anthropics/claude-cookbooks
File Complexity*
The distribution of files by complexity: the sum of the McCabe indexes of their units.
File Complexity Overall
  • There are 88 files with units, with 13,670 lines of code.
    • 0 very complex files (McCabe index sum 251+; 0 lines of code)
    • 1 complex files (McCabe index sum 126-250; 632 lines of code)
    • 7 medium complex files (McCabe index sum 51-125; 1,733 lines of code)
    • 14 slightly complex files (McCabe index sum 26-50; 2,915 lines of code)
    • 66 simple files (McCabe index sum 1-25; 8,390 lines of code)
  • 95 main files have no units (e.g. languages without unit analysis, or files without functions) and are not classified.
system0% | 4% | 12% | 21% | 61%
Legend:
251+
126-250
51-125
26-50
1-25


explore: grouped by folders | grouped by complexity
File Complexity per Extension
251+
126-250
51-125
26-50
1-25
py0% | 4% | 13% | 20% | 61%
ts0% | 0% | 0% | 52% | 47%
c0% | 0% | 0% | 0% | 100%
File Complexity per Logical Decomposition
primary
251+
126-250
51-125
26-50
1-25
scripts0% | 85% | 0% | 0% | 14%
claude_agent_sdk0% | 0% | 9% | 8% | 81%
tool_use0% | 0% | 19% | 29% | 50%
.claude0% | 0% | 100% | 0% | 0%
capabilities0% | 0% | 13% | 9% | 76%
.github0% | 0% | 100% | 0% | 0%
skills0% | 0% | 0% | 55% | 44%
managed_agents0% | 0% | 0% | 46% | 53%
evals0% | 0% | 0% | 0% | 100%
patterns0% | 0% | 0% | 0% | 100%
Most Complex Files (Top 50)

The McCabe index of a file grows with its size: per 100 lines tells a large but plain file from a dense one, and most complex unit whether the complexity sits in one unit or is spread over many.

File# lines# unitsMcCabe index
(sum)		per 100
lines		most complex
unit
632 14 194 31 36
agent_visualizer.py
in claude_agent_sdk/utils
 285 8 124 44 46
validate_notebook.py
in .claude/skills/cookbook-audit
 346 17 96 28 25
html_renderer.py
in claude_agent_sdk/utils
 220 19 88 40 28
engine.py
in capabilities/content_moderation
 222 7 85 38 28
visualize.py
in tool_use/utils
 247 16 76 31 11
memory_tool.py
in tool_use
 207 10 69 33 16
verify_registry.py
in .github/scripts
 206 7 59 29 20
validate_brand.py
in skills/custom_skills/applying-brand-guidelines
 185 11 45 24 10
184 9 44 24 24
interpret_ratios.py
in skills/custom_skills/analyzing-financial-statements
 260 9 44 17 15
calculate_ratios.py
in skills/custom_skills/analyzing-financial-statements
 231 12 41 18 17
vectordb.py
in capabilities/retrieval_augmented_generation/evaluation
 149 12 40 27 6
customer_service_tools.py
in tool_use/utils
 209 12 37 18 11
tools.py
in managed_agents/mongodb_on_cma
 201 15 34 17 12
file_utils.py
in skills
 126 5 34 27 25
scheduled_review.py
in claude_agent_sdk/scheduled_repository_reviewer
 340 11 33 10 11
talent_scorer.py
in claude_agent_sdk/chief_of_staff_agent/scripts
 119 5 32 27 10
ap2_mandates.py
in managed_agents/mongodb_on_cma
 169 6 31 18 22
webhook.ts
in managed_agents/self_hosted_sandboxes/vercel/api
 275 12 31 11 8
research_corpus.py
in tool_use/context_engineering
 275 1 29 11 29
code_review_demo.py
in tool_use/memory_demo
 192 9 27 14 13
customer_service_api.py
in tool_use/utils
 289 6 24 8 10
dcf_model.py
in skills/custom_skills/creating-financial-models
 289 12 23 8 6
apply_brand.py
in skills/custom_skills/applying-brand-guidelines
 286 10 23 8 7
vectordb.py
in capabilities/classification/evaluation
 63 4 22 35 12
embeddings.py
in managed_agents/mongodb_on_cma
 96 12 22 23 4
demo_helpers.py
in tool_use/memory_demo
 133 4 21 16 16
decision_matrix.py
in claude_agent_sdk/chief_of_staff_agent/scripts
 217 3 20 9 11
prompts.py
in capabilities/retrieval_augmented_generation/evaluation
 100 7 19 19 10
39 2 19 49 10
eval_extraction.py
in capabilities/knowledge_graph/evaluation
 103 5 18 17 10
data_processor_v1.py
in tool_use/memory_demo/sample_code
 77 9 17 22 4
provider_retrieval.py
in capabilities/retrieval_augmented_generation/evaluation
 94 4 17 18 10
team_expense_api.py
in tool_use/utils
 435 4 16 4 10
run_eval.py
in capabilities/content_moderation/evaluation
 86 3 15 17 9
infra_setup.py
in claude_agent_sdk/site_reliability_agent
 552 8 15 3 5
build_creatives.py
in capabilities/content_moderation/data/ad_creatives
 108 8 14 13 4
vectordb.py
in capabilities/text_to_sql/evaluation
 54 5 14 26 6
container.ts
in managed_agents/self_hosted_sandboxes/cf/src
 67 5 14 21 5
64 5 14 22 5
agentic_search.py
in evals/agentic_search/utils
 137 5 13 9 6
canary.c
in claude_agent_sdk/vulnerability_detection_agent/canary
 39 4 13 33 7
financial_forecast.py
in claude_agent_sdk/chief_of_staff_agent/scripts
 99 4 13 13 6
pipeline.py
in capabilities/content_moderation
 159 7 12 8 3
eval_retrieval.py
in capabilities/retrieval_augmented_generation/evaluation
 87 3 12 14 5
prompts.py
in capabilities/text_to_sql/evaluation
 57 5 12 21 5
s3_adapter.py
in capabilities/contextual-embeddings/contextual-rag-lambda-function
 35 4 11 31 4
lambda_function.py
in capabilities/contextual-embeddings/contextual-rag-lambda-function
 57 1 11 19 11
runner.ts
in managed_agents/self_hosted_sandboxes/cf-worker/src
 73 6 11 15 3
About This Analysis
  • File complexity is the sum of the McCabe indexes (conditional complexity) of the units (methods, functions...) in a file.
  • Files are classified in five categories based on that sum: 1-25 (simple files), 26-50 (slightly complex files), 51-125 (medium complex files), 126-250 (complex files), 251+ (very complex files). The default bands are five times the unit complexity bands, as a file is a group of units.
  • Only main code files with units are classified. Files without units (languages without unit analysis, or files without functions) have no complexity to measure and are left out rather than counted as simple.
  • A very complex file holds many decisions, which often means it has too many responsibilities: a candidate to split, and a place where changes need more testing.
Learn more...