Edition of Monday 16 November 2026

Codemode in Claude Code

Comments on “Codemode in Claude Code”

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

Anthropic's Claude Code documentation describes Code Mode, an experimental setting where Claude writes and runs JavaScript that batches tool calls such as Bash, Read, and Edit, rather than calling each tool one at a time. It can run commands in parallel and return only the output Claude needs.

Read the original at code.claude.com. 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. 54 of 60 with a score of 0.56. The panel rated it highest on new information (0.82) and practical relevance (0.75), lowest on audience breadth (0.44). Placed No. 54, No. 53 by score alone: the twelfth 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
Product documentation for an AI coding agent's Code Mode feature: practically useful to developers using it, with detailed mechanics and limits, but it is vendor docs with little broader significance and is largely how-to rather than new research.
AI judgeJudge 3gpt-5.6-luna
A detailed feature announcement and operational guide for agentic coding workflows, with concrete execution, permissions, hooks, limits, compatibility, and troubleshooting information. It is highly actionable, though specific to one coding environment.

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

0.56total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.50
  • Reader interest0.61
  • Audience breadth0.44
  • Practical relevance0.75
  • Substantiated0.61
  • Technical depth0.73
  • New information0.82
  • Counts against: Promotional0.16
  • Counts against: Overclaim0.13

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?0.540.350.620.500.27+0.24+0.121
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.550.500.780.610.28+0.26+0.159
Audience breadthHow many people who build technology does it concern?0.250.500.580.440.33+0.13+0.057
Practical relevanceHow useful is it to someone who builds software or tech products?0.830.600.820.750.23+0.22+0.165
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.0.650.450.720.610.27+0.05+0.030
Technical depthHow technically substantive is it?0.920.600.680.730.32+0.05+0.037
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.860.700.900.820.20+0.05+0.041
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.0.070.300.120.160.23−0.19−0.031
OverclaimDo the headline or conclusions claim more than the body supports?0.100.200.080.130.12−0.11−0.014
Sum of contributions+0.565
Claim-check penalty0.000
Total, as published0.565

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 #54 on Rubric, 16 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-16/54/"><img src="https://rubric.hrih.si/badge/2026-11-16/54.svg" alt="Ranked #54 on Rubric, 16 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 2 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 16 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 “Codemode in Claude Code”

More on Rubric

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

  1. Score 0.75

    llama.cpp v1.0