Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By aman-2709
Disciplined workflow skills, security review, learning system, and cross-platform tooling for Claude Code
npx claudepluginhub aman-2709/superpowers-ecc --plugin superpowers-eccStart a brainstorming session to refine ideas into specs before writing code
Incrementally fix build and type errors with minimal, safe changes
Create or verify a checkpoint in your workflow for safe rollback points
Comprehensive security and quality review of uncommitted changes
Generate and run end-to-end tests with Playwright — create test journeys, run tests, capture artifacts
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for planning tasks.
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when extracting reusable patterns from sessions into instincts with confidence scoring for cross-session learning
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Matches all tools
Hooks run on every tool call, not just specific ones
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Agentic development framework for Claude Code — disciplined workflow routing, TDD enforcement, safety hooks, systematic debugging, and code review
Unified Claude Code plugin merging superpowers workflows (TDD, debugging, planning) with everything-claude-code productivity (agents, learning, hooks, rules)
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Comprehensive development toolkit with skills, commands, and documentation standards
Harness-native ECC operator layer - 60 agents, 232 skills, 75 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related 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.
A focused Claude Code plugin merging superpowers workflow discipline with curated ECC tooling.
/plugin marketplace add https://github.com/aman-2709/superpowers-ecc
/plugin install superpowers-ecc@superpowers-ecc
/reload-plugins
Start with /superpowers-ecc:brainstorm to kick off a new feature or project. The brainstorming skill guides you through spec refinement, then transitions to planning and implementation.
| Component | Count | Details |
|---|---|---|
| Skills | 24 | 14 workflow + 10 tooling |
| Standalone agents | 7 | Domain consultants (planner, architect, etc.) |
| Slash commands | 24 | Workflow, quality, security, learning, orchestration |
| Rule sets | 4 | common + typescript + python + golang |
| Learning system | 6 commands | Instincts, confidence scoring, cross-session memory |
| Cross-platform | 4 | Claude Code, Cursor, OpenCode, Codex CLI |
The plugin enforces a 7-step development loop:
brainstorm -> worktree -> plan -> implement (subagent-driven) -> review -> verify -> merge
Each step has a dedicated skill with guardrails. Start with /superpowers-ecc:brainstorm to enter the loop.
| Layer | Purpose | Examples |
|---|---|---|
| Embedded subagent prompts | Execution machinery | implementer, spec-reviewer, quality-reviewer |
| Standalone agents | Domain consultants | planner, architect, security-reviewer, build-error-resolver |
Embedded prompts are invoked automatically during /superpowers-ecc:execute-plan. Standalone agents are called on-demand via their slash commands or by other skills that need specialist input.
The continuous learning system observes patterns across sessions and codifies them as instincts -- lightweight heuristics that evolve over time.
Lifecycle: observe patterns -> score confidence -> evolve into skills
| Command | Purpose |
|---|---|
/superpowers-ecc:learn | Record an observation or pattern |
/superpowers-ecc:learn-eval | Evaluate and score recorded instincts |
/superpowers-ecc:evolve | Promote high-confidence instincts to skills |
/superpowers-ecc:instinct-status | Show current instincts and their confidence scores |
/superpowers-ecc:instinct-import | Import instincts from a file |
/superpowers-ecc:instinct-export | Export instincts to a file |
| Command | Description |
|---|---|
/superpowers-ecc:brainstorm | Structured ideation with spec document output |
/superpowers-ecc:write-plan | Generate an implementation plan from a spec |
/superpowers-ecc:execute-plan | Run a plan via subagent-driven implementation |
/superpowers-ecc:plan | Alias for /superpowers-ecc:write-plan — shorter name, same behavior |
| Command | Description |
|---|---|
/superpowers-ecc:tdd | Test-driven development cycle |
/superpowers-ecc:code-review | Request a code review |
/superpowers-ecc:verify | Run verification checks before completion |
/superpowers-ecc:quality-gate | Enforce quality standards on changes |
/superpowers-ecc:test-coverage | Analyze and report test coverage |
| Command | Description |
|---|---|
/superpowers-ecc:security-scan | Run security review on code changes |
| Command | Description |
|---|---|
/superpowers-ecc:build-fix | Invoke build-error-resolver agent |
/superpowers-ecc:refactor-clean | Invoke refactor-cleaner agent |
/superpowers-ecc:e2e | Invoke e2e-runner agent |
| Command | Description |
|---|---|
/superpowers-ecc:learn | Record a pattern or observation |
/superpowers-ecc:learn-eval | Evaluate instinct confidence |
/superpowers-ecc:evolve | Promote instincts to skills |
/superpowers-ecc:instinct-status | Show instinct scores |
/superpowers-ecc:instinct-import | Import instincts |
/superpowers-ecc:instinct-export | Export instincts |
| Command | Description |
|---|---|
/superpowers-ecc:multi-plan | Plan across multiple worktrees |
/superpowers-ecc:multi-execute | Execute across multiple worktrees |
| Command | Description |
|---|---|
/superpowers-ecc:sessions | List and manage sessions |
/superpowers-ecc:checkpoint | Save session state for later restore |
| Command | Description |
|---|---|
/superpowers-ecc:model-route | Route tasks to appropriate model tiers |