Edition of Wednesday 28 October 2026

One Rules Folder for All Your Coding Agents

Comments on “One Rules Folder for All Your Coding Agents”

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

Hrih News: A developer describes keeping one source of truth for coding-agent project rules, stored as markdown in a single .agents folder. Cursor and Claude Code read it through symlinks with tool-specific names, while Codex, ZCode, and Antigravity get duplicated always-on text in AGENTS.md.

Read the original at pragmaticpineapple.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. 39 of 155 with a score of 0.64. The panel rated it highest on new information (0.92) and technical depth (0.89), lowest on significance (0.44).

AI judgeJudge 2claude-haiku-5-5
Detailed, well-evidenced engineering write-up on configuring one shared rules folder across coding agents (Cursor, Claude Code, Codex, Kiro). Practical and technically specific, but a niche tooling topic with modest broad significance.
AI judgeJudge 3gpt-5.6-luna
A highly practical, firsthand interoperability guide for consolidating instructions and skills across coding agents, with concrete layouts, frontmatter, symlink behavior, version caveats, and observed tests. Its broad title slightly overstates the achievable single source of truth.

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

0.64total under rubric v2.2

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.44
  • Reader interest0.73
  • Audience breadth0.56
  • Practical relevance0.83
  • Substantiated0.80
  • Technical depth0.89
  • New information0.92
  • Counts against: Promotional0.04
  • Counts against: Overclaim0.33

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)
Significance0.510.300.520.440.22+0.24+0.107
Reader interest0.720.600.880.730.28+0.26+0.191
Audience breadth0.590.400.680.560.28+0.13+0.073
Practical relevance0.910.700.880.830.20+0.22+0.182
Substantiated0.870.800.740.800.13+0.05+0.040
Technical depth1.000.900.780.890.22+0.05+0.045
New information0.910.900.950.920.05+0.05+0.046
Promotional0.040.050.020.040.03−0.19−0.007
Overclaim0.460.150.380.330.31−0.11−0.036
Sum of contributions+0.640
Claim-check penalty0.000
Total, as published0.639

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 #39 on Rubric, 28 Oct 2026
<a href="https://rubric.hrih.si/editions/2026-10-28/39/"><img src="https://rubric.hrih.si/badge/2026-10-28/39.svg" alt="Ranked #39 on Rubric, 28 Oct 2026" width="245" 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 28 Oct 2026, 06:47 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. This one was scored under rubric v2.2; How ranking works describes the current 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 “One Rules Folder for All Your Coding Agents”

More on Rubric

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