• There are 12 files with 1,211 lines of code.
• 0 very long files (0 lines of code)
• 0 long files (0 lines of code)
• 2 medium size files (454 lines of code)
• 3 small files (395 lines of code)
• 7 very small files (362 lines of code)

File	# lines	≈ tokens to read	# changes (1y)	≈ lines edited per change	lines read per line changed
evaluation.go in model-runner	242	~1.5k–5k	4	~100	~3
main.go in data-preparation	212	~1k–3k	4	~100	~2
main.go in model-runner	154	~1k–3k	3	~70	~2
recipeschema.go in schema	77	~500–1.5k	2	~50	~2
models.go in model-runner	139	~700–2k	1	~200	~1
bedrock.go in model-runner	64	~300–1k	2	~30	~2
sonnet.go in sonnet	62	~300–1k	2	~30	~2
prompts.go in common	102	~700–1.5k	1	~100	~1
parser.go in schema	36	under 1k	2	~30	~2
main.go in reportaverages	62	~300–1k	1	~70	~1
datasearch.go in common	36	under 1k	1	~50	~1
tuning_models.go in common	25	under 1k	1	~30	~1

Tokens are lines × 7 to 14 (analysis.fileReadsForChanges). Lines edited per change are the file's lines added and deleted divided by its commits over the whole history. Agents read about 2,000 lines at a time: when a 17,000-line file was split into modules, the tokens an agent read for the same change fell by 83% (The Economic Benefit of Refactoring, 2026).

There are 6 files with lines longer than 120 characters. In total, there are 30 long lines.

File	# lines	# units	# long lines
evaluation.go in model-runner	242	7	24
main.go in model-runner	154	6	2
main.go in reportaverages	62	1	1
main.go in data-preparation	212	8	1
prompts.go in common	102	-	1
sonnet.go in sonnet	62	2	1

• File size measurements show the distribution of size of files.
• Files are classified in four categories based on their size (lines of code): 1-100 (very small files), 101-200 (small files), 201-500 (medium size files), 501-1000 (long files), 1001+(very long files).
• It is a good practice to keep files small. Long files may become "bloaters", code that have increased to such gargantuan proportions that they are hard to work with.