# Recording Claude Code session notes makes design reasons and work history easier to find later

- Link: https://qiita.com/qwertyhoge/items/987c0ea8afdb5cd045e8?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items
- Discussion: https://startupxo.com/en/1202/
- Posted by startupxo at 2026-10-27T18:28:54.805Z
- 0 points, 1 comment, kind story, origin curated
- Written in ko, machine translated to en

## Summary

- Developer @qwertyhoge introduces a self-made work instruction file (skill) that they call with the /decision-log command when a Claude Code task ends. It selects technical choices, alternatives not adopted and their reasons, parts where AI suggestions were corrected, whether self-review was done before the PR, and whether code license and confidential information were checked, then appends them to a monthly record file.
- When there is an important choice, they also write an ADR (Architecture Decision Record, a document that records the background and alternatives of a design decision). According to the original, over about 1 months they left 5 work records and 10 ADRs.
- The author explains that AI tends to interpret its own work favorably, so they added an instruction not to write about things that were not done. They wrote that across several tests with the Opus 5.5 model they did not see cases of it writing about things that did not happen, but this is the author's personal observation.
- Looking at the records, the author found they had rarely done self-review before PRs. They therefore created a separate skill and hook that enforce review, so a PR cannot be created without going through review.

## Sources

- Qiita: https://qiita.com/qwertyhoge/items/987c0ea8afdb5cd045e8?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items

## Comments (1)

- **startupxo** (editorial), 0 points, 2026-10-27T18:28:54.805Z, #c473
  O: A developer who builds with Claude Code inside a company and later has to explain design decisions may want to use /decision-log at the end of each session to record, in a monthly log, the alternatives they did not adopt and whether they did a self-review.
  X: This is an experience report from one author who ran it for about 1 months, not data measuring its effect. The author admits the limitation that the record is missing entries if you forget to call it, so this point should be weighed first.

JSON: https://startupxo.com/api/v1/item.json?id=1202&lang=en