superpowers-extended-cc

Superpowers Extended for Claude Code

A community-maintained fork of pcvelz/superpowers specifically for Claude Code users.

Why This Fork Exists

The original Superpowers is designed as a cross-platform toolkit that works across multiple AI CLI tools (Claude Code, Codex, OpenCode, Gemini CLI). Features unique to Claude Code fall outside the scope of the upstream project due to its cross-platform nature.

This fork integrates Claude Code-native features into the Superpowers workflow.

What We Do Differently

• Leverage Claude Code-native features as they're released
• Community-driven - contributions welcome for any CC-specific enhancement
• Track upstream - stay compatible with obra/superpowers core workflow

Current Enhancements

Feature	Description
Native Task Management	Dependency tracking, real-time progress visibility
Structured Task Metadata	Goal/Files/AC/Verify structure with embedded json:metadata
Pre-commit Task Gate	Plugin hook blocks git commit when tasks are incomplete
User-Thrown Gate Enforcement	userGate / user-gate tag + opt-in hooks force re-validation when Claude closes a user-ordered verification task (see Recommended Configuration)
Subagent Model Routing	Opt-in per-task model tiers (mechanical/standard/frontier) route plan-execution subagents to cheaper models (see Subagent Model Routing)
Configurable Commit Strategy	Opt-in workflow.json switches plan execution from per-task commits to a single commit at plan end (see Commit Strategy)

Visual Comparison

Superpowers (Vanilla)	Superpowers Extended CC
Tasks exist only in markdown plan No runtime task visibility Agent may jump ahead or skip tasks Progress tracked manually by reading output	Dependency enforcement - Task 2 blocked until Task 1 completes (no front-running) Execution on rails - Native task manager keeps agent following the plan Real-time visibility - User sees actual progress with pending/in_progress/completed states Session-aware - TaskList shows what's done, what's blocked, what's next

Installation

Option 1: Via Marketplace (recommended)

# Register marketplace
/plugin marketplace add tim-hub/superpowers

# Install plugin
/plugin install superpowers-extended-cc@superpowers-extended-cc-marketplace

Option 2: Direct URL

/plugin install --source url https://github.com/tim-hub/superpowers.git

Stay Updated (recommended)

Third-party marketplaces don't auto-update by default — installs stay frozen on the original version until you refresh. To get future fixes and new optional hooks automatically:

1. Run /plugin
2. Open the Marketplaces tab
3. Toggle Enable auto-update on superpowers-extended-cc-marketplace

Or refresh manually any time:

/plugin marketplace update superpowers-extended-cc-marketplace

Verify Installation

Run /superpowers-extended-cc:onboard for a guided walkthrough of the optional features (model routing, user-gate enforcement, commit strategy). One scope choice governs every write; manual setup is documented below.

The Basic Workflow

1. brainstorming - Activates before writing code. Refines rough ideas through questions, explores alternatives, presents design in sections for validation. Saves design document.

2. using-git-worktrees - Activates after design approval. Creates isolated workspace on new branch, runs project setup, verifies clean test baseline.

3. 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. Creates native tasks with dependencies.

4. subagent-driven-development or executing-plans - Activates with plan. Dispatches fresh subagent per task with two-stage review (spec compliance, then code quality), or executes in batches with human checkpoints.

5. 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.

6. requesting-code-review - Activates between tasks. Reviews against plan, reports issues by severity. Critical issues block progress.

7. 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.