BlogCraft

The Claude Code workflow that runs eleven products

Orchestrator in main context, specialists in subagents, MCPs over CLI, skills over memory. The concrete setup I use to own an entire vertical alone.

I don't write much code anymore. I orchestrate. Here's the actual setup.

The mental model

Claude Code is a team, not a tool. The main conversation is the orchestrator — it routes, decides, and synthesizes. Specialized agents do the work in isolated contexts. MCPs handle service calls. Skills encode workflows.

If I'm reading files or writing Python, something's wrong with my routing.

The four-tier hierarchy

TierWhat lives hereWhy
Main contextArchitecture decisions, skill routing, synthesisPreserves "session state" across interactions
SubagentsImplementation, exploration, verificationIsolates token usage, parallelizes work
MCPsService calls (Supabase, Sentry, Vercel, PostHog)Structured output beats parsing CLI stdout
SkillsPackaged workflows (ship, review, investigate, qa)Forces discipline where I'd otherwise cut corners

What this looks like in practice

"Ship the new booking flow" isn't me writing code. It's:

  1. /ship skill routes me through test → review → commit → PR
  2. security-reviewer agent audits the diff in parallel
  3. mcp__plugin_supabase_supabase__apply_migration runs the schema change
  4. mcp__plugin_vercel_vercel__ triggers the preview deploy
  5. I read the agent reports, approve or iterate
  6. Main context writes a handoff note to tasks/session-state.md for the next session

Total time from "ship it" to merged PR: roughly 20 minutes for a typical feature. Most of that is me reading agent output.

The rule that actually matters

Delegate before you explore. The default trap is to start reading files to "get context" before routing. By the time you're oriented, you've burned 40% of your session on grep output that a subagent could have produced in parallel.

If a task will touch 2+ files, spawn an agent. If it needs deep codebase exploration, spawn an Explore agent. You write the prompt, it does the reading, you read the summary.

What I don't use Claude Code for

  • Naming variables. I name things; AI picks boring names.
  • Product decisions. AI has no skin in the game.
  • Writing this post. I write the ideas, AI edits for tightness.

The skill ceiling of this workflow isn't "prompt better." It's "understand your own product better, so your taste scales." AI is leverage on judgment, not a substitute for it.