• There are 10 files with 3,959 lines of code.
• 1 very long files (1,414 lines of code)
• 1 long files (504 lines of code)
• 5 medium size files (1,905 lines of code)
• 1 small files (119 lines of code)
• 2 very small files (17 lines of code)

File	# lines	≈ tokens to read	# changes (1y)	≈ lines edited per change	lines read per line changed
encoding.rs in src	1414	~7k–20k	2	~200	~7
__init__.py in python/openai_harmony	472	~3k–7k	1	~10	~50
wasm_module.rs in src	334	~2k–5k	1	~15	~20
py_module.rs in src	323	~2k–5k	1	~10	~30
lib.rs in src	15	under 1k	1	~2	~7

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 4 files with lines longer than 120 characters. In total, there are 10 long lines.

File	# lines	# units	# long lines
public_encodings.rs in src/tiktoken_ext	504	13	5
chat.rs in src	411	10	3
wasm_module.rs in src	334	-	1
encoding.rs in src	1414	21	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.