yetone/avante.nvim

3.4

Adjusted Score

3.4

Raw Score

100%

Time Factor

2026-07-08

Last Push

18.0K

Stars

Lua

Language

50.1K

Lines of Code

186

Files

Pattern Hits

2026-07-14

Scan Date

0.09

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 17MEDIUM 10LOW 34

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 61 distinct pattern matches across 12 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.

Magic Placeholder Names15 hits · 105 pts

Severity	File	Line	Snippet	Context
HIGH⚡	README.md	925	> export ANTHROPIC_API_KEY=your-api-key	CODE
HIGH⚡	README.md	931	> export OPENAI_API_KEY=your-api-key	CODE
HIGH⚡	README.md	937	> export AZURE_OPENAI_API_KEY=your-api-key	CODE
HIGH	README.md	1154	export MORPH_API_KEY="your-api-key"	CODE
HIGH⚡	README_zh.md	631	> export ANTHROPIC_API_KEY=your-api-key	CODE
HIGH⚡	README_zh.md	637	> export OPENAI_API_KEY=your-api-key	CODE
HIGH⚡	README_zh.md	643	> export AZURE_OPENAI_API_KEY=your-api-key	CODE
HIGH⚡	lua/avante/init.lua	52	--- export ANTHROPIC_API_KEY=your-api-key	CODE
HIGH⚡	lua/avante/init.lua	53	--- export OPENAI_API_KEY=your-api-key	CODE
HIGH⚡	lua/avante/init.lua	54	--- export AZURE_OPENAI_API_KEY=your-api-key	CODE
HIGH	lua/avante/config.lua	144	--- export MORPH_API_KEY="your-api-key"	CODE
HIGH⚡	doc/avante.txt	52	export ANTHROPIC_API_KEY=your-api-key	CODE
HIGH⚡	doc/avante.txt	53	export OPENAI_API_KEY=your-api-key	CODE
HIGH⚡	doc/avante.txt	54	export AZURE_OPENAI_API_KEY=your-api-key	CODE
HIGH	doc/avante.txt	344	export MORPH_API_KEY="your-api-key"	CODE

Modern AI Meta-Vocabulary6 hits · 17 pts

Severity	File	Line	Snippet	Context
MEDIUM	README.md	1329	## RAG Service	COMMENT
MEDIUM	README.md	1653	### How to disable agentic mode?	COMMENT
MEDIUM	README_zh.md	804	## RAG 服务	COMMENT
MEDIUM	py/rag-service/README.md	1	# RAG Service Configuration	COMMENT
MEDIUM	py/rag-service/src/main.py	489	# Initialize embedding model and LLM based on provider using the factory	COMMENT
MEDIUM	lua/avante/providers/claude.lua	617	if prompt_opts.tools and #prompt_opts.tools > 0 and Config.mode == "agentic" then	CODE

Docstring Block Structure2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	py/rag-service/src/providers/factory.py	20	Initialize embedding model based on specified provider and configuration. Dynamically loads the provider modul	STRING
HIGH	py/rag-service/src/providers/factory.py	104	Create LLM model with the specified configuration. Dynamically loads the provider module based on the llm_prov	STRING

Redundant / Tautological Comments8 hits · 9 pts

Severity	File	Line	Snippet	Context
LOW	py/rag-service/src/main.py	418	# # Check if provider or model has changed	COMMENT
LOW	py/rag-service/src/main.py	594	# Check if the file was recently processed	COMMENT
LOW	py/rag-service/src/main.py	608	# Check if the text mainly contains printable characters	COMMENT
LOW	py/rag-service/src/main.py	632	# Check if document with same hash has already been successfully processed	COMMENT
LOW⚡	py/rag-service/src/main.py	1333	# Check if the file path starts with the specified directory	STRING
LOW⚡	py/rag-service/src/main.py	1336	# Check if directory is a parent of file_path	STRING
LOW	py/rag-service/src/main.py	1193	# Check if resource already exists	STRING
LOW	py/rag-service/src/services/indexing_history.py	64	# Check if record exists	COMMENT

Deep Nesting6 hits · 6 pts

Severity	File	Line	Context
LOW	py/rag-service/src/main.py	182	CODE
LOW	py/rag-service/src/main.py	623	CODE
LOW	py/rag-service/src/main.py	734	CODE
LOW	py/rag-service/src/main.py	1311	CODE
LOW	py/rag-service/src/main.py	1327	CODE
LOW	py/rag-service/src/services/indexing_history.py	106	CODE

Excessive Try-Catch Wrapping5 hits · 6 pts

Severity	File	Line	Snippet	Context
LOW	py/rag-service/src/providers/factory.py	61	except Exception as err:	CODE
LOW	py/rag-service/src/providers/factory.py	88	except Exception as err:	CODE
LOW	py/rag-service/src/providers/factory.py	149	except Exception as e:	CODE
LOW	py/rag-service/src/providers/factory.py	171	except Exception as e:	CODE
MEDIUM	lua/avante/repo_map.lua	154	print("Error watching directory " .. project_root .. ":", err)	CODE

Hyper-Verbose Identifiers7 hits · 6 pts

Severity	File	Line	Snippet	Context
LOW	py/rag-service/src/main.py	980	def append_embedding_sized_documents(doc: Document, base_metadata: dict[str, object] \| None = None) -> None:	CODE
LOW	py/rag-service/src/main.py	1059	async def index_remote_resource_async(resource: Resource) -> None:	CODE
LOW	py/rag-service/src/main.py	1124	async def index_local_resource_async(resource: Resource) -> None:	CODE
LOW	py/rag-service/src/main.py	362	def is_remote_resource_exists(url: str) -> bool:	STRING
LOW	py/rag-service/src/main.py	1487	async def get_indexing_status_for_resource(request: IndexingStatusRequest): # noqa: D103, ANN201	STRING
LOW	py/rag-service/src/services/resource.py	29	def update_resource_indexing_status(self, uri: str, indexing_status: str, indexing_status_message: str) -> None:	CODE
LOW	py/rag-service/src/services/indexing_history.py	26	def delete_indexing_status_by_document_id(self, document_id: str) -> None:	CODE

Modern Structural Boilerplate4 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	py/rag-service/src/main.py	933	def update_index_for_file(directory: Path, abs_file_path: Path) -> None:	CODE
LOW	py/rag-service/src/libs/logger.py	16	logger = logging.getLogger(__name__)	CODE
LOW	py/rag-service/src/services/resource.py	29	def update_resource_indexing_status(self, uri: str, indexing_status: str, indexing_status_message: str) -> None:	CODE
LOW	py/rag-service/src/services/resource.py	52	def update_resource_status(self, uri: str, status: str, error: str \| None = None) -> None:	CODE

Unused Imports3 hits · 3 pts

Severity	File	Line	Context
LOW	py/rag-service/src/main.py	3	CODE
LOW	py/rag-service/src/providers/factory.py	8	CODE
LOW	py/rag-service/src/libs/utils.py	1	CODE

AI Slop Vocabulary2 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	lua/avante/suggestion.lua	188	L4: # just pass	CODE
MEDIUM	lua/avante/libs/acp_client.lua	5	---Avante.nvim now supports the Agent Client Protocol (ACP) (https://agentclientprotocol.com/overview/introduction), ena	CODE

Self-Referential Comments2 hits · 2 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	py/rag-service/src/main.py	1326	# Create a filter function to only include documents from the specified directory	STRING
MEDIUM	py/rag-service/src/main.py	1360	# Create a custom post processor	STRING

Over-Commented Block1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	.github/workflows/tests.yaml	61	# docker_platform: linux/amd64	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings