One orchestrator, seventeen specialists, three automatic review gates — and a memory that learns from every PR. A practical pattern for working with AI as a team.
The orchestrator never writes code or designs solutions itself. It routes every request to the right specialist, then verifies the work passes through automatic quality gates.
/architectModern foundation models follow instructions literally. Strict delegation is the design — not a limitation.
Invoked with a slash command. Each has its own model, effort level, allowed tools, and a Handoff Contract that defines "done".
These never need to be invoked manually. They are non-optional gates that protect every code change and capture every lesson.
A missed review gate is an orchestrator failure — not a subagent failure.
Below the skills sits invisible infrastructure that catches mistakes, enforces conventions, and survives every context compaction.
Auto-format your code after every save. Block edits to lock files. Run your linter and type-checker before letting the session end. Preserve critical context on compaction. Desktop notification when done.
Different files, different conventions. Backend conventions apply to your server code, frontend rules to your UI code, migration rules to schema changes. Auto-loaded based on path — never the wrong style applied to the wrong file.
Across sessions. Project state, deadlines, recent PRs, feedback, ecosystem warnings, lessons. Indexed in a project memory file. Auto-saved when something surprising happens. Verified against current code before being trusted.
feature/, fix/, chore/migrations/V* without /db-engineer.env readsgit reset --hardUser: "Add a save function to that data-table page." (One sentence. Zero technical detail. The team fills in the rest.)
/architect decides the approach: REST route + optimistic UI updates + rollback on error./frontend implements the UI component and the client-side API call./backend adds or extends the Go endpoint (if backend work is needed).code-reviewer reviews the diff automatically — quality, naming, reuse.security-reviewer runs automatically because a new API route was added./github creates the branch, commits, pushes, opens the PR.teacher writes a ~400-word lesson and schedules concept reviews for spaced repetition.The team doesn't just ship work — it accumulates institutional knowledge that survives every context window.
Every merged PR generates a lesson in memory/lessons/PR-XXX-*.md. ~400 words covering What changed · Why those decisions · Domain concepts · Anti-patterns avoided.
Concepts get reviewed on the Ebbinghaus curve: 7 → 14 → 30 → 90 days → archive. Misunderstood concepts surface again. Mastered ones step aside.
Weekly cadence — auto-scans your repos for version bumps, new migrations, route changes, dependency updates. Writes to a project memory file.
Weekly cadence — multi-agent research team audits platform best practices + each skill domain. CVEs, EOL deadlines, new APIs. Applies improvements automatically.
Result: the team that ships your work today is materially better than the team from a month ago.
code-reviewer and security-reviewer cannot be skipped. Missing one is an orchestrator failure, not an oversight.Skills, subagents, automation, and memory — all coordinated from a single point.