Pu.sh
Ranked 8 of 11 coding agent harnesses by recommenders
Recommended as a small shell-based coding agent that fits in a few hundred lines. Critics say the code is minified to hit the line count and is hard to read.
Recommended as a small shell-based coding agent that fits in a few hundred lines. Critics say the code is minified to hit the line count and is hard to read.
12 people gave an opinion
- recommend it
- 8
- criticize it
- 4
- approval share
- 67%
Recommended in 2 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: recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 8 people recommend itNeeds 10 or more, not met.
- 2 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 2 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
Appealing simple, small-surface idea
“I love this. This is the grown-up brother of my one-liner bash+python”
Comment from 30 Apr 2026 in “Show HN: Pu.sh – a full coding-agent harness in 400 lines of shell” “i like the idea but i wanted slightly different constraints”
Comment from 1 May 2026 in “Show HN: Pu.sh – a full coding-agent harness in 400 lines of shell” “I like the small-surface-area approach.”
Comment from 1 May 2026 in “Show HN: Pu.sh – a full coding-agent harness in 400 lines of shell”
What people warn about
Each mark is one comment
Minified code is hard to read
“minifying the code to achieve the “400 lines” marketing gimmick is a huge turn-off”
Comment from 30 Apr 2026 in “Show HN: Pu.sh – a full coding-agent harness in 400 lines of shell” “this would be much more convincing and useful with an unminified source”
Comment from 30 Apr 2026 in “Show HN: Pu.sh – a full coding-agent harness in 400 lines of shell” Code quality and readability concerns
“This is just spaghetti. Maybe it's spaghetti that runs, but code of this quality does not engender confidence.”
Comment from 30 Apr 2026 in “Show HN: Pu.sh – a full coding-agent harness in 400 lines of shell” “your 500 LOC requirement has made this thing completely and unnecessarily inscrutable and unreadable”
Comment from 30 Apr 2026 in “Show HN: Pu.sh – a full coding-agent harness in 400 lines of shell”
Other coding agent harnesses people recommend
The four most recommended other coding agent harnesses, 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 |
|---|---|---|---|---|---|---|
| Pi coding agent | 892 | 198 | 82% | 12 | 3 mo51 owners | Approved |
| omp (oh-my-pi) | 80 | 21 | 79% | 6 | — | Approved |
| ForgeCode | 39 | 12 | 76% | 10 | — | Approved |
| Reasonix | 26 | 19 | 58% | 6 | — | — |
| Pu.shThis page | 8 | 4 | 67% | 2 | — | — |
What people said
7 of the 13 comments that mention it, newest first. Each links to the original comment.
“i like the idea but i wanted slightly different constraints”
“I like the small-surface-area approach.”
“This is just spaghetti. Maybe it's spaghetti that runs, but code of this quality does not engender confidence.”
“I love this. This is the grown-up brother of my one-liner bash+python”
“this would be much more convincing and useful with an unminified source”
“minifying the code to achieve the “400 lines” marketing gimmick is a huge turn-off”
“your 500 LOC requirement has made this thing completely and unnecessarily inscrutable and unreadable”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.