Superpowers

“Really the single biggest piece I use today is using a tool like superpowers to ensure your task is well defined.”

“It ended up burning so much tokens and taking actually longer to finish and just could have been done without any agent.”

“took one of my test runs (local AI) from 40 minutes to 8 hours, and produced a lower-quality result”

“the agent proactively adopts TDD for every new feature. But its understanding of testing often stays superficial”

“My coworkers who've used it seem to think that its main purpose is to consume a lot of tokens.”

“superpowers front-load 22k tokens before you even hit send and their context inflation balloons after 500k”

“with superpowers and it's prevalence of splitting things into smaller focused subagents - this could seriously reduce costs”

“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.”

“folks are complaining that it’s opinionated on git workflows and overriding user instructions otherwise”

“I wish I could turn it on selectively. Many of my requests do not require the "verification before completion" and TDD ceremony.”

“Superpowers already, generally, figures out to keep the questions up front, so during implementation it doesn't stop.”

“I found the original superpowers was a great start, but rewrote all those skills to fit my workflow”

“I ripped it out after I kept seeing Claude/codex TDD things like when I asked them to make a pydantic model immutable.”

“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.”

“It works very well for the way that I work (interactively and iteratively, not "one-shot"), and it helps me to better work in less time.”

“I'm finding it great at taking discrete tasks from beginning to end with very little hand holding.”

“the bigger solution is in process where you use something like superpowers to force the llm through stages”

“this specific skill makes claude think better and bring up and ask thoughtful stuff before it gets to a solution part”

“You have to use something like superpowers, the key is that the humans need to make the important decisions.”

“It allows you to explore the problem space upfront, it questions your assumptions, asks more probing questions”

“For more complicated tasks (30+ minutes) it works well, and seems to replace a lot of prompting that I'd normally need to do”

“See how much more effective Claude can be for moderate or large changes when using the superpowers skill.”

“comparing Claude Code and Codex extensively side by side over the past couple of weeks with my favorite prompting framework superpowers”

“Almost every time, it finds and fixes a bunch of self-review issues before writing the final plan.”

“Add the word "brainstorm" before your prompt and it does a little bit better at figuring out how you want things.”

“I recommend brainstorming everything with https://github.com/obra/superpowers , at least to start with.”

“One single invocation of superpowers on fixing a single GitHub issue that's not super complex eats up all my context.”

“gets close but I think it overindexes on testing and doesn't go far enough with design document templates”

“it uses subagents to adversarially review its own spec/plan; that has caught several things I would've missed”

“Superpowers isn't the ideal solution because it too lacks flexibility, but including the "plan sketch" stage is sure an improvement.”

“Superpowers works well at building comprehensive plans for implementing large features or refactors”

“It's quite verbose however and if your codebase moves quickly, the code might have bad/stale examples.”

“grafting the brainstorm, design, and implementation planning skills from Superpowers onto a Ralph-based implementation layer”

“finding it's doing a better job with similar problems than I was getting with base plan mode”

“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.”

“helps immensely with extracting assumptions and unsaid preferences into a comprehensive plan”

“Clarification and planning has gotten a lot better using some skills (e.g. obra/superpowers)”

“the plans are broken down enough so that the actual coding agent instance doesn't get overwhelmed and lost”

“the superpowers are way more helpful for picking up on you wanting to build/modify something”

“I've found https://github.com/obra/superpowers very helpful for breaking the work up into logical chunks a subagent can handle.”