• There are 165 files with units, with 14,744 lines of code.
• 0 very complex files (McCabe index sum 251+; 0 lines of code)
• 3 complex files (McCabe index sum 126-250; 2,066 lines of code)
• 7 medium complex files (McCabe index sum 51-125; 2,495 lines of code)
• 18 slightly complex files (McCabe index sum 26-50; 2,976 lines of code)
• 137 simple files (McCabe index sum 1-25; 7,207 lines of code)
• 76 main files have no units (e.g. languages without unit analysis, or files without functions) and are not classified.

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	# units	McCabe index (sum)	per 100 lines	most complex unit
bot.js in agent-battle/bot	984	28	212	22	29
my_agent.py in agent-battle	614	18	153	25	22
cma.py in agent-decomposition/agents	468	23	152	32	44
probes.py in agent-battle/harness	405	14	104	26	13
graders.py in agent-decomposition/evals	204	16	94	46	27
ReplayPage.tsx in how-we-claude-code/phase-3-verify/src/verify/harness	581	11	79	14	42
cast.js in agent-battle/event/public/js	268	15	69	26	14
ChatPanel.tsx in production-ready-agent/solution/components	430	7	61	14	38
ChatPanel.tsx in production-ready-agent/starter/components	430	7	61	14	38
provided.py in ship-your-first-managed-agent	177	6	57	32	37
sandbox_tools.py in agent-decomposition/agents	152	18	50	33	10
replay.py in agent-battle/harness	126	7	45	36	29
client.py in agent-battle/harness	131	11	41	31	12
tools.py in agent-decomposition/agents/before	160	17	40	25	7
seed.py in agent-decomposition/data	221	9	37	17	8
DeskChat.tsx in research-desk/src/components	168	3	36	21	25
logging_.py in agent-battle/harness	201	12	34	17	8
run.py in agent-decomposition/evals	152	7	34	22	13
orchestrator.ts in research-desk/solutions/src/lib	180	8	33	18	8
recorder.ts in how-we-claude-code/phase-3-verify/src/verify/harness	173	12	33	19	6
agent.py in agent-battle/harness	355	10	32	9	11
parse-pptx.ts in eval-driven-agent-development/src	185	7	30	16	12
eval-runner.ts in eval-driven-agent-development/src	203	6	29	14	9
orchestrator.ts in research-desk/src/lib	158	6	28	18	7
leaderboard.py in agent-battle/harness	82	11	27	33	5
chat.ts in production-ready-agent/solution/lib	80	2	26	33	25
chat.ts in production-ready-agent/starter/lib	80	2	26	33	25
runner.ts in how-we-claude-code/phase-3-verify/src/verify/core	169	14	26	15	4
verify.py in agent-battle/harness	71	2	24	34	23
memory.ts in research-desk/src/lib	62	6	23	37	6
analysis.ts in research-desk/src/lib	151	8	23	15	10
generate_log.py in ship-your-first-managed-agent/data	123	9	23	19	6
analysis.ts in research-desk/solutions/src/lib	159	7	22	14	10
UnitPage.tsx in how-we-claude-code/phase-3-verify/src/verify/harness	140	3	21	15	19
prompts.py in agent-battle/harness	75	8	21	28	6
create-slides.ts in eval-driven-agent-development/src	129	2	21	16	13
a11y.ts in how-we-claude-code/phase-3-verify/src/verify/verifiers	88	3	20	23	9
common.py in agent-decomposition/agents	81	9	20	25	5
config.ts in research-desk/src/lib	89	8	19	21	4
seed.ts in research-desk/scripts	127	3	18	14	11
page.tsx in research-desk/src/app	63	1	18	29	18
provision.ts in research-desk/solutions/src/lib	176	7	16	9	4
sessions.ts in research-desk/solutions/src/lib	108	6	16	15	9
sessions.ts in research-desk/src/lib	104	6	16	15	9
relay-client.cjs in agent-battle/bot	71	3	16	23	13
subagents.py in agent-decomposition/agents/before	66	5	16	24	8
DeploymentsPanel.tsx in research-desk/src/components	117	2	15	13	10
visibleAct.ts in how-we-claude-code/phase-3-verify/src/verify/harness	83	8	15	18	4
agent_complete.py in ship-your-first-managed-agent	77	7	15	19	6
report.py in agent-decomposition/evals	34	4	15	44	7

• 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.