You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements and design before implementation.
Execute plan in batches with review checkpoints
Create detailed implementation plan with bite-sized tasks
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when publishing a new version of superpowers-extended-cc - handles upstream sync, version bump, testing, tagging, and GitHub release creation
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.
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
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.
Executes directly as bash, bypassing the AI model
Executes directly as bash, bypassing the AI model
A community-maintained fork of obra/superpowers for Claude Code, with native task management and dex cross-session persistence.
The original Superpowers is a cross-platform toolkit for multiple AI CLI tools (Claude Code, Codex, OpenCode, Gemini CLI). Features unique to Claude Code fall outside its cross-platform scope.
This fork adds Claude Code-native integrations.
| Feature | Description |
|---|---|
| Native Task Management | Claude Code TaskCreate/TaskUpdate for real-time progress visibility and dependency tracking |
| Dex Persistence | Cross-session task memory via dex CLI — resume work across conversations |
| Dual-Write Pattern | In-session native tasks + persistent dex storage, so nothing is lost between sessions |
Skills use a dual-write pattern:
dex list --in-progress recovers where you left offThis means:
using-superpowers checks dex on session start and offers to resume| Superpowers (Vanilla) | Superpowers Dex |
|---|---|
|
|
|
# Register marketplace
/plugin marketplace add abhishekray07/superpowers-dex
# Install plugin
/plugin install superpowers-dex@superpowers-dex-marketplace
claude plugins add abhishekray07/superpowers-dex
After restarting Claude Code:
/help
# Should show superpowers-dex skills:
# superpowers-dex:brainstorming
# superpowers-dex:writing-plans
# superpowers-dex:executing-plans
# ...
Install dex for cross-session persistence:
# Install from https://dex.rip/install
curl -fsSL https://dex.rip/install | bash
Without dex, the plugin still works — you just lose cross-session memory.
brainstorming — Refines ideas through questions, explores alternatives, saves design document. Creates dex epic for persistence.
using-git-worktrees — Creates isolated workspace on new branch, runs setup, verifies clean test baseline.
writing-plans — Breaks work into small tasks with exact file paths, code, and verification steps. Creates native tasks with dependencies + dex epic.
subagent-driven-development or executing-plans — Dispatches subagent per task with two-stage review, or executes in batches with checkpoints. Loads from dex on session resume.
test-driven-development — RED-GREEN-REFACTOR. Write failing test, make it pass, commit.
requesting-code-review — Reviews against plan, reports by severity. Critical issues block progress.
finishing-a-development-branch — Verifies tests, presents options (merge/PR/keep/discard), cleans up.
Skills are checked automatically before any task — mandatory workflows, not suggestions.
Testing
Debugging
Collaboration
npx claudepluginhub abhishekray07/superpowers-dexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Supergraph enforces a complete, evidence-based coding pipeline — scan → plan → TDD → fix → verify → review — grounded in real codebase analysis at every step. It combines AST dependency graphs, LSP-level code intelligence, and a structured skill chain so Claude never guesses about impact before making a change.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
v9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).