Claude Code output styles
Shares rank 9 of 10 coding agent features by recommenders
Recommended for embedding custom instructions in the system prompt, with periodic reminders. Critics say it does not reliably fix model behavior.
Recommended for embedding custom instructions in the system prompt, with periodic reminders. Critics say it does not reliably fix model behavior.
10 people gave an opinion
- recommend it
- 6
- criticize it
- 4
- approval share
- 60%
Recommended in 3 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- 1.5 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 3 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
More effective than memory or Claude.md
“a custom output style would be a more idiomatic (and likely more effective) way to implement this”
Comment from 8 Sep 2026 in “I-have-ADHD: A skill to stop coding agents from burying the answer” “You'll get a lot more mileage out of an "output style" with the same instructions”
Comment from 8 Sep 2026 in “I-have-ADHD: A skill to stop coding agents from burying the answer” “definitely yields way better results than just relying on memory or Claude.md”
Comment from 14 Aug 2026 in “Why does Opus 5 feel worse to work with?” Reusable custom instructions you can add
“You'll get a lot more mileage out of an "output style" with the same instructions”
Comment from 8 Sep 2026 in “I-have-ADHD: A skill to stop coding agents from burying the answer” “You can add your own. wfm”
Comment from 20 Aug 2026 in “Clean up Claude 5's token vomit with a separate LLM”
What people warn about
Each mark is one comment
Does not reliably change model behavior
“Is like a band-aid on a bullet wound, properly solving it would mean retraining the model”
Comment from 27 Aug 2026 in “Show HN: The load-bearing vocabulary of Claude” “My experiments with output styles have not been sufficient to keep the model in check.”
Comment from 27 Aug 2026 in “Show HN: The load-bearing vocabulary of Claude” “It hasn't changed the output for me at all at "concise".”
Comment from 28 Aug 2026 in “Show HN: The load-bearing vocabulary of Claude”
Other coding agent features people recommend
The four most recommended other coding agent features, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Claude Code plan mode | 41 | 22 | 65% | 11 | — | — |
| Claude Code auto mode | 20 | 29 | 41% | 6 | — | — |
| Claude Code Routines | 16 | 27 | 37% | 2 | — | — |
| Claude Code Dynamic Workflows | 13 | 10 | 57% | 4 | — | — |
| Claude Code output stylesThis page | 6 | 4 | 60% | 3 | — | — |
What people said
9 of the 12 comments that mention it, newest first. Each links to the original comment.
“You'll get a lot more mileage out of an "output style" with the same instructions”
“a custom output style would be a more idiomatic (and likely more effective) way to implement this”
“It hasn't changed the output for me at all at "concise".”
“My experiments with output styles have not been sufficient to keep the model in check.”
“Is like a band-aid on a bullet wound, properly solving it would mean retraining the model”
“You can add your own. wfm”
“definitely yields way better results than just relying on memory or Claude.md”
“It takes 2 minutes to fix Opus 5”
“more deeply embedded - into a system prompt - and agent is also periodically reminded of them during the session”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.