CookiesForAI

using-superpowers

Using Superpowers

Using Superpowers is the agent skill that makes your agent check for a relevant Superpowers skill before it responds, announce it, and follow it whenever one applies.

Agent skill by Jesse Vincent · Updated

Install Using Superpowers

In Claude Code, install the whole Superpowers plugin from Anthropic's official marketplace

Terminal
/plugin install superpowers@claude-plugins-official

Or install only this skill with the skills CLI

Terminal
npx skills add obra/superpowers --skill using-superpowers

Or paste this into your coding agent: Install the agent skill using-superpowers from github.com/obra/superpowers. A skill can include scripts that run on your computer, so read its source first.

What Using Superpowers does

Using Superpowers is one of the skills in Superpowers, Jesse Vincent's open-source method for AI coding agents. It loads at the start of any conversation and sets how the agent finds and uses skills. The agent checks for relevant skills before any response or action, including clarifying questions and exploring the codebase. If there is even a 1% chance a skill applies, the agent invokes it, announces which skill it is using, and follows it.

In Using Superpowers, process skills come first and set the approach, then implementation skills carry it out: a request to build something starts with Brainstorming, and a bug starts with Systematic Debugging. Before entering plan mode, the agent brainstorms first. A table of red flags lists the thoughts that mean the agent is about to skip a skill, such as "this is just a simple question" or "let me explore the codebase first".

Reference files in Using Superpowers map the actions skills ask for to the tools of each agent, with notes for Claude Code, Codex, Gemini CLI, Pi, Antigravity, Hermes Agent and Muse. Your own instructions, in files such as CLAUDE.md, AGENTS.md or GEMINI.md or in direct requests, take precedence over skills, and skills override the agent's default behavior. A subagent dispatched for a specific task is told to ignore this skill.

When to use Using Superpowers

  • You installed Superpowers and want your agent to use its skills without being reminded.
  • Your agent jumps into code or questions before checking whether a skill fits the task.
  • You use Superpowers in more than one agent tool and want the same behavior in each.

Which agents Using Superpowers works in

Jesse Vincent documents Using Superpowers for Claude Code, Codex (app and CLI), Cursor, Gemini CLI, GitHub Copilot CLI, OpenCode, Antigravity, Devin CLI, Factory Droid, Grok Build CLI, Kimi Code, Pi, Qwen Code, Hermes Agent, Muse. The open skills CLI also installs it into 78 agents, including Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode (we listed it with the CLI on October 1, 2026). See where each agent looks for skills.

Superpowers is written in Claude Code's vocabulary (subagent dispatch, todos, the Skill tool) and ships tool mappings for Codex, Gemini CLI, Pi, Antigravity, Hermes Agent and Muse. Installed as the full plugin, a session-start hook loads Using Superpowers so the agent reaches for skills on its own; one skill installed with the skills CLI gets no hook and may point to sibling skills you do not have.

Using Superpowers license

Using Superpowers is published under MIT.

  • Grill me: grill-me is Matt Pocock's agent skill that turns your agent into a relentless interviewer, asking numbered rounds of questions about a plan or design until every decision is settled. (273,901 repository stars on October 2, 2026)
  • Brainstorming: Brainstorming is an agent skill from Superpowers that makes your coding agent work out what you want and agree a design with you before it writes any code. (293,976 repository stars on October 2, 2026)
  • Diagnosing Superpowers: Diagnosing Superpowers is an agent skill from Superpowers that reads a session's transcripts when work went wrong and reports what happened, with every finding tied to a file and line. (293,976 repository stars on October 2, 2026)
  • Dispatching Parallel Agents: Dispatching Parallel Agents is an agent skill from Superpowers: when several problems are independent, your agent sends a focused subagent to each at once, then checks the results together. (293,976 repository stars on October 2, 2026)

More from Jesse Vincent

  • Executing Plans: Executing Plans is an agent skill from Superpowers in which your agent works through a written plan itself, task by task with tests, then gets one fresh review of the whole branch. (293,976 repository stars on October 2, 2026)
  • Finishing a Development Branch: Finishing a Development Branch is an agent skill from Superpowers: when work is done, your agent runs the tests, offers to merge, open a pull request or keep the branch, then cleans up. (293,976 repository stars on October 2, 2026)
  • Receiving Code Review: Receiving Code Review is an agent skill from Superpowers: your agent checks review feedback against the code before acting, pushes back with reasons when it is wrong, and skips the flattery. (293,976 repository stars on October 2, 2026)
  • Requesting Code Review: Requesting Code Review is an agent skill from Superpowers: your agent sends its changes to a separate reviewer subagent that checks them against the plan and grades each issue by severity. (293,976 repository stars on October 2, 2026)

Lists that include using-superpowers