Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and some initial instructions that make sure your agent uses them.
Auto-invoked ships a router so the right skill fires automatically as you prompt. No remembering which skill to call.
Normal is the plain upstream plugin, installed as-is. You invoke its skills yourself.
The plugin> /plugin marketplace add obra/superpowers> /plugin install superpowers@superpowers-devAuto-invocation> /plugin marketplace add flowy-sh/flowy-core> /plugin install flowy-core> /plugin install flowy-superpowers
What's inside
Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and some initial instructions that make sure your agent uses them.
It starts from the moment you fire up your coding agent. As soon as it sees that you're building something, it doesn't just jump into trying to write code. Instead, it steps back and asks you what you're really trying to do.
Once it's teased a spec out of the conversation, it shows it to you in chunks short enough to actually read and digest.
After you've signed off on the design, your agent puts together an implementation plan that's clear enough for an enthusiastic junior engineer with poor taste, no judgement, no project context, and an aversion to testing to follow. It emphasizes true red/green TDD, YAGNI (You Aren't Gonna Need It), and DRY.
Next up, once you say "go", it launches a subagent-driven-development process, having agents work through each engineering task, inspecting and reviewing their work, and continuing forward. It's not uncommon for your agent to work autonomously for a couple hours at a time without deviating from the plan you put together.
There's a bunch more to it, but that's the core of the system. And because the skills trigger automatically, you don't need to do anything special. Your coding agent just has Superpowers.
If you're using Superpowers in enterprise and could benefit from commercial support, additional tooling, or managed spending, please don't hesitate to drop us a line at sales@primeradiant.com.
Installation differs by harness. If you use more than one, install Superpowers separately for each one.
Superpowers is available via the official Claude plugin marketplace
Install the plugin from Anthropic's official marketplace:
/plugin install superpowers@claude-plugins-official
The Superpowers marketplace provides Superpowers and some other related plugins for Claude Code.
Register the marketplace:
/plugin marketplace add obra/superpowers-marketplace
Install the plugin from this marketplace:
/plugin install superpowers@superpowers-marketplace
Install Superpowers as a plugin from this repository:
agy plugin install https://github.com/obra/superpowers
Antigravity runs the plugin's session-start hook, so Superpowers is active from the first message. Reinstall with the same command to update.
Superpowers is available via the official Codex plugin marketplace.
Superpowers in the Coding section.+ next to Superpowers and follow the prompts.Superpowers is available via the official Codex plugin marketplace.
Open the plugin search interface:
/plugins
Search for Superpowers:
superpowers
Select Install Plugin.
In Cursor Agent chat, install from marketplace:
/add-plugin superpowers
Or search for "superpowers" in the plugin marketplace.
Install the plugin from this repository:
devin plugins install obra/superpowers
Update to the latest version with:
devin plugins update superpowers
Register the marketplace:
droid plugin marketplace add https://github.com/obra/superpowers
Install the plugin:
droid plugin install superpowers@superpowers
Install the extension:
gemini extensions install https://github.com/obra/superpowers
Update later:
gemini extensions update superpowers
Register the marketplace:
copilot plugin marketplace add obra/superpowers-marketplace
Install the plugin:
copilot plugin install superpowers@superpowers-marketplace
Superpowers is available via the official Grok plugin marketplace.
Install the plugin from xAI's official marketplace:
grok plugin install superpowers@xai-official --trust
Or open the marketplace in the TUI, search for Superpowers, and install it:
/marketplace
Superpowers is available in Kimi Code's plugin marketplace.
Open Kimi Code's plugin manager:
/plugins
Go to Marketplace > Superpowers and install it.
Or install directly from this repository:
/plugins install https://github.com/obra/superpowers
Detailed docs: docs/README.kimi.md
OpenCode uses its own plugin install; install Superpowers separately even if you already use it in another harness.
