Edition of Thursday 12 November 2026

What a Coding Agent Costs

Comments on “What a Coding Agent Costs”

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

A developer built smelt, an open-source coding agent, and wrote a benchmark measuring CPU and memory across seven agents using a scripted model for identical runs on the same hardware. Memory at idle ranged from 5.8 MiB (fx) to 430 MiB (opencode).

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

Why it ranked

No. 104 of 106 with a score of 0.55. The panel rated it highest on substantiated (0.83) and new information (0.79), lowest on significance (0.40). Placed No. 104, No. 105 by score alone: the 16th Programming & dev tools story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
A self-authored benchmark of coding agent resource costs with transparent methodology and limits; useful engineering measurements, but narrow scope, self-interest, and a new side project.
AI judgeJudge 3gpt-5.6-luna
A reproducible, open benchmark compares coding-agent CPU and memory costs with concrete methodology and caveats. It is practically useful for agent builders, though limited to one machine, scripted workloads, and an early project.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.55total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.40
  • Reader interest0.71
  • Audience breadth0.53
  • Practical relevance0.66
  • Substantiated0.83
  • Technical depth0.71
  • New information0.79
  • Counts against: Promotional0.18
  • Counts against: Overclaim0.22

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

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.470.300.420.400.17+0.24+0.095
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.680.600.860.710.26+0.26+0.185
Audience breadthHow many people who build technology does it concern?0.600.400.580.530.20+0.13+0.068
Practical relevanceHow useful is it to someone who builds software or tech products?0.700.550.710.660.16+0.22+0.144
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.960.700.840.830.26+0.05+0.042
Technical depthHow technically substantive is it?0.820.700.620.710.20+0.05+0.036
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.820.600.960.790.36+0.05+0.040
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.100.350.080.180.27−0.19−0.034
OverclaimDo the headline or conclusions claim more than the body supports?0.270.300.100.220.20−0.11−0.025
Sum of contributions+0.552
Claim-check penalty0.000
Total, as published0.552

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

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #104 on Rubric, 12 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-12/104/"><img src="https://rubric.hrih.si/badge/2026-11-12/104.svg" alt="Ranked #104 on Rubric, 12 Nov 2026" width="252" height="28"></a>

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 12 Nov 2026, 05:47 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. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “What a Coding Agent Costs”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.

  1. Score 0.75

    llama.cpp v1.0