Open sourceMDX · ≈323k stars · MIT
superpowers
An agentic skills framework and software methodology that works.
Superpowers is a software development method for coding agents, built from composable skills that trigger on their own. The agent first asks what you want to build and why, shows the design in short sections, writes an implementation plan built on red/green TDD, then runs subagent-driven development to carry out and review each task. It installs as a plugin for Claude Code, Codex, Cursor, Gemini CLI, Copilot CLI, Antigravity, OpenCode, Pi, Hermes and other harnesses.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- DocsA full auto-triggering methodology: brainstorm, then a spec shown in digestible chunks, then a written plan, then subagent-driven development with review.[1]
- DocsInstalls across many harnesses (Claude Code via the official plugin marketplace, Codex, Cursor, Gemini CLI, OpenCode, Copilot CLI and others).[1]
- User reportsOne user reports being consistently happy with the brainstorming skill, and another says DeepSeek plus Superpowers in OpenCode feels on par with Opus.[1][2]
- MetadataMIT, with about 308k stars and active releases (v7.0.1 on 2026-10-21).[1]
Cons
- User reportsUsers report slower responses after installing and suspect skill context is filling the window (open, 27 comments).[1]
- User reportsProcess friction: v7's brainstorm questions are called annoying, and plans over-specify implementation, leaving the executor no room for judgment.[1][2]
- DocsBy default the brainstorming visual companion loads a logo from the vendor's site that reports your Superpowers version, which the README describes as telemetry.[1]
- User reportsHeavyweight compared with minimal harnesses: users who like Pi cite Claude Code spinning up superpowers skills and many background agents.[1]
- Best for
- Developers who want an opinionated spec-plan-execute discipline on top of any coding agent with little setup.
- Watch out for
- Extra ceremony and context cost on small tasks; turn skills off where the process outweighs the change.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
Founder
Creator of superpowers; Prime Radiant
Skills, plugins & mods · Claude Code
Activity
- Last push
- · 2w ago
- Latest release
- v7.0.2
· 2w ago - Last 90 days
- 5 releases
- · 2w ago
This release further tunes brainstorming's questions. It asks fewer of them, starts by asking why, and when there's a choice to make it gives you options to pick from. It also fixes bootstrap problems on six harnesses, and makes the SDD and executing-plans helper scripts much…
- · 4w ago
This release retunes brainstorming after its rebuild in v7.0.0. Many of you told us, rightly, that the new default questions got annoying fast and felt formulaic. Brainstorming now digs for context before it asks anything, and tries to ask better questions. We expect to keep…
- · 6w ago
We rebuilt brainstorming from scratch so it does a much better job of what it was always for: helping you work out what you actually want and put it into words before anything gets built. The new skill asks you to describe what you're after and why, plays back what it heard so…
- · 8w ago
writing-plans produces leaner plans, faster. Plans now record the decisions an implementer needs (signatures, test assertions, the spec's values) instead of writing out the code. Some frontier models, including Opus 5.5, could get overzealous during plan writing and, with…
- · 2mo ago
v6.4.0 was never shipped. v6.4.1 is the first release with these changes. It holds back the new proving-it-works-with-a-movie skill, which is getting cleanup and robustness work and will return in a later release. The new diagnosing-superpowers skill figures out what went wrong…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
Neighbours on the workbench
TypeScript · ≈395k stars · MIT
openclaw/openclaw
The viral open-source personal AI assistant that really does things.
Maintained by OpenClaw Foundation
v2026.11.6releasedShell · ≈329k stars · MIT
mattpocock/skills
Small, composable agent skills for real engineering work.
Maintained by Matt Pocock (AI Hero)
JavaScript · ≈308k stars · MIT
affaan-m/ECC
Agent harness performance optimization system: skills, instincts, memory and security for coding agents.
Maintained by Affaan Mustafa
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- Jesse VincentOrganisation
Built on · 3
- Claude CodeProject
- CodexProject
- Gemini CLIProject
Similar entries · 8
- Agent Skills (Osmani)Project
- claude-code-infrastructure-showcaseProject
- claude-code-settingsProject
- Compound EngineeringProject
- GStackProject
- labratProject
and 2 more
Sources
Verified Nov 16, 2026
