Edition of Wednesday 18 November 2026

A set of rules to save tokens

Comments on “A set of rules to save tokens”

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

A GitHub repo called token-savings, by author Cicero Hellmann, measures waste in Claude Code token spend using local transcripts. Its grade.py script scores known wasteful patterns, such as oversized helper contexts and idle cache rewrites, and ships rules and lean helper types to fix them.

Read the original at github.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. 98 of 142 with a score of 0.59. The panel rated it highest on new information (0.90) and practical relevance (0.80), lowest on significance (0.41). The judges disagreed most on substantiated (spread 0.50), so the story is marked contested. Placed No. 98, No. 90 by score alone: the 40th AI & machine learning story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Practical, self-measured tooling for cutting Claude Code token costs; on-topic and actionable for AI builders, but single-machine evidence with unclear attribution and a self-promotional repo framing lower substantiation.
AI judgeJudge 3gpt-5.6-luna
A practical Claude Code token-cost grader with concrete mechanisms, rules, measurements, and caveats. Evidence is limited to one machine and confounded by concurrent changes, but the repo and methodology make it useful to AI-assisted developers.

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

0.59total under rubric v2.3Contestedjudges differ by 0.50 on substantiated, 0.41 on technical depth

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.41
  • Reader interest0.70
  • Audience breadth0.49
  • Practical relevance0.80
  • Substantiated0.73
  • Technical depth0.74
  • New information0.90
  • Counts against: Promotional0.10
  • Counts against: Overclaim0.24

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?0.530.250.450.410.28+0.24+0.098
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.720.550.820.700.27+0.26+0.181
Audience breadthHow many people who build technology does it concern?0.470.500.500.490.03+0.13+0.064
Practical relevanceHow useful is it to someone who builds software or tech products?0.910.700.800.800.21+0.22+0.177
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.0.950.450.780.730.50 , above the contested threshold+0.05+0.036
Technical depthHow technically substantive is it?0.960.550.720.740.41 , above the contested threshold+0.05+0.037
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.890.850.970.900.12+0.05+0.045
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.0.070.100.120.100.05−0.19−0.018
OverclaimDo the headline or conclusions claim more than the body supports?0.230.400.080.240.32−0.11−0.026
Sum of contributions+0.594
Claim-check penalty0.000
Total, as published0.594

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 #98 on Rubric, 18 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-18/98/"><img src="https://rubric.hrih.si/badge/2026-11-18/98.svg" alt="Ranked #98 on Rubric, 18 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 18 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 “A set of rules to save tokens”

More on Rubric

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

  1. Score 0.69

    Inkling 2 Mini