Datasheet · A prompt line
Plan first
Before writing code, write a short plan of the steps.
Folklore, as cited: plan-then-code rules in coding-agent prompts
Changes nothing that matters on Coding, Haiku 5.5 with thinking off.
Coding, Haiku 5.5 with thinking off
Pooled across 1 notebook: −0.3 points, 95% interval −2.2 to +1.5; measured once.
- INERTNotebook #088−0.3 points (−2.9 to +2.1), 432 pairs, cost ×1.33signed verdict 543
Where it acts
No family moved clearly.
All 11 families, none moved clearly
- Parsing durations+7.7−2.6 to +19.239 tasks
- Trade profit+2.6−12.8 to +14.139 tasks
- Moving averages+1.3−9.0 to +11.539 tasks
- Business days+0.0+0.0 to +0.039 tasks
- Fees in whole cents+0.0+0.0 to +0.040 tasks
- Merging intervals+0.0+0.0 to +0.040 tasks
- Run-length encoding+0.0+0.0 to +0.039 tasks
- Comparing versions+0.0+0.0 to +0.039 tasks
- Top k by score+0.0+0.0 to +0.039 tasks
- URL slugs−2.5−12.5 to +0.040 tasks
- AMM swap output−12.8−30.8 to +5.139 tasks
Read from 432 paired tasks in 1 notebook, each task against its own notebook’s two controls, with every interval widened for the 11 families read. No notebook preregisters a family: this says where to look, and a notebook says whether it holds. The runs behind it are on each notebook’s page.
Put this datasheet in a README
The badge shows what the signed record says about this part, in the setting measured most, and links here. It follows the record as new notebooks publish. Add ?suite= and a suite’s id to show another setting.
[](https://opsinlab.io/parts/3462fc2400f45aa0)Measure it in a setting it has not been measured in: propose it. As JSON for an agent: /v1/parts/3462fc2400f45aa0. Every part: the atlas.