By mzored
Run structured Codex-backed workflows directly from Claude Code: brainstorm and design, plan implementations, dispatch parallel tasks, enforce TDD red-green-refactor, debug with root-cause analysis, review code with verification gates, and complete branches with merge/PR/discard options.
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. Codex-backed variant.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Complete development work with Codex-backed branch analysis and structured finish options. Use only when the user explicitly asks for the Codex-backed branch finishing workflow.
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
Request a high-signal Codex-backed review of a diff or task result. Use when completing tasks, implementing major features, or before merging. Codex-backed variant.
Admin access level
Server config contains admin-level keywords
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.
Claude orchestrates. Codex executes. One plugin, two models.
A Claude Code plugin that combines Claude's orchestration and judgment with GPT's speed at bounded coding tasks. Forked from obra/superpowers, adapted for Codex CLI delegation.
Claude and GPT have complementary strengths:
| Claude | GPT (via Codex) | |
|---|---|---|
| Best at | Orchestration, planning, user dialogue, subagent coordination | Fast code generation, debugging, diff review |
| Role here | Controller — owns the conversation thread | Worker — executes bounded tasks |
| Speed | Thoughtful, context-rich | Fast mode available for supported Codex models |
The plugin keeps Claude in the driver's seat for design decisions and workflow control, while delegating execution-heavy work to Codex — getting the best of both worlds.
User ↔ Claude (controller)
│
├─ skills/ SKILL.md workflows guide Claude's decisions
│
├─ MCP Server scripts/mcp-server.mjs (primary transport)
│ ├─ codex_research read-only repo exploration
│ ├─ codex_plan first-pass implementation plans
│ ├─ codex_implement bounded coding tasks
│ ├─ codex_review structured or advisory diff review
│ ├─ codex_debug root cause investigation
│ ├─ codex_branch_analysis branch readiness check
│ └─ codex_resume resume existing thread
│
└─ Codex CLI respects ~/.codex/config.toml (model + effort) by default
# Add the marketplace
/plugin marketplace add mzored/superpowers-cc-to-codex
# Install the plugin
/plugin install superpowers-cc-to-codex@superpowers-cc-to-codex
Want the original Superpowers without Codex delegation? See obra/superpowers.
.claude/codex-defaults.json is automatically created on first use. By default it defers every model/effort decision to your ~/.codex/config.toml and only opts into the ChatGPT-account fast service tier:
{
"model": "auto",
"modelMini": "auto",
"effort": "auto",
"serviceTier": "fast"
}
| Key | Description | Default |
|---|---|---|
model | Model for implementation, review, resume. auto defers to ~/.codex/config.toml. | auto |
modelMini | Model for research, planning, debug, branch analysis. Falls back to model if not set. auto defers to ~/.codex/config.toml. | auto |
effort | Reasoning effort: auto, minimal, low, medium, high, xhigh. auto defers to ~/.codex/config.toml. | auto |
serviceTier | Set to "fast" for GPT Fast mode (requires ChatGPT auth). | fast |
Resolution: explicit MCP args → project config → tool defaults. auto is a sentinel that means "do not pass -m / -c model_reasoning_effort to Codex CLI", so your global Codex configuration wins. Per-call overrides always trump these defaults.
Example — pin reasoning effort to xhigh for this project regardless of your global Codex config:
{ "effort": "xhigh", "serviceTier": "fast" }
| Environment variable | Effect |
|---|---|
SUPERPOWERS_CODEX_LOG_FILE | Appends sanitized Codex and MCP lifecycle events as JSON Lines. Prompt text is redacted. |
SUPERPOWERS_CODEX_LOG=1 | Mirrors sanitized lifecycle events to stderr as JSON for local debugging. |
Run npm run doctor -- --verbose with SUPERPOWERS_CODEX_LOG_FILE set to summarize the last 100 events by mode, retry count, recent errors, and p50/p95 invocation duration.
| Skill | What it does | MCP Tool |
|---|---|---|
brainstorming-codex | Design exploration with bounded repo research | codex_research |
writing-plans-codex | Plan creation with Codex first-pass drafting | codex_plan |
subagent-driven-development-codex | Task execution with implementer + reviewer | codex_implement + codex_review |
requesting-code-review-codex | Structured or advisory diff review | codex_review |
receiving-code-review-codex | External feedback reception with verification | codex_review |
systematic-debugging-codex | 4-phase debugging with root cause investigation | codex_debug |
test-driven-development-codex | Strict red-green-refactor TDD | codex_implement (TDD mode) |
finishing-a-development-branch-codex | Branch completion with readiness analysis | codex_branch_analysis |
dispatching-parallel-agents-codex | Parallel independent-domain dispatch | codex_implement (parallel) |
verification-before-completion-codex | Evidence-before-claims safety gate | Claude-side only |
using-git-worktrees-codex | Isolated worktree setup with safety checks | Claude-side only |
npx claudepluginhub mzored/superpowers-cc-to-codex --plugin superpowers-cc-to-codexHarness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
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).
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.