anthropics/axt-verify

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*

6.2ABCDE

for people · measured on 7 of 10 sub-scores

Ease of change*

6.9ABCDE

for AI · measured on 7 of 9 sub-scores

Duplication

<1%good

of main code duplicated

Complex units

16%high

of unit code with McCabe > 25

Long units

28%high

of unit code in units > 50 lines

Large files

25%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.

Human6.2ABCDE

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

Unit complexity4.9−1.216% 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.
Unit size4.6−1.028% 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.
File complexity5.0−0.625% 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.
File size5.8−0.325% 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.
Volume9.73,178 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.
Duplication9.8<1% 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.
Test code9.484 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.

AI6.9ABCDE

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

File size5.8−0.825% 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.
Unit size4.6−0.728% 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 complexity4.9−0.616% 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.
File complexity5.0−0.425% 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.
Test code9.4−0.184 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.
Volume9.73,178 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.
Duplication9.8<1% 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.

Where to look first

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

1
verifier.go
McCabe 234791 LOC
2
main.go
cmd/axt-verify/
McCabe 92351 LOC
3
leaf.go
leaf/
McCabe 91356 LOC
4
client.go
compliance/
McCabe 78309 LOC
5
events.go
cmd/axt-verify/
McCabe 75271 LOC
6
checkpoint.go
checkpoint/
McCabe 52199 LOC
7
server.go
internal/testlog/
McCabe 52256 LOC
8
trust.go
cmd/axt-verify/
McCabe 30108 LOC
9
testlog.go
internal/testlog/
McCabe 30140 LOC
10
state.go
McCabe 26123 LOC

Explore all files →

Standard analyses:
		Main Code: 3,178 LOC (20 files) = GO (99%) + YAML (<1%) Secondary code: Test: 2,661 LOC (12); Generated: 0 LOC (0); Build & Deploy: 59 LOC (4); Other: 342 LOC (5);
		Duplication: <1%
		File Size: 0% long (>1000 LOC), 26% short (<= 200 LOC)
		Logical Component Decomposition: primary (7 components)
		Goals: Keep the system simple and easy to change (4)

Experimental analyses (less reliable heuristic analyses):
		Unit Size: 15% long (>100 LOC), 37% short (<= 10 LOC)
		Conditional Complexity: 15% complex (McCabe index > 50), 34% simple (McCabe index <= 5)
		Static Component Dependencies: primary (7 components)