AGENT ORCHESTRATION

Plan. Build. Review.

A multi-agent pipeline that takes ideas from plan to production using Claude Code.

Model-matched agents Deep reasoning where it counts, fast execution everywhere else
Enforced code quality Adversarial critic loop catches issues before anything ships
Unattended execution Hand it a plan or task ticket and walk away
Single-shot delivery Working, reviewed, tested, and documented code in one run

Pipelines

Agent Roster

Orchestrator
Opus

Master coordinator. Breaks work into subtasks and delegates to specialists; never writes code itself.

Ideator
Opus

Lateral thinker. Explores solution space and stress-tests approaches; output goes to the human, never directly to builders.

🧠 Brainstorming Skill
Researcher
Sonnet

Research specialist. Finds current documentation, compares libraries, and surfaces best practices online.

⌕ WebSearch
Explorer
Haiku

Codebase navigator. Fast, cheap mapping of files, dependencies, and patterns before any task begins.

Architect
Opus

Design authority. Produces written design decisions and file-level plans before any implementation begins.

⌕ WebSearch
Storage
Sonnet

Data persistence specialist. Sole owner of RLS policies; covers Postgres, Supabase, S3, and local filesystem.

Frontend
Sonnet

UI specialist. Owns React, TypeScript, Tailwind, browser APIs, accessibility, and client-side state.

🎨 Frontend Design Skill🌐 Playwright
Backend
Sonnet

Server specialist. Owns API routes, business logic, database queries, auth, and all server-side concerns.

Critic
Opus

Adversarial reviewer. Actively tries to break code with edge cases; returns FAIL with specifics or PASS when solid.

🌐 Playwright
Tester
Sonnet

Test specialist. Writes and runs tests; never marks a task done if tests are red.

🌐 Playwright
Reviewer
Sonnet

Standards checker. Read-only code review returning structured BLOