	225	except Exception as e:	STRING
LOW	gui_agents/s2/agents/agent_s.py	361	except Exception as e:	CODE
LOW	gui_agents/s2/agents/grounding.py	305	except Exception as e:	STRING
LOW	gui_agents/s2/utils/common_utils.py	36	except Exception as e:	CODE
MEDIUM⚡	gui_agents/s2/utils/common_utils.py	79	print("Error: Invalid JSON")	CODE
MEDIUM⚡	gui_agents/s2/utils/common_utils.py	82	print("Error: 'dag' key not found in JSON")	CODE
MEDIUM⚡	gui_agents/s2/utils/common_utils.py	85	print(f"Error: Invalid data structure - {e}")	CODE
MEDIUM⚡	gui_agents/s2/utils/common_utils.py	88	print("Error: JSON not found")	CODE
MEDIUM⚡	gui_agents/s2/utils/common_utils.py	109	print("Error: JSON not found in either <json> tags or ```json``` fence")	CODE
MEDIUM⚡	gui_agents/s2/utils/common_utils.py	115	print(f"Error: Invalid JSON ({e})")	CODE
MEDIUM⚡	gui_agents/s2/utils/common_utils.py	119	print("Error: 'dag' key not found in JSON")	CODE
MEDIUM⚡	gui_agents/s2/utils/common_utils.py	125	print(f"Error: Invalid data structure - {e}")	CODE
LOW⚡	gui_agents/s2/utils/common_utils.py	204	except Exception as e:	CODE
MEDIUM⚡	gui_agents/s2/utils/common_utils.py	205	print(f"Error loading knowledge base: {e}")	CODE
LOW⚡	gui_agents/s2/utils/common_utils.py	213	except Exception as e:	CODE
MEDIUM⚡	gui_agents/s2/utils/common_utils.py	214	print(f"Error loading embeddings: {e}")	CODE
LOW⚡	gui_agents/s2/utils/common_utils.py	222	except Exception as e:	CODE
MEDIUM⚡	gui_agents/s2/utils/common_utils.py	223	print(f"Error saving embeddings: {e}")	CODE
LOW	gui_agents/s3/bbon/comparative_judge.py	57	except Exception as e:	CODE
MEDIUM	gui_agents/s3/bbon/comparative_judge.py	58	print(f"Error loading image {image_path}: {e}")	CODE
LOW	gui_agents/s3/agents/worker.py	329	except Exception as e:	STRING
LOW	gui_agents/s3/agents/code_agent.py	47	except Exception as e:	CODE
LOW	gui_agents/s3/agents/code_agent.py	329	except Exception as e:	STRING
LOW	gui_agents/s3/agents/grounding.py	74	except Exception:	CODE
LOW	gui_agents/s3/agents/grounding.py	78	except Exception:	CODE
LOW	gui_agents/s3/utils/formatters.py	26	except Exception as e:	CODE
LOW	gui_agents/s3/utils/local_env.py	40	except Exception as e:	CODE
LOW	gui_agents/s3/utils/local_env.py	64	except Exception as e:	CODE
LOW	gui_agents/s3/utils/common_utils.py	50	except Exception as e:	CODE
LOW	gui_agents/s3/utils/common_utils.py	139	except Exception as e:	CODE
LOW	gui_agents/s1/core/AgentS.py	318	except Exception as e:	CODE
MEDIUM⚡	gui_agents/s1/utils/common_utils.py	437	print("Error: Invalid JSON")	CODE
MEDIUM⚡	gui_agents/s1/utils/common_utils.py	440	print("Error: 'dag' key not found in JSON")	CODE
MEDIUM⚡	gui_agents/s1/utils/common_utils.py	443	print(f"Error: Invalid data structure - {e}")	CODE
MEDIUM⚡	gui_agents/s1/utils/common_utils.py	446	print("Error: JSON not found")	CODE
MEDIUM⚡	gui_agents/s1/utils/common_utils.py	845	print(f"Error loading knowledge base: {e}")	CODE
MEDIUM⚡	gui_agents/s1/utils/common_utils.py	854	print(f"Error loading embeddings: {e}")	CODE
MEDIUM⚡	gui_agents/s1/utils/common_utils.py	863	print(f"Error saving embeddings: {e}")	CODE
LOW⚡	gui_agents/s1/utils/common_utils.py	844	except Exception as e:	CODE
LOW⚡	gui_agents/s1/utils/common_utils.py	853	except Exception as e:	CODE
LOW⚡	gui_agents/s1/utils/common_utils.py	862	except Exception as e:	CODE
LOW	gui_agents/s1/utils/common_utils.py	67	except Exception as e:	CODE
LOW	gui_agents/s1/aci/LinuxOSACI.py	249	except Exception as e:	CODE
MEDIUM	gui_agents/s1/aci/LinuxOSACI.py	250	print(f"Error: {e}")	CODE
LOW	gui_agents/s1/aci/WindowsOSACI.py	133	except Exception as e:	CODE
MEDIUM	gui_agents/s1/aci/WindowsOSACI.py	134	print(f"Error: {e}")	CODE
LOW⚡	gui_agents/s1/aci/WindowsOSACI.py	194	except Exception as e:	CODE
MEDIUM⚡	gui_agents/s1/aci/WindowsOSACI.py	195	print(f"Error accessing foreground window: {e}")	CODE
LOW	gui_agents/s1/aci/WindowsOSACI.py	471	except Exception as e:	CODE
MEDIUM	gui_agents/s1/aci/WindowsOSACI.py	472	print(f"Error accessing children: {e}")	CODE
MEDIUM	gui_agents/s1/aci/WindowsOSACI.py	468	def children(self):	CODE
LOW	gui_agents/s1/aci/MacOSACI.py	154	except Exception as e:	CODE
MEDIUM	gui_agents/s1/aci/MacOSACI.py	155	print(f"Error: {e}")	CODE
LOW	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	211	except Exception as e:	CODE
MEDIUM	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	212	print(f"Error: {e}")	CODE
LOW	gui_agents/s2_5/agents/worker.py	186	except Exception as e:	STRING
LOW	gui_agents/s2_5/agents/grounding.py	305	except Exception as e:	STRING
LOW	gui_agents/s2_5/utils/common_utils.py	20	except Exception as e:	CODE
LOW	gui_agents/s2_5/utils/common_utils.py	40	except Exception as e:	CODE
LOW	integrations/openclaw/agent_s_wrapper.py	108	except Exception as e:	CODE
45 more matches not shown…

Magic Placeholder Names21 hits · 152 pts

Severity	File	Line	Snippet	Context
HIGH⚡	README.md	124	export OPENAI_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	README.md	124	export OPENAI_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	README.md	132	os.environ["OPENAI_API_KEY"] = "<YOUR_API_KEY>"	CODE
HIGH⚡	README.md	132	os.environ["OPENAI_API_KEY"] = "<YOUR_API_KEY>"	CODE
HIGH⚡	models.md	6	export OPENAI_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	models.md	6	export OPENAI_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	models.md	12	export ANTHROPIC_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	models.md	12	export ANTHROPIC_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	models.md	18	export GEMINI_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	models.md	18	export GEMINI_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	models.md	26	export AZURE_OPENAI_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	models.md	26	export AZURE_OPENAI_API_KEY=<YOUR_API_KEY>	CODE
HIGH	models.md	40	export OPENROUTER_API_KEY=<YOUR_API_KEY>	CODE
HIGH	models.md	40	export OPENROUTER_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	gui_agents/s1/README.md	64	export OPENAI_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	gui_agents/s1/README.md	64	export OPENAI_API_KEY=<YOUR_API_KEY>	CODE
HIGH⚡	gui_agents/s1/README.md	71	os.environ["OPENAI_API_KEY"] = "<YOUR_API_KEY>"	CODE
HIGH⚡	gui_agents/s1/README.md	71	os.environ["OPENAI_API_KEY"] = "<YOUR_API_KEY>"	CODE
HIGH⚡	integrations/openclaw/README.md	33	export ANTHROPIC_API_KEY="your-api-key-here"	CODE
HIGH⚡	integrations/openclaw/README.md	38	export OPENAI_API_KEY="your-api-key-here"	CODE
HIGH⚡	integrations/openclaw/README.md	43	export GEMINI_API_KEY="your-api-key-here"	CODE

Deep Nesting61 hits · 58 pts

Severity	File	Line	Context
LOW	gui_agents/s2/cli_app.py	48	CODE
LOW	gui_agents/s2/cli_app.py	154	CODE
LOW	gui_agents/s2/core/mllm.py	18	CODE
LOW	gui_agents/s2/core/mllm.py	112	CODE
LOW	gui_agents/s2/agents/agent_s.py	210	CODE
LOW	gui_agents/s2/utils/common_utils.py	129	CODE
LOW	gui_agents/s3/cli_app.py	49	CODE
LOW	gui_agents/s3/cli_app.py	155	CODE
LOW	gui_agents/s3/core/mllm.py	18	CODE
LOW	gui_agents/s3/core/mllm.py	175	CODE
LOW	gui_agents/s3/agents/worker.py	90	CODE
LOW	gui_agents/s3/agents/worker.py	178	CODE
LOW	gui_agents/s1/cli_app.py	46	CODE
LOW	gui_agents/s1/cli_app.py	154	CODE
LOW	gui_agents/s1/core/Worker.py	85	CODE
LOW	gui_agents/s1/core/AgentS.py	187	CODE
LOW	gui_agents/s1/utils/common_utils.py	193	CODE
LOW	gui_agents/s1/utils/common_utils.py	466	CODE
LOW	gui_agents/s1/utils/common_utils.py	515	CODE
LOW	gui_agents/s1/utils/common_utils.py	556	CODE
LOW	gui_agents/s1/utils/common_utils.py	595	CODE
LOW	gui_agents/s1/aci/LinuxOSACI.py	581	CODE
LOW	gui_agents/s1/aci/LinuxOSACI.py	140	CODE
LOW	gui_agents/s1/aci/LinuxOSACI.py	225	CODE
LOW	gui_agents/s1/aci/WindowsOSACI.py	26	CODE
LOW	gui_agents/s1/aci/WindowsOSACI.py	104	CODE
LOW	gui_agents/s1/aci/MacOSACI.py	125	CODE
LOW	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	105	CODE
LOW	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	187	CODE
LOW	gui_agents/s1/mllm/MultimodalAgent.py	22	CODE
LOW	gui_agents/s1/mllm/MultimodalAgent.py	108	CODE
LOW	gui_agents/s2_5/cli_app.py	48	CODE
LOW	gui_agents/s2_5/cli_app.py	154	CODE
LOW	gui_agents/s2_5/core/mllm.py	18	CODE
LOW	gui_agents/s2_5/core/mllm.py	112	CODE
LOW	gui_agents/s2_5/agents/worker.py	75	CODE
LOW	gui_agents/s2_5/utils/common_utils.py	44	CODE
LOW	osworld_setup/s2/run.py	160	CODE
LOW	osworld_setup/s2/run.py	305	CODE
LOW	osworld_setup/s2/run.py	342	CODE
LOW	osworld_setup/s3/run.py	80	CODE
LOW	osworld_setup/s3/run.py	362	CODE
LOW	osworld_setup/s3/run.py	462	CODE
LOW	osworld_setup/s3/run.py	499	CODE
LOW	osworld_setup/s3/run_local.py	176	CODE
LOW	osworld_setup/s3/run_local.py	303	CODE
LOW	osworld_setup/s3/run_local.py	340	CODE
LOW	osworld_setup/s3/bbon/run_judge.py	78	CODE
LOW	osworld_setup/s3/bbon/generate_facts.py	145	CODE
LOW	osworld_setup/s3/bbon/utils.py	50	CODE
LOW	osworld_setup/s3/bbon/utils.py	163	CODE
LOW	osworld_setup/s1/run.py	121	CODE
LOW	osworld_setup/s1/run.py	241	CODE
LOW	osworld_setup/s1/run.py	278	CODE
LOW	osworld_setup/s2_5/run.py	76	CODE
LOW	osworld_setup/s2_5/run.py	356	CODE
LOW	osworld_setup/s2_5/run.py	456	CODE
LOW	osworld_setup/s2_5/run.py	493	CODE
LOW	osworld_setup/s2_5/run_local.py	176	CODE
LOW	osworld_setup/s2_5/run_local.py	306	CODE
1 more matches not shown…

Hyper-Verbose Identifiers49 hits · 48 pts

Severity	File	Line	Snippet	Context
LOW	gui_agents/s2/core/knowledge.py	161	def retrieve_narrative_experience(self, instruction: str) -> Tuple[str, str]:	CODE
LOW	gui_agents/s2/core/knowledge.py	198	def retrieve_episodic_experience(self, instruction: str) -> Tuple[str, str]:	CODE
LOW	gui_agents/s2/core/knowledge.py	312	def initialize_task_trajectory(self, instruction: str) -> None:	CODE
LOW	gui_agents/s2/core/knowledge.py	338	def handle_subtask_trajectory(self, meta_data: Dict) -> None:	CODE
LOW	gui_agents/s2/memory/procedural_memory.py	8	def construct_worker_procedural_memory(agent_class, skipped_actions):	CODE
LOW	gui_agents/s2/agents/worker.py	247	def clean_worker_generation_for_reflection(self, worker_generation: str) -> str:	STRING
LOW	gui_agents/s2/agents/manager.py	100	def _generate_step_by_step_plan(	CODE
LOW⚡	gui_agents/s2/utils/common_utils.py	129	def parse_single_code_from_string(input_string):	CODE
LOW	gui_agents/s2/utils/common_utils.py	189	def extract_first_agent_function(code_string):	CODE
LOW	gui_agents/s3/memory/procedural_memory.py	13	def construct_simple_worker_procedural_memory(agent_class, skipped_actions):	STRING
LOW	gui_agents/s3/bbon/behavior_narrator.py	85	def get_mouse_action_representation(mouse_actions: list[str]) -> str:	CODE
LOW	gui_agents/s3/bbon/comparative_judge.py	10	def get_final_screenshot_file(task_dir: str) -> str:	CODE
LOW	gui_agents/s3/bbon/comparative_judge.py	31	def image_to_openai_message_format(	CODE
LOW	gui_agents/s1/core/ProceduralMemory.py	7	def construct_worker_procedural_memory(agent_class):	CODE
LOW	gui_agents/s1/core/Knowledge.py	154	def retrieve_narrative_experience(self, instruction: str) -> Tuple[str, str]:	CODE
LOW	gui_agents/s1/core/Knowledge.py	190	def retrieve_episodic_experience(self, instruction: str) -> Tuple[str, str]:	CODE
LOW	gui_agents/s1/core/Manager.py	86	def _generate_step_by_step_plan(	CODE
LOW	gui_agents/s1/utils/ocr_server.py	19	def text_cvt_orc_format_paddle(paddle_result):	CODE
LOW⚡	gui_agents/s1/utils/common_utils.py	595	def parse_action_from_fixed_code(action_string, linearized_accessibility_tree):	CODE
LOW⚡	gui_agents/s1/utils/common_utils.py	599	def parse_action_from_agent_code(action_str):	CODE
LOW	gui_agents/s1/utils/common_utils.py	360	def linearize_accessibility_tree(accessibility_tree, platform="ubuntu", tag=False):	CODE
LOW	gui_agents/s1/utils/common_utils.py	466	def parse_actions_from_string(input_string):	CODE
LOW	gui_agents/s1/utils/common_utils.py	500	def parse_fixed_action_from_string(input_string):	CODE
LOW	gui_agents/s1/utils/common_utils.py	556	def parse_single_code_from_string(input_string):	CODE
LOW	gui_agents/s1/utils/common_utils.py	695	def parse_code_from_som_string(input_string, masks):	CODE
LOW	gui_agents/s1/utils/common_utils.py	769	def text_cvt_orc_format_paddle(paddle_result):	CODE
LOW	gui_agents/s1/utils/common_utils.py	829	def extract_first_agent_function(code_string):	CODE
LOW	gui_agents/s1/aci/LinuxOSACI.py	199	def extract_elements_from_screenshot(self, screenshot) -> Dict:	STRING
LOW	gui_agents/s1/aci/LinuxOSACI.py	301	def linearize_and_annotate_tree(self, obs, show_all=False):	CODE
LOW	gui_agents/s1/aci/WindowsOSACI.py	89	def extract_elements_from_screenshot(self, screenshot: bytes) -> Dict[str, Any]:	CODE
LOW⚡	gui_agents/s1/aci/WindowsOSACI.py	186	def linearize_and_annotate_tree(	CODE
LOW	gui_agents/s1/aci/ACI.py	30	def linearize_and_annotate_tree(	CODE
LOW	gui_agents/s1/aci/MacOSACI.py	110	def extract_elements_from_screenshot(self, screenshot: bytes) -> Dict[str, Any]:	CODE
LOW	gui_agents/s1/aci/MacOSACI.py	207	def linearize_and_annotate_tree(	CODE
LOW	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	163	def extract_elements_from_screenshot(self, screenshot) -> Dict:	STRING
LOW	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	263	def linearize_and_annotate_tree(self, obs, show_all=False):	CODE
LOW	gui_agents/s2_5/memory/procedural_memory.py	7	def construct_simple_worker_procedural_memory(agent_class, skipped_actions):	CODE
LOW	gui_agents/s2_5/utils/common_utils.py	44	def parse_single_code_from_string(input_string):	CODE
LOW	gui_agents/s2_5/utils/common_utils.py	98	def extract_first_agent_function(code_string):	CODE
LOW	tests/test_providers.py	22	def test_ollama_missing_config(self):	CODE
LOW	tests/test_providers.py	28	def test_ollama_valid_config_param(self):	CODE
LOW	tests/test_providers.py	40	def test_ollama_valid_config_env(self):	CODE
LOW	osworld_setup/s3/bbon/generate_facts.py	14	async def generate_single_fact_caption(	CODE
LOW	osworld_setup/s3/bbon/generate_facts.py	59	async def generate_fact_captions_parallel(	CODE
LOW	osworld_setup/s3/bbon/utils.py	10	def image_to_openai_message_format(	CODE
LOW	osworld_setup/s3/bbon/utils.py	107	def get_final_screenshot_file(result_dir: str) -> str:	CODE
LOW⚡	osworld_setup/s3/bbon/utils.py	163	def get_new_tasks_classification(results_dirs: [str]):	CODE
LOW	osworld_setup/s3/bbon/utils.py	229	def check_selected_trajectory(results_dirs: [str], selected_trajectory: str, task: str):	CODE
LOW	osworld_setup/s3/bbon/utils.py	268	def evaluate_comparative_results(results_dirs: [str], json_path: str = None):	CODE

Structural Annotation Overuse18 hits · 36 pts

Severity	File	Line	Snippet	Context
LOW	osworld_setup/s2/OSWorld.md	3	# Step 1: Set up Agent S2	COMMENT
LOW	osworld_setup/s2/OSWorld.md	7	# Step 2: Copying Over Run Files	COMMENT
LOW	osworld_setup/s3/run.sh	1	# Step 1: Complete 2 or more rollouts on either AWS or locally	COMMENT
LOW⚡	osworld_setup/s3/run.sh	36	# Step 2: Generate Facts	COMMENT
LOW⚡	osworld_setup/s3/run.sh	45	# Step 3: Run the Judge. Make sure the order of the results-dirs is the same as the order above.	COMMENT
LOW⚡	osworld_setup/s3/OSWorld.md	3	# Step 1: Set up Agent S3	COMMENT
LOW⚡	osworld_setup/s3/OSWorld.md	7	# Step 2: Copying Over Run Files	COMMENT
LOW⚡	osworld_setup/s3/OSWorld.md	11	# Step 3: Switch the AMI	COMMENT
LOW⚡	osworld_setup/s3/OSWorld.md	15	# Step 4: Generating Facts	COMMENT
LOW	osworld_setup/s3/OSWorld.md	31	# Step 5: Run the Judge	COMMENT
LOW⚡	osworld_setup/s3/bbon/utils.py	164	# Step 1: collect domain/task_ids for each trajectory	COMMENT
LOW⚡	osworld_setup/s3/bbon/utils.py	178	# Step 2: find tasks common to all trajectories	COMMENT
LOW⚡	osworld_setup/s3/bbon/utils.py	187	# Step 3: evaluate each common task	COMMENT
LOW⚡	osworld_setup/s1/OSWorld.md	3	# Step 1: Set up Agent S	COMMENT
LOW⚡	osworld_setup/s1/OSWorld.md	7	# Step 2: Copying Over Run Files	COMMENT
LOW⚡	osworld_setup/s1/OSWorld.md	14	# Step 3: Best Practices	COMMENT
LOW	osworld_setup/s2_5/OSWorld.md	3	# Step 1: Set up Agent S2.5	COMMENT
LOW	osworld_setup/s2_5/OSWorld.md	7	# Step 2: Copying Over Run Files	COMMENT

