By Wilder1222
Plan Lean, Execute Complete — A fused AI coding skill framework for Claude Code.
Trigger the **brainstorm** skill.
Update all project documentation after shipping.
Trigger the **executing-plans** skill.
Trigger the **frontend-design** skill with **automatic mode detection**.
Run a full **harness engineering audit** on the superomni skill framework — evaluate context efficiency, tool action space, evaluation gate coverage, feedback loops, and documentation freshness.
Diff-driven technical documentation generation and updates. Reads actual code changes and keeps README, CHANGELOG, ARCHITECTURE in sync.
Read-only isolated-context repo exploration and evidence gathering. Absorbs the Phase-2 evidence-gathering role of the retired debugger agent. Returns a structured EXPLORATION REPORT; does NOT modify files.
UX review with 10-dimension scoring, AI slop detection, and accessibility audit. Dispatched by frontend-design (quality gate), plan-review (design phase on UI plans), executing-plans (UI steps), and code-review (on UI file diffs). Renamed from the previous `designer` agent.
Canonical multi-mode review agent. Six modes: planning (plan authoring), strategy (CEO lens — scope, demand validation), engineering (architecture review), evaluation (independent verdict gate), security (OWASP audit + dependency CVE), code-review (P0/P1/P2 layered review). Absorbs the retired planner, architect, ceo-advisor, evaluator, security-auditor, and code-reviewer agents.
Safe, behavior-preserving code refactoring with tests-first protocol. One change at a time. Keeps the test suite green throughout.
Turn a fuzzy idea into a concrete, reviewable spec via structured dialogue. THINK stage entry. Triggers: "brainstorm", "design", "spec this out", "let's think through".
Safety guardrails that activate before high-risk operations. Prevents destructive, irreversible, or security-sensitive changes without explicit confirmation. Triggers: destructive operations, production configs, database migrations, security-sensitive files, "be careful", "careful mode".
Structured P0/P1/P2 code review of WRITTEN CODE (not plans). Three modes: giving / receiving / security. Triggers: "review this code", "ready for PR", "address review", "security audit". NOT for reviewing plans — use plan-review for that.
Dependency security, license, and freshness audit. Dispatches dependency-auditor agent to scan all package managers. Triggers: "dependency audit", "check dependencies", "npm audit", "security scan", "check for vulnerabilities", "outdated packages", "license check".
Post-ship documentation update. Cross-references the diff, updates README, ARCHITECTURE, CONTRIBUTING, CLAUDE.md to match what shipped. Polishes CHANGELOG voice, cleans up TODOs, optionally bumps VERSION. Triggers: "update docs", "sync documentation", "post-ship docs", "update the readme", "document what shipped". Proactively suggest after a PR is merged or code is shipped.
Uses power tools
Uses Bash, Write, or Edit tools
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.
Plan Lean, Execute Complete — A fused AI coding skill framework for Claude Code, Codex, Gemini CLI, and GitHub Copilot.
Current stable version: 0.6.11
superomni is an opinionated AI coding skill framework for Claude Code, Codex, Gemini CLI, and GitHub Copilot.
superomni is a collection of skills — structured behavior specifications for AI coding assistants. Each skill tells Claude Code exactly how to handle a specific type of work: brainstorm, planning, debugging, testing, reviewing, shipping.
The framework is built on one core philosophy:
Plan with YAGNI. Execute with completeness.
Plan only what you need. But what you decide to build — build it fully.
THINK → PLAN → REVIEW → BUILD → VERIFY → RELEASE
One human gate: spec approval at THINK. Everything after auto-advances on DONE. The RELEASE stage combines ship + retrospective into a single artifact.
| Platform | Slash Commands | Recommended Install |
|---|---|---|
| Claude Code | ✅ Full support | Plugin (recommended) or npx |
| Gemini CLI | ✅ Full support | npx |
| GitHub Copilot (VS Code) | ✅ Via prompt files | npx |
| GitHub Copilot (CLI) | ⚠️ Plugin only | Plugin |
| Codex CLI | ❌ Not supported | npx (context via AGENTS.md) |
/plugin marketplace add Wilder1222/superomni
Installs skills, slash commands, and session hooks automatically. Type /vibe to start.
npx github:Wilder1222/superomni --only claude
Installs slash commands to .claude/commands/ and skills to .superomni/. Works identically to the plugin for slash command support.
npx github:Wilder1222/superomni --only gemini
Installs slash commands to .gemini/commands/ as .toml files. Type /vibe, /brainstorm, etc. directly in Gemini CLI.
npx github:Wilder1222/superomni --only copilot
Installs slash commands to .github/prompts/ as .prompt.md files. Use /vibe, /brainstorm, etc. in VS Code Copilot Chat.
Copilot CLI users: Slash commands are not supported in
gh copilotCLI. Install via plugin instead:/plugin marketplace add Wilder1222/superomni
npx github:Wilder1222/superomni --only codex
Installs project context to AGENTS.md. Codex CLI does not support custom slash commands (they are hardcoded in the binary). Activate skills using trigger phrases in conversation — e.g., "brainstorm this feature", "write a plan", "debug this".
# Project-level: install into current directory
npx github:Wilder1222/superomni
# Global: symlink skills to all detected CLI directories
npm install -g github:Wilder1222/superomni && superomni setup
npx github:Wilder1222/superomni --only claude # Single platform
npx github:Wilder1222/superomni --skip gemini # Skip a platform
npx github:Wilder1222/superomni --force # Overwrite existing files
npx github:Wilder1222/superomni --dry-run # Preview without changes
superomni upgrade # Upgrade global install
Open your project in your AI CLI. Skills activate automatically.
Claude Code — use slash commands:
/vibe — activate the full framework, auto-detect pipeline stage/brainstorm — design a feature from scratch/write-plan — turn an idea into an executable plan/execute-plan — run the plan step by step/review — structured code review/release — ship + retrospective in one combined step/front-design — frontend design optimization/style-capture — capture code style preferencesCodex / Copilot / Gemini — use trigger phrases:
| Skill | When to Use | Key Output |
|---|---|---|
vibe | Framework activation / entry point | Auto-detects pipeline stage |
using-skills | Always active | Loads the framework |
brainstorm | New feature/design | docs/superomni/specs/spec-*.md |
writing-plans | Planning implementation | docs/superomni/plans/plan-*.md |
executing-plans | Running a plan | Code changes + report |
systematic-debugging | Any bug/error (includes scope lock via /freeze) | Debug report + fix |
npx claudepluginhub wilder1222/superomni --plugin superomniAI Football Intelligence System for the 2026 FIFA World Cup — multi-model prediction, team analysis, player evaluation, and schedule lookup.
Universal intent router for Claude Code. One command that picks the highest-ROI skill automatically — GSD, Superpowers, or gstack.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review