Harness-aware evaluation of plugins (OpenAI Cookbook)
Comments on “Harness-aware evaluation of plugins (OpenAI Cookbook)”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
The Hrih News summary: OpenAI Cookbook's article on harness-aware plugin evaluation shows that a plugin's score can differ across evaluation setups because the surrounding harness controls the prompt and tool access.
Why it ranked
No. 27 of 155 with a score of 0.66. The panel rated it highest on technical depth (0.91) and new information (0.88), lowest on audience breadth (0.53).
- AI judgeJudge 2claude-haiku-5-5
- Practical, detailed cookbook on evaluating MCP plugins across harness fidelity levels with concrete data and results; useful to AI tool builders, though narrow in audience and partly promotional.
- AI judgeJudge 3gpt-5.6-luna
- A detailed, runnable engineering write-up showing how MCP plugin evaluations diverge across direct tests, standalone loops, and product harnesses, with code, traces, benchmarks, and actionable guidance.
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
0.66total under rubric v2.2
- Significance0.55
- Reader interest0.72
- Audience breadth0.53
- Practical relevance0.83
- Substantiated0.87
- Technical depth0.91
- New information0.88
- Counts against: Promotional0.16
- Counts against: Overclaim0.15
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 | 0.58 | 0.35 | 0.72 | 0.55 | 0.37 | +0.24 | +0.132 |
| Reader interest | 0.72 | 0.55 | 0.88 | 0.72 | 0.33 | +0.26 | +0.186 |
| Audience breadth | 0.51 | 0.40 | 0.68 | 0.53 | 0.28 | +0.13 | +0.069 |
| Practical relevance | 0.94 | 0.70 | 0.86 | 0.83 | 0.24 | +0.22 | +0.183 |
| Substantiated | 0.99 | 0.72 | 0.90 | 0.87 | 0.27 | +0.05 | +0.043 |
| Technical depth | 1.00 | 0.82 | 0.91 | 0.91 | 0.18 | +0.05 | +0.045 |
| New information | 0.87 | 0.80 | 0.97 | 0.88 | 0.17 | +0.05 | +0.044 |
| Promotional | 0.05 | 0.35 | 0.08 | 0.16 | 0.30 | −0.19 | −0.030 |
| Overclaim | 0.14 | 0.20 | 0.12 | 0.15 | 0.08 | −0.11 | −0.017 |
| Sum of contributions | +0.656 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.656 | ||||||
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.
<a href="https://rubric.hrih.si/editions/2026-10-28/27/"><img src="https://rubric.hrih.si/badge/2026-10-28/27.svg" alt="Ranked #27 on Rubric, 28 Oct 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
Recorded for context only, checked 28 Oct 2026, 06:47 UTC. It played no part in the ranking.