Tell OpenCode:
Fetch and follow instructions from https://raw.githubusercontent.com/obra/superpowers/refs/heads/main/.opencode/INSTALL.md
Detailed docs: docs/README.opencode.md
Install Superpowers as a Pi package from this repository:
pi install git:github.com/obra/superpowers
For local development, run Pi with this checkout loaded as a temporary package:
pi -e /path/to/superpowers
The Pi package loads the Superpowers skills and a small extension that injects the using-superpowers bootstrap at session startup and again after compaction. Pi has native skills, so no compatibility Skill tool is required. Subagent and task-list tools remain optional Pi companion packages.
Qwen Code installs plugins from Claude Code marketplaces directly.
Install the plugin from this repository, and pick superpowers when prompted:
qwen extensions install obra/superpowers
Update later:
qwen extensions update superpowers
Install Superpowers as a Hermes plugin from this repository:
hermes plugins install obra/superpowers --enable
Restart any active Hermes sessions after installing. Note: Hermes has no post-compaction hook, so a very long session that compacts over its first turn loses the bootstrap — start a fresh session if skills stop triggering.
Superpowers is available as a native Muse plugin — same repo, same skills, all harnesses. The using-superpowers bootstrap is injected via the native SessionStart hook alongside Claude Code, Codex, Cursor, Gemini, Pi, and the rest — no per-session opt-in.
Install from a local checkout:
muse plugins install ./
muse plugins approve superpowers
Or clone and install:
git clone https://github.com/obra/superpowers.git
muse plugins install ./superpowers
muse plugins approve superpowers
Update later:
muse plugins update superpowers
Restart any active Muse sessions after installing so the SessionStart hook takes effect — skills are active immediately, hooks require approval on first install. To verify, start a fresh session and send Let's make a react todo list — a working install auto-triggers brainstorming before any code is written. Version is tracked in .version-bump.json so scripts/bump-version.sh keeps it in sync.
brainstorming - Activates before writing code. Refines rough ideas through questions, explores alternatives, presents design in sections for validation. Saves design document.
using-git-worktrees - Activates after design approval. Creates isolated workspace on new branch, runs project setup, verifies clean test baseline.
writing-plans - Activates with approved design. Breaks work into bite-sized tasks (2-5 minutes each). Every task has exact file paths, complete code, verification steps.
subagent-driven-development or executing-plans - Activates with plan. Either dispatches a fresh subagent per task with a review after each (most thorough), or implements every task inline in the current session with one fresh review of the whole branch at the end (cheapest).
test-driven-development - Activates during implementation. Enforces RED-GREEN-REFACTOR: write failing test, watch it fail, write minimal code, watch it pass, commit. Deletes code written before tests.
requesting-code-review - Activates between tasks. Reviews against plan, reports issues by severity. Critical issues block progress.
finishing-a-development-branch - Activates when tasks complete. Verifies tests, presents options (merge/PR/keep/discard), cleans up worktree.
The agent checks for relevant skills before any task. Mandatory workflows, not suggestions.
Sometimes a session misbehaves: a skill fires when it shouldn't, stays silent when it should, or the agent ignores its plan, repeats work, or burns more tokens than you'd expect. Ask your coding agent to "figure out what went wrong with superpowers in this session" and it will invoke the diagnosing-superpowers skill. To examine an earlier session, name it: "figure out what went wrong with superpowers in session <id>".
The skill reads the session transcript, reports what happened with line-level evidence, and, if you want, packages a scrubbed bundle for a bug report.
Superpowers is built by Jesse Vincent and the rest of the folks at Prime Radiant.
Testing
Debugging
Collaboration
The FLOW.md
This file reads your intent and auto-invokes the right skill at the right moment. You just prompt.