Redundant / Tautological Comments22 hits · 33 pts

Severity	File	Line	Snippet	Context
LOW	gui_agents/s2/cli_app.py	160	# Check if we're in paused state and wait	COMMENT
LOW	gui_agents/s2/core/mllm.py	149	# Check if image_content is a list or a single image	COMMENT
LOW	gui_agents/s2/core/mllm.py	200	# Check if image_content is a list or a single image	COMMENT
LOW	gui_agents/s2/core/mllm.py	247	# Check if image_content is a list or a single image	COMMENT
LOW	gui_agents/s3/cli_app.py	161	# Check if we're in paused state and wait	COMMENT
LOW	gui_agents/s3/core/mllm.py	212	# Check if image_content is a list or a single image	COMMENT
LOW	gui_agents/s3/core/mllm.py	263	# Check if image_content is a list or a single image	COMMENT
LOW	gui_agents/s3/core/mllm.py	310	# Check if image_content is a list or a single image	COMMENT
LOW	gui_agents/s3/agents/code_agent.py	155	# Check if response is None or empty	COMMENT
LOW	gui_agents/s3/agents/grounding.py	450	# Check if text contains Unicode characters that pyautogui.write() can't handle	COMMENT
LOW	gui_agents/s1/cli_app.py	160	# Check if we're in paused state and wait	COMMENT
LOW	gui_agents/s1/utils/common_utils.py	254	# Check if the area only contains one color	COMMENT
LOW	gui_agents/s1/aci/MacOSACI.py	546	# Iterate through the list and print each application's name	COMMENT
LOW	gui_agents/s1/mllm/MultimodalAgent.py	130	# Check if image_content is a list or a single image	COMMENT
LOW	gui_agents/s1/mllm/MultimodalAgent.py	175	# Check if image_content is a list or a single image	COMMENT
LOW	gui_agents/s1/mllm/MultimodalAgent.py	222	# Check if image_content is a list or a single image	COMMENT
LOW	gui_agents/s2_5/cli_app.py	160	# Check if we're in paused state and wait	COMMENT
LOW	gui_agents/s2_5/core/mllm.py	149	# Check if image_content is a list or a single image	COMMENT
LOW	gui_agents/s2_5/core/mllm.py	200	# Check if image_content is a list or a single image	COMMENT
LOW	gui_agents/s2_5/core/mllm.py	247	# Check if image_content is a list or a single image	COMMENT
LOW	integrations/openclaw/agent_s_wrapper.py	165	# Output result	COMMENT
LOW	osworld_setup/s3/bbon/utils.py	134	# Check if file exists and is valid	COMMENT

Modern AI Meta-Vocabulary6 hits · 18 pts

Severity	File	Line	Snippet	Context
MEDIUM	gui_agents/s2/core/knowledge.py	55	# All three agents share a generic RAG prompt that asks the agent to provide information for UI automation in CU	COMMENT
MEDIUM	gui_agents/s2/agents/worker.py	114	# Get RAG knowledge, only update system message at t=0	COMMENT
MEDIUM	gui_agents/s3/agents/grounding.py	573	# This is a full task - use the original task instruction to prevent hallucination	COMMENT
MEDIUM	gui_agents/s1/core/Worker.py	125	# Get RAG knowledge, only update system message at t=0	COMMENT
MEDIUM	gui_agents/s1/core/Worker.py	127	# TODO: uncomment and fix for subtask level RAG	COMMENT
MEDIUM	gui_agents/s1/core/Knowledge.py	56	# All three agent share a generic RAG prompt that ask agent to provide information for UI automation in CURRENT_	COMMENT

