Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
Superpowers
Jesse Vincent's skills framework and development methodology (brainstorm, plan, subagent-driven development, TDD) installed as a plugin in 15+ coding agents.
v7.0.1 released 2026-10-21; last push 2026-10-23; ~305k stars. (checked 2026-10-25)
In Skills and plugin packs for coding agents
Where it stands apart
- How is it mainly sustained? company with a paid product, tier, or ads (22% of 18 others)
- Does it publish evidence that it makes agents better? an eval harness or tests, but no published results (16% of 19 others)
- Does it send usage data to its maker? on by default, with an opt-out (11% of 19 others)
What it shares with most of the community
- Is it actively maintained? active (74% of 19 others)
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (84% of 19 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (95% of 19 others)
- Do you need an account to use it? no account (95% of 19 others)
- Who is it for? developers (79% of 19 others)
- Which shared standard or format does it mainly build on? Agent Skills (SKILL.md) (74% of 19 others)
- What is most of it, whatever it's packaged as? Agent Skills (SKILL.md folders), even if packaged as a plugin (63% of 19 others)
- How big is it? a large bundle (more than 10) (58% of 19 others)
- Does it need an outside service beyond the agent and its model? no (74% of 19 others)
Nearest neighbors
- agent-skills (implement-spec) 76% of 17 shared answers match
- HumanLayer show-me 76% of 17 shared answers match
- Whetstone 76% of 17 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-26 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) | source 2026-10-26 |
| How is it mainly sustained? | stands apart company with a paid product, tier, or ads Built by Jesse Vincent and Prime Radiant, which offers commercial support and tooling to enterprises (sales@primeradiant.com). Judgment call between company and individual. | source 2026-10-26 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes | source 2026-10-26 |
| Do you need an account to use it? | no account | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-26 |
| Which shared standard or format does it mainly build on? | Agent Skills (SKILL.md) Core is SKILL.md skills; plugin manifests and a hook bootstrap them. | source 2026-10-26 |
| Which coding agents does it give install steps for? | 6 or more named agents, or any agent via a cross-agent installer (npx skills) | source 2026-10-26 |
| What is most of it, whatever it's packaged as? | Agent Skills (SKILL.md folders), even if packaged as a plugin Core is SKILL.md skills; per-agent plugin manifests and a SessionStart hook bootstrap them. | source 2026-10-26 |
| How is it mainly installed? | a plugin marketplace command Listed in Anthropic's official Claude plugin marketplace and OpenAI's Codex plugin marketplace; per-agent plugin commands elsewhere. | source 2026-10-26 |
| How big is it? | a large bundle (more than 10) 15 skill folders. | source 2026-10-26 |
| What work is it for? | general coding workflow and discipline | source 2026-10-26 |
| Does it need an outside service beyond the agent and its model? | no | source 2026-10-26 |
| How does it get the agent to follow it? | instructions only: the model decides (a hook that only loads instructions counts here) Skills plus one SessionStart hook that only loads instructions; no blocking gates. | source 2026-10-26 |
| Where does its know-how mainly come from? | the maker's own practice and failures | source 2026-10-26 |
| Does it publish evidence that it makes agents better? | stands apart an eval harness or tests, but no published results tests/ covers each harness and skills, but README publishes no improvement numbers. | source 2026-10-26 |
| Does it send usage data to its maker? | stands apart on by default, with an opt-out The visual companion loads a Prime Radiant logo that reports the version; opt out with SUPERPOWERS_DISABLE_TELEMETRY or Claude Code's DISABLE_TELEMETRY. | source 2026-10-26 |
In Spec-driven development
Where it stands apart
- How is the path from idea to code structured? adaptive: the process scales to the size of the change (11% of 19 others)
What it shares with most of the community
- Is it actively maintained? active (74% of 19 others)
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (74% of 19 others)
- How is it mainly sustained? company with a paid product, tier, or ads (50% of 18 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? yes (79% of 19 others)
- Do you need an account to use it? no account (74% of 19 others)
- Who is it for? developers (100% of 19 others)
- Once code exists, what is the spec? a planning scaffold: code becomes the truth after implementation (53% of 19 others)
- What format are specs written in? markdown from templates or free-form (67% of 18 others)
- Where do specs live? plain files in the project repository (89% of 19 others)
- Which coding agents does it work with? many agents (five or more) (78% of 18 others)
- Does a human approve the spec or plan before code is written? yes, the workflow waits for approval (50% of 18 others)
- What does it offer teams beyond sharing files in git? (if both, pick the paid product) nothing beyond git (50% of 18 others)
Nearest neighbors
- GSD (Get Shit Done) / GSD Core 81% of 16 shared answers match
- BMAD Method 76% of 17 shared answers match
- cc-sdd 76% of 17 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | active | source 2026-10-25 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) MIT | source 2026-10-25 |
| How is it mainly sustained? | company with a paid product, tier, or ads Prime Radiant (AI lab) offers enterprise commercial support and tooling via sales; no public pricing. | source 2026-10-26 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | yes | source 2026-10-25 |
| Do you need an account to use it? | no account Plugin installed into your harness; no sign-up. Newsletter is optional. | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | Agent Skills (SKILL.md) SKILL.md skills across harnesses. | source 2026-10-26 |
| Once code exists, what is the spec? | a planning scaffold: code becomes the truth after implementation Design and plan drive implementation; no step keeps them current afterward. | source 2026-10-25 |
| After implementation, what built-in step keeps specs and code aligned? (if several, the first that applies) | a step checks code against the spec (tests, review, or verifier) Review after each task; finishing step verifies tests. | source 2026-10-25 |
| What format are specs written in? | markdown from templates or free-form | source 2026-10-25 |
| Where do specs live? | plain files in the project repository | source 2026-10-25 |
| Which coding agents does it work with? | many agents (five or more) Claude Code, Codex, Cursor, Gemini CLI, Copilot CLI, OpenCode, and more. | source 2026-10-25 |
| What form does it mainly ship in? | prompts, skills, or slash commands installed into an agent (even if a CLI installs them) | source 2026-10-25 |
| How is the path from idea to code structured? | stands apart adaptive: the process scales to the size of the change 'Small changes get agreed in chat; projects get a written design'. | source 2026-10-25 |
| Does a human approve the spec or plan before code is written? | yes, the workflow waits for approval 'After you've signed off on the design' / skills activate 'after design approval'. | source 2026-10-25 |
| By default, once a plan is approved, how is implementation run? | agents run the whole plan with automated review or verification loops subagent-driven-development dispatches a fresh subagent per task with review. | source 2026-10-25 |
| What does it offer teams beyond sharing files in git? (if both, pick the paid product) | nothing beyond git | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/obra/superpowers · read 2026-10-25
- GitHub · github.com/obra/superpowers/releases · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.