A community-maintained fork of obra/superpowers specifically for Claude Code users, adapted for Perforce (Helix Core) workflows.

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, and replaces the Git workflow with a Perforce MAIN+shelves workflow for studios using Helix Core.

• Perforce-first workflow — no Git branching; one pending CL per task, shelves replace commits, Swarm reviews replace PRs
• 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

# Register marketplace
/plugin marketplace add pcvelz/superpowers

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

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

Check that commands appear:

/help

# Should see:
# /superpowers-extended-cc:brainstorming - Interactive design refinement
# /superpowers-extended-cc:writing-plans - Create implementation plan
# /superpowers-extended-cc:executing-plans - Execute plan in batches

Start a new session and ask for something that should trigger a skill (for example, "help me plan this feature"). The agent should automatically invoke the relevant superpowers skill.

This plugin uses the p4mcp-server MCP server for all Perforce operations.

Quick setup — add to your .claude/settings.json:

{
  "mcpServers": {
    "perforce": {
      "command": "p4mcp-server",
      "args": ["--port", "ssl:perforce:1666"],
      "env": {
        "P4PORT": "ssl:perforce:1666",
        "P4USER": "<your-username>",
        "P4CLIENT": "<your-workspace-name>"
      }
    }
  },
  "permissions": {
    "deny": ["EnterPlanMode"]
  }
}

IMPORTANT: Run p4mcp-server in read-write mode (NOT --readonly) — the modify_* tools are required for creating CLs, shelving, and submitting.

Full setup guide: docs/perforce-mcp-setup.md

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

2. using-perforce-workspaces - Activates after design approval. Sets up a Perforce workspace on MAIN, creates a numbered pending CL for the task, verifies clean test baseline. For parallel agents: creates per-agent workspaces cloned cheaply from a golden MAIN workspace.

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, and shelve checkpoints. 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, shelve. Deletes code written before tests.

6. requesting-code-review - Activates between tasks. Checks shelved CL diff, dispatches code-reviewer subagent, reports issues by severity. Critical issues block progress.

7. finishing-a-changelist - Activates when tasks complete. Verifies tests, shelves final state, creates/updates Swarm review, presents options (submit/keep/discard), submits to MAIN after approval.

The agent checks for relevant skills before any task. Mandatory workflows, not suggestions.

For depots 100GB+ (or 400GB+), always follow these rules to avoid accidentally triggering operations that scan the entire depot:

• Never sync //... — always use explicit path-limited sync: modify_files({ action: "sync", file_paths: ["//depot/main/path/..."] })
• Never reconcile //... — always path-limited: modify_files({ action: "reconcile", file_paths: ["//depot/main/path/..."] })
• Use golden workspace cloning — copy files from a pre-synced golden workspace instead of re-downloading from the depot
• Use p4 flush for workspace seeding — register cloned files as synced without re-downloading (only needed during workspace creation)

Full details: docs/perforce-workspaces.md

Testing

• test-driven-development - RED-GREEN-REFACTOR cycle (includes testing anti-patterns reference)

Debugging

• systematic-debugging - 4-phase root cause process (includes root-cause-tracing, defense-in-depth, condition-based-waiting techniques)
• verification-before-completion - Ensure it's actually fixed before shelving/submitting

Collaboration

• brainstorming - Socratic design refinement + native task creation
• writing-plans - Detailed implementation plans + native task dependencies + shelve checkpoints
• executing-plans - Batch execution with checkpoints
• dispatching-parallel-agents - Concurrent subagent workflows with workspace isolation
• requesting-code-review - Shelved CL diff review + code-reviewer subagent
• receiving-code-review - Responding to Swarm review feedback
• using-perforce-workspaces - Workspace setup, CL creation, golden clone strategy
• finishing-a-changelist - Shelve → Swarm review → submit to MAIN
• subagent-driven-development - Fast iteration with two-stage review (spec compliance, then code quality)

Meta

• writing-skills - Create new skills following best practices (includes testing methodology)
• using-superpowers - Introduction to the skills system

• Test-Driven Development - Write tests first, always
• Systematic over ad-hoc - Process over guessing
• Complexity reduction - Simplicity as primary goal
• Evidence over claims - Verify before declaring success

Read more: Superpowers for Claude Code

Coming from the Git-based Superpowers workflow? See docs/migration-notes.md for a full concept and skill name mapping.

Quick reference:

Contributions for Claude Code-specific enhancements are welcome!

1. Fork this repository
2. Create a branch for your enhancement
3. Follow the writing-skills skill for creating and testing new skills
4. Submit a PR

See skills/writing-skills/SKILL.md for the complete guide.

Claude Code may automatically enter Plan mode during planning tasks, which conflicts with the structured skill workflows in this plugin. To prevent this, add EnterPlanMode to your permission deny list.

In your project's .claude/settings.json:

{
  "permissions": {
    "deny": ["EnterPlanMode"]
  }
}

This blocks the model from calling EnterPlanMode, ensuring the brainstorming and writing-plans skills operate correctly in normal mode. See upstream discussion for context.

Skills update automatically when you update the plugin:

/plugin update superpowers-extended-cc@superpowers-extended-cc-marketplace

This fork tracks obra/superpowers main branch. Changes specific to Claude Code are additive - the core workflow remains compatible.

MIT License - see LICENSE file for details

• Issues: https://github.com/pcvelz/superpowers/issues
• Upstream: https://github.com/obra/superpowers