Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By REPOZY
Enforce a disciplined agentic workflow: design-before-code with adversarial review, TDD-based implementation in isolated Git worktrees, adversarial red-team testing, structured debugging with known-issues memory, and review-gated code merging into PRs — all with automatic token efficiency and safety context checks.
npx claudepluginhub repozy/superpowers-optimizedUse this agent to review completed implementation work against requirements, correctness, and production readiness.
Use this agent to adversarially attack completed implementation work — find concrete ways to break the code through specific inputs, state sequences, race conditions, assumption violations, and production context mismatches that checklist-based review would miss.
Validates whether proposed or in-progress work should exist before investing in it. Invoke BEFORE designing, planning, or building anything non-trivial — and WHEN new evidence arrives that could change the motivation for existing work. Triggers on: "design a system", "create a plan", "build out the full version", "extend this to handle", architecture proposals, or any moment where test results, research findings, or changed requirements weaken the original reason for doing something. Also triggers when you catch yourself updating a document's facts without reassessing its conclusions.
MUST USE when the user wants new features, behavior changes, refactoring with new capabilities, or architecture decisions and no approved design exists yet. Produces an approved design document before any code is written. Triggers on: "build this", "add a feature", "I want to change", "how should we", "design", "architect", "new project", "refactor", "we need to add/build/create", "implement a new". Routed by using-superpowers, or invoke directly via /brainstorming.
Creates minimal, high-signal CLAUDE.md and AGENTS.md context files based on empirical best practices. Invoke on /init command, "create CLAUDE.md", "update CLAUDE.md", "write AGENTS.md", or "set up Claude Code for this project". Also invoked by brainstorming when repo lacks a context file. tools: Read, Glob, Grep, Bash, Edit
Use in long or noisy sessions to persist durable state across session boundaries via state.md. Also generates project-map.md when asked to map the project. Triggers on: user explicitly asks to "save state", "compress context", "map this project", "generate project map", "create project map", cross-session handoff needed, or repeated failures indicate context is getting stale.
Use BEFORE brainstorming when facing a complex architectural, technology, or design decision where the options are not yet well-defined or the problem itself may need reframing. Assembles named stakeholder perspectives that each speak once without debate, then surfaces where they converge and where real tension remains — without forcing a premature choice. Triggers on: "should we use X or Y", "not sure which approach", "evaluate these options", "what are the trade-offs between", "help me think through this decision", "architecture decision", "technology choice". Routed by using-superpowers before brainstorming when the decision space is unclear.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Development marketplace for Superpowers core skills library
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC plugin for engineering teams - 64 agents, 262 skills, 84 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.

The production-grade fork of obra/superpowers — same trusted workflow, dramatically leaner, safer, and more intelligent.
Built on the trusted obra/superpowers workflow and refined through research into LLM agent behavior, it adds automatic 3-tier workflow routing, proactive safety hooks, self-consistency verification at critical decision points, cross-session memory, and adversarial red-teaming — everything the original does, plus the discipline layer it was missing.
Cross-session memory changes the experience fundamentally. Without it, every session starts blind: the AI re-explores structure it already mapped, re-proposes approaches that were already rejected, re-debugs errors that were already solved. With the memory stack, it arrives knowing what was tried, what was decided, and why — and with a pre-computed snapshot of exactly what changed since the last commit — and builds forward instead of sideways.
Five research-backed principles run throughout: less is more (minimal always-on instructions), fresh context beats accumulated context (subagents get clean scoped prompts, not polluted history), compliance ≠ competence (instructions must be carefully engineered, not just comprehensive), verify your own reasoning (multi-path self-consistency catches confident-but-wrong failures before they become expensive), and accountability drives accuracy (agents that know their output has real downstream consequences perform better).
| Feature | Original Superpowers | Superpowers Optimized | Real-world impact |
|---|---|---|---|
| Workflow selection | Manual | Automatic 3-tier (micro / lightweight / full) | Zero overhead on simple tasks |
| Safety & hooks | None | 9 proactive hooks (dangerous-command blocker, secrets protector, subagent guard, edit tracker, session stats, stop reminders, skill activator, session start, context engine) | Zero risk of rm -rf or secret leaks |
| Security review | None | Built into code review with OWASP checklist | Security catches before merge |
| Adversarial red team | None | Red team agent + auto-fix pipeline | Finds bugs checklists miss, fixes them with TDD |
| Error recovery | None | Project-specific known-issues.md | No rediscovering the same bug |
| Token efficiency | Standard | Always-on context hygiene + exploration tracking | Less re-discovery, fewer wasted iterations |
| Discipline enforcement | Instructional tone | Rationalization tables, red flags, iron laws | Fewer LLM shortcuts |
| Progress visibility | None | Session stats (skills used, duration, actions) | See what the plugin did for you |
| Cross-session memory | None | Four-file memory stack: project-map.md (structure cache) + session-log.md (decision history) + state.md (task snapshot) + known-issues.md (error map) + automatic context-snapshot.json (git blast radius, written every session start) | The AI starts every session with full project context — no re-exploring, no re-explaining, no re-debugging |
In any supported agent IDE, start a new chat and paste:
Activate Superpowers Optimized and plan a secure user-authentication endpoint with full TDD and security review.
The agent will automatically route to the correct workflow, apply safety guards, and run an integrated security review during code review — no manual skill selection required.