Unused Imports17 hits · 17 pts

Severity	File	Line	Context
LOW	gui_agents/s2/agents/manager.py	11	CODE
LOW	gui_agents/s1/core/Worker.py	2	CODE
LOW	gui_agents/s1/utils/query_perplexica.py	2	CODE
LOW	gui_agents/s1/aci/MacOSACI.py	11	CODE
LOW	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	3	CODE
LOW	gui_agents/s1/mllm/MultimodalEngine.py	6	CODE
LOW	gui_agents/s1/mllm/MultimodalEngine.py	11	CODE
LOW	gui_agents/s1/mllm/MultimodalAgent.py	6	CODE
LOW	tests/test_providers.py	3	CODE
LOW	osworld_setup/s2/lib_run_single.py	6	CODE
LOW	osworld_setup/s3/lib_run_single.py	6	CODE
LOW	osworld_setup/s3/lib_run_single.py	7	CODE
LOW	osworld_setup/s1/lib_run_single.py	6	CODE
LOW	osworld_setup/s2_5/lib_run_single_local.py	6	CODE
LOW	osworld_setup/s2_5/lib_run_single_local.py	7	CODE
LOW	osworld_setup/s2_5/lib_run_single.py	6	CODE
LOW	osworld_setup/s2_5/lib_run_single.py	7	CODE

Verbosity Indicators6 hits · 13 pts

Severity	File	Line	Snippet	Context
LOW	osworld_setup/s3/run.sh	1	# Step 1: Complete 2 or more rollouts on either AWS or locally	COMMENT
LOW⚡	osworld_setup/s3/run.sh	36	# Step 2: Generate Facts	COMMENT
LOW⚡	osworld_setup/s3/run.sh	45	# Step 3: Run the Judge. Make sure the order of the results-dirs is the same as the order above.	COMMENT
LOW⚡	osworld_setup/s3/bbon/utils.py	164	# Step 1: collect domain/task_ids for each trajectory	COMMENT
LOW⚡	osworld_setup/s3/bbon/utils.py	178	# Step 2: find tasks common to all trajectories	COMMENT
LOW⚡	osworld_setup/s3/bbon/utils.py	187	# Step 3: evaluate each common task	COMMENT

Slop Phrases3 hits · 6 pts

Severity	File	Line	Snippet	Context
MEDIUM	gui_agents/s2/memory/procedural_memory.py	88	- If you feel some future subtasks are incorrect or unnecessary, feel free to modify or even remove them.	CODE
MEDIUM	gui_agents/s1/core/Worker.py	159	# Clear older messages - we keep full context. if you want to keep only the last n messages, you can use the flu	COMMENT
LOW	gui_agents/s1/core/ProceduralMemory.py	60	# MANAGER_PROMPT = """You are a planning agent for solving GUI navigation tasks. You will be provided the initial co	STRING

Modern Structural Boilerplate5 hits · 5 pts

Severity	File	Line	Snippet	Context
LOW	gui_agents/s2/core/knowledge.py	322	def update_task_trajectory(self, meta_data: Dict) -> None:	CODE
LOW	gui_agents/s2/agents/agent_s.py	66	def update_narrative_memory(self, trajectory: str) -> None:	CODE
LOW	gui_agents/s2/agents/agent_s.py	339	def update_narrative_memory(self, trajectory: str) -> None:	CODE
LOW	gui_agents/s1/core/AgentS.py	61	def update_narrative_memory(self, trajectory: str) -> None:	CODE
LOW	gui_agents/s1/core/AgentS.py	296	def update_narrative_memory(self, trajectory: str) -> None:	CODE

Docstring Block Structure1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	gui_agents/s3/utils/common_utils.py	16	Attempts to evaluate the code into a pyautogui code snippet with grounded actions using the observation screenshot.	STRING

Self-Referential Comments1 hit · 4 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	gui_agents/s1/utils/common_utils.py	609	# Define a regex pattern to extract the action type and parameters	COMMENT

Over-Commented Block4 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	421	# if overwrite:	COMMENT
LOW	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	441		COMMENT
LOW	gui_agents/s1/aci/windowsagentarena/GroundingAgent.py	461	# node = self.find_element(0)	COMMENT
LOW	gui_agents/s1/mllm/MultimodalEngine.py	21	# tokenizer_image_token,	COMMENT

AI Structural Patterns3 hits · 3 pts

Severity	File	Line	Context
LOW	gui_agents/s2/agents/agent_s.py	90	CODE
LOW	gui_agents/s3/bbon/behavior_narrator.py	271	CODE
LOW	gui_agents/s1/mllm/MultimodalEngine.py	40	CODE

AI Slop Vocabulary1 hit · 3 pts

Severity	File	Line	Snippet	Context
MEDIUM	gui_agents/s1/core/ProceduralMemory.py	66	# MANAGER_PROMPT = """You are an expert planning agent for GUI tasks. You will be provided with an initial state of	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings