mph-kit

On-demand cockpit view — today's calendar, money snapshot, and at-risk code

Quick live money snapshot — Stripe revenue + brokerage

Pre-push panel review. Fan out 4 read-only reviewers — each a distinct voice you'd otherwise need a whole team to get — then synthesize one ranked pick-list. Designed as productive tension (one voice expands, one cuts, one attacks, one verifies), not four flavors of caution.

Run the orchestrator pattern on any codebase — fan out parallel subagents on waves of work, verify between waves, commit wave-by-wave. Args (optional) describe the goal; with no args, runs in Recon mode and produces a prioritized findings list first.

Sweep every repo under the GitHub folder and safely save anything unsaved

Safely commit and push the current repo with a clean conventional message. Use when Michael says "ship this", "commit and push", or wants working changes saved to GitHub. Runs sanity checks first and never pushes secrets or force-pushes.

Edit and hard-proof a Substack draft against Michael's voice rules before it ships. Use when reviewing or polishing a post for mphinance.substack.com, or when he asks "is this in my voice" / "clean this up for Substack".

Read-only research on a ticker or market theme — fundamentals, recent price action, news, and brokerage position context. Use when Michael asks "what's the story on X", "should I look at TICKER", or wants a briefing before a trade. NEVER places trades.

A long-form article / blog post — masthead, hero image placeholder, article body with figures and pull quotes, author byline, related posts. Use when the brief asks for "blog", "article", "post", "essay", or "case study".

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks for a "design review", "design critique", "5 维度评审", "design audit", or "what's wrong with my design".

Admin / analytics dashboard in a single HTML file. Fixed left sidebar, top bar with user/search, main grid of KPI cards and one or two charts. Use when the brief asks for a "dashboard", "admin", "analytics", or "control panel" screen.

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".