# FLOW.md: Superpowers Flow > Routes the 14 superpowers agent-discipline skills so the right one fires at the right phase: the agent cannot skip brainstorming, TDD, debugging, review, or verification. > Skills by Jesse Vincent (https://github.com/obra/superpowers, MIT). Routing by Flowy. <!-- The Flowy engine supplies the universal contract (announce ritual, invoke/READ, host-wins, post-compaction re-read). This file carries only the routing. --> ## Routing **The rule:** when a trigger matches you INVOKE the named skill BEFORE doing the task yourself. Writing the code, patching the bug, or claiming "done" without first invoking is the failure this Flow exists to stop. ``` USER MESSAGE ├─ session start / first message? → invoke using-superpowers (bootstrap once) ├─ new idea / feature / project? → invoke brainstorming gate: approved design doc ├─ design exists, no plan? → invoke writing-plans gate: checkboxed tasks, approved ├─ plan has unchecked tasks? │ ├─ 3+ independent tasks? → invoke subagent-driven-development │ └─ otherwise → invoke executing-plans gate: all boxes checked, tests green ├─ about to write implementation code? → invoke test-driven-development gate: a failing test exists FIRST ├─ something broken / erroring? → invoke systematic-debugging gate: root cause written down ├─ about to claim done / fixed / passing? → invoke verification-before-completion gate: command output proves it ├─ code complete, needs review? → invoke requesting-code-review gate: findings addressed ├─ review feedback received? → invoke receiving-code-review gate: every finding resolved ├─ all tasks done, branch ready? → invoke finishing-a-development-branch gate: tests pass + integration choice ├─ need parallel isolated branches? → invoke using-git-worktrees ├─ ad-hoc parallel research / fan-out? → invoke dispatching-parallel-agents ├─ want to author a custom skill? → invoke writing-skills ├─ scope changed mid-task (brief or reqs changed)? → re-enter the earliest invalidated phase (brainstorming or writing-plans) ├─ blocked / waiting on an external dependency? → park: record the blocker and resume condition; do not fake progress └─ question, not work (advise / explain)? → answer only; no files change ``` ## Priority on collision When more than one branch matches, resolve top-down: 1. **Debugging**: a broken state is handled before anything else. 2. **Verification**: a pending "done" claim is verified before it is spoken. 3. **TDD**: code about to be written gets its failing test first. 4. **Planning**: no plan means plan before building. 5. **Brainstorming**: no design means design before planning. 6. Everything else in lifecycle order. A scope change re-enters the earliest invalidated phase (usually brainstorming or writing-plans). ## Phases 1. **Design**: brainstorming. Gate: approved design doc. 2. **Plan**: writing-plans. Gate: checkboxed tasks, approved. 3. **Build**: executing-plans or subagent-driven-development, with TDD inside every code-bearing task. Gate: all boxes checked, tests green. 4. **Verify**: verification-before-completion. Gate: fresh command output proves each claim. 5. **Ship**: requesting-code-review, then receiving-code-review, then finishing-a-development-branch. Gate: findings resolved, tests pass, integration chosen. **Shortcuts:** bug → debugging → TDD (regression test) → verify → review → finish (skip Design/Plan). Small feature (under ~200 LOC, no new surface) → plan → build → verify → review → finish (skip Design). Typo or config → fix → verify. ## You are rationalizing if you think… - "This is too simple for brainstorming." → Invoke it. Thirty seconds. - "I'll write the tests after." → TDD. Failing test first, always. - "It obviously works." → Verification. Run the command in THIS message. - "I can just fix this quickly." → Debugging. Root cause in writing first. - "They only asked a question." → If you are about to write code to answer, TDD fires. - "The summary says I already routed." → After compaction, re-read this file and restate the phase. ## Attribution Skills in `skills/` by Jesse Vincent (obra), MIT (https://github.com/obra/superpowers). FLOW.md routing by Flowy, CC-BY-SA-4.0.
FAQ
superpowers is a Claude Code plugin of 15 hand-picked skills with a FLOW.md router. Install it once and the right skill fires as you prompt, with no slash command to remember. It is built for development work. It includes brainstorming, diagnosing-superpowers, dispatching-parallel-agents. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it