# Superpowers

138 Hacker News commenters recommended Superpowers and 72 criticized it, November 2025 to November 2026. It was recommended in 12 of 13 months; owners who said how long report a median of 0.3 years (7 owners).

**Verdict:** A free Claude Code skills plugin that makes the agent ask clarifying questions and write detailed plans before coding; critics say it burns tokens and forces unneeded TDD.

## Why people recommend it

- Clarifies requirements before coding (11 comments): "It's great for feature development. It queries you about you intentions, creates a spec for you to review and modify, creates a plan for it to follow, then farms out the work to subagents." ([source](https://news.ycombinator.com/item?id=48827788)) "this specific skill makes claude think better and bring up and ask thoughtful stuff before it gets to a solution part" ([source](https://news.ycombinator.com/item?id=48508445)) "Superpowers already, generally, figures out to keep the questions up front, so during implementation it doesn't stop." ([source](https://news.ycombinator.com/item?id=48772453))
- Detailed plans for larger features (8 comments): "It's great for feature development. It queries you about you intentions, creates a spec for you to review and modify, creates a plan for it to follow, then farms out the work to subagents." ([source](https://news.ycombinator.com/item?id=48827788)) "It's not uncommon for Claude to be able to work autonomously for a couple hours at a time without deviating from the plan you put together." ([source](https://news.ycombinator.com/item?id=47341828)) "For more complicated tasks (30+ minutes) it works well, and seems to replace a lot of prompting that I'd normally need to do" ([source](https://news.ycombinator.com/item?id=48017796))
- Splits work across subagents (4 comments): "It's great for feature development. It queries you about you intentions, creates a spec for you to review and modify, creates a plan for it to follow, then farms out the work to subagents." ([source](https://news.ycombinator.com/item?id=48827788)) "I've found https://github.com/obra/superpowers very helpful for breaking the work up into logical chunks a subagent can handle." ([source](https://news.ycombinator.com/item?id=46675726)) "with superpowers and it's prevalence of splitting things into smaller focused subagents - this could seriously reduce costs" ([source](https://news.ycombinator.com/item?id=48844069))
- Self-review catches missed issues (2 comments): "it uses subagents to adversarially review its own spec/plan; that has caught several things I would've missed" ([source](https://news.ycombinator.com/item?id=47624894)) "Almost every time, it finds and fixes a bunch of self-review issues before writing the final plan." ([source](https://news.ycombinator.com/item?id=47894497))

## What people warn about

- Consumes lots of tokens, context (5 comments): "My coworkers who've used it seem to think that its main purpose is to consume a lot of tokens." ([source](https://news.ycombinator.com/item?id=49037528)) "It's just not necessary with the modern models and fills up the context windows with garbage and adds an insane number of turns for no benefit." ([source](https://news.ycombinator.com/item?id=48768689)) "It ended up burning so much tokens and taking actually longer to finish and just could have been done without any agent." ([source](https://news.ycombinator.com/item?id=49967693))
- Overdoes TDD and verification (4 comments): "I wish I could turn it on selectively. Many of my requests do not require the "verification before completion" and TDD ceremony." ([source](https://news.ycombinator.com/item?id=48772878)) "the agent proactively adopts TDD for every new feature. But its understanding of testing often stays superficial" ([source](https://news.ycombinator.com/item?id=49606921)) "gets close but I think it overindexes on testing and doesn't go far enough with design document templates" ([source](https://news.ycombinator.com/item?id=47655974))
- Slower, adds many extra turns (3 comments): "It's just not necessary with the modern models and fills up the context windows with garbage and adds an insane number of turns for no benefit." ([source](https://news.ycombinator.com/item?id=48768689)) "It ended up burning so much tokens and taking actually longer to finish and just could have been done without any agent." ([source](https://news.ycombinator.com/item?id=49967693)) "took one of my test runs (local AI) from 40 minutes to 8 hours, and produced a lower-quality result" ([source](https://news.ycombinator.com/item?id=49882442))
- Rigid and opinionated workflow (3 comments): "Superpowers isn't the ideal solution because it too lacks flexibility, but including the "plan sketch" stage is sure an improvement." ([source](https://news.ycombinator.com/item?id=47624807)) "I found the original superpowers was a great start, but rewrote all those skills to fit my workflow" ([source](https://news.ycombinator.com/item?id=48771380)) "folks are complaining that it’s opinionated on git workflows and overriding user instructions otherwise" ([source](https://news.ycombinator.com/item?id=48827568))

## Alternatives hackers recommend

- [Claude Skills](https://hackerapproved.com/p/claude-skills.md): 59 recommend
- [grill-me skill by Matt Pocock](https://hackerapproved.com/p/grill-me-skill.md): 39 recommend
- [Get Shit Done](https://hackerapproved.com/p/get-shit-done.md): 31 recommend
- [Matt Pocock's skills](https://hackerapproved.com/p/matt-pocock-s-skills.md): 27 recommend
- [Claude Code skills](https://hackerapproved.com/p/claude-code-skills.md): 21 recommend

## Cite as

Hacker Approved, "Superpowers", https://hackerapproved.com/p/superpowers/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).