I paired seven months of coding-agent transcripts with a token inventory

No. 168 of 245 · morkeeth.substack.com · Morkeeth · published 23 Oct 2026, 22:58 UTC · 12 min read

Programming & dev tools
AI & machine learning
Paper

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

A developer audited seven months of coding-agent logs (Claude Code and Codex) and found $33,807 in list-price token usage, with 42% spent on agents orchestrating other agents and only 15% on user-facing apps. Most of the cost was cache reads, meaning agents repeatedly re-sending large conversation contexts.

Read the original at morkeeth.substack.com. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Score

0.62total under rubric v2.0Contestedjudges differ by 0.47 on substantiated

Significance0.49
Reader interest0.81
Audience breadth0.58
Practical relevance0.81
Substantiated0.78
Technical depth0.78
New information0.82
Counts against: Promotional0.07
Counts against: Overclaim0.45

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

Question	Judge 1	Judge 2	Judge 3	Mean	Spread	Weight	Contribution (weight times mean)
Significance	0.50	0.30	0.68	0.49	0.38	+0.25	+0.124
Reader interest	0.72	0.80	0.91	0.81	0.19	+0.20	+0.162
Audience breadth	0.62	0.50	0.62	0.58	0.12	+0.10	+0.058
Practical relevance	0.91	0.70	0.83	0.81	0.20	+0.15	+0.122
Substantiated	0.97	0.50	0.86	0.78	0.47 , above the contested threshold	+0.10	+0.078
Technical depth	0.99	0.60	0.74	0.78	0.40	+0.10	+0.078
New information	0.89	0.60	0.97	0.82	0.37	+0.10	+0.082
Promotional	0.04	0.10	0.08	0.07	0.06	−0.15	−0.011
Overclaim	0.67	0.40	0.28	0.45	0.39	−0.15	−0.068
Sum of contributions							+0.624
Claim-check penalty							0.000
Total, as published							0.624

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 1 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.