anthropics/commerce-agents

Rules of thumb, not measurements: one man-year rebuilds about 10,000 lines of main code (design, testing and coordination included), and keeping a code base alive takes about 15% of its rebuild value per year (20 man-years of rebuild value need about 3 man-years of maintenance every year). Your changes are remembered in this browser for every report.

Ease of change*

7.5ABCDE

for people · measured on 7 of 10 sub-scores

Ease of change*

7.1ABCDE

for AI · measured on 7 of 9 sub-scores

Duplication

11%high

of main code duplicated

Complex units

4%good

of unit code with McCabe > 25

Long units

16%watch

of unit code in units > 50 lines

Large files

26%watch

of main code in files > 500 lines

Goals

3 / 4high

controls in range

Ease of change*

How easily the code can be understood and changed, from 0 to 10. Other things equal, less code is easier and cheaper to change, for people and for agents. Both ratings weigh the same sub-scores: people struggle most with complex logic and knowledge held by few; agents pay for every line they read, copy duplicates and need tests to check their work. The total is a weighted geometric mean; above the weakest code sub-score + 4 only half of it counts, so one weak spot is not averaged away. Sub-scores are ordered by drag, how much the uncapped mean would rise if that sub-score were 10; click one to see why it matters. * A heuristic: compare repositories rather than read it as absolute. Set weights, or your own framework, in analysis.maintainabilityScores.

Human7.5ABCDE

Measured on 7 of 10 sub-scores (not measured: Change entropy, Context per change, Knowledge spread).

Unit size6.8−0.616% of unit code in units > 50 lines
For people: Long functions do many things at once: they are hard to name, read, test and reuse.
For AI agents: To change one line, an agent reads and often rewrites the whole function: bigger edits, more tokens, more breakage.
Duplication5.8−0.511% of main code duplicated
For people: A fix in one copy must be repeated in all the others; a missed copy becomes a bug.
For AI agents: Agents copy the patterns they find, so duplicates multiply; a change to one copy misses the others, and every copy costs context.
Unit complexity8.3−0.44% of unit code with McCabe > 25
For people: Every branch is another path to understand and test; complex logic is where mistakes are made and missed in review.
For AI agents: Nested conditions are where generated changes break edge cases; complex units need more tests and review before an agent's change can be trusted.
File size5.5−0.426% of main code in files > 500 lines
For people: Large files are hard to navigate, mix responsibilities and attract merge conflicts.
For AI agents: Agents read whole files into their context: every change to a large file costs many tokens and crowds out other relevant code.
Volume8.9−0.112,060 lines of main code
For people: More code is more to learn, search and keep in mind; onboarding and judging a change's impact slow down as it grows.
For AI agents: An agent sees only a slice at a time: the bigger the code base, the more it searches, and the likelier it misses relevant code or rewrites an existing helper.
File complexity8.8−0.16% of main code in files with McCabe sum > 125
For people: Complex files concentrate risk: understanding one means keeping many paths in mind.
For AI agents: Much to read and much logic to get right in one place: the costliest combination for an agent.
Test code8.6−0.162 test lines per 100 main lines
For people: Tests document the intended behaviour and make changes safe.
For AI agents: Tests let an agent check its own work; without them its mistakes surface later, in review or in production.

AI7.1ABCDE

Measured on 7 of 9 sub-scores (not measured: Change entropy, Context per change).

File size5.5−0.926% of main code in files > 500 lines
For AI agents: Agents read whole files into their context: every change to a large file costs many tokens and crowds out other relevant code.
For people: Large files are hard to navigate, mix responsibilities and attract merge conflicts.
Duplication5.8−0.711% of main code duplicated
For AI agents: Agents copy the patterns they find, so duplicates multiply; a change to one copy misses the others, and every copy costs context.
For people: A fix in one copy must be repeated in all the others; a missed copy becomes a bug.
Unit size6.8−0.316% of unit code in units > 50 lines
For AI agents: To change one line, an agent reads and often rewrites the whole function: bigger edits, more tokens, more breakage.
For people: Long functions do many things at once: they are hard to name, read, test and reuse.
Unit complexity8.3−0.24% of unit code with McCabe > 25
For AI agents: Nested conditions are where generated changes break edge cases; complex units need more tests and review before an agent's change can be trusted.
For people: Every branch is another path to understand and test; complex logic is where mistakes are made and missed in review.
Test code8.6−0.262 test lines per 100 main lines
For AI agents: Tests let an agent check its own work; without them its mistakes surface later, in review or in production.
For people: Tests document the intended behaviour and make changes safe.
Volume8.9−0.112,060 lines of main code
For AI agents: An agent sees only a slice at a time: the bigger the code base, the more it searches, and the likelier it misses relevant code or rewrites an existing helper.
For people: More code is more to learn, search and keep in mind; onboarding and judging a change's impact slow down as it grows.
File complexity8.8−0.16% of main code in files with McCabe sum > 125
For AI agents: Much to read and much logic to get right in one place: the costliest combination for an agent.
For people: Complex files concentrate risk: understanding one means keeping many paths in mind.

Where to look first

The most complex main files (no git history, so no change frequency).

1
check.py
scripts/
McCabe 207647 LOC
2
turn.py
commerce-common/commerce_common/
McCabe 109419 LOC
3
run_demo.py
scripts/
McCabe 85286 LOC
4
enrichment.py
merchant-agent/core/merchant_agent/
McCabe 83367 LOC
5
memory.py
commerce-common/commerce_common/
McCabe 55451 LOC
6
enrichment.py
shopping-agent/core/shopping_agent/
McCabe 53248 LOC
7
agent_sdk.py
commerce-common/commerce_common/
McCabe 48199 LOC
8
serialization.py
shopping-agent/core/shopping_agent/
McCabe 45104 LOC
9
streaming.py
commerce-common/commerce_common/
McCabe 41173 LOC
10
manifest.py
commerce-common/commerce_common/
McCabe 38143 LOC

Explore all files →

Standard analyses:
		Main Code: 12,060 LOC (75 files) = PY (95%) + YAML (3%) + TOML (<1%) Secondary code: Test: 7,464 LOC (49); Generated: 1,881 LOC (1); Build & Deploy: 357 LOC (13); Other: 53,013 LOC (420);
		Duplication: 10%
		File Size: 0% long (>1000 LOC), 36% short (<= 200 LOC)
		Logical Component Decomposition: primary (5 components)
		Goals: Keep the system simple and easy to change (4)

Experimental analyses (less reliable heuristic analyses):
		Unit Size: 6% long (>100 LOC), 62% short (<= 10 LOC)
		Conditional Complexity: 4% complex (McCabe index > 50), 54% simple (McCabe index <= 5)
		Static Component Dependencies: primary (5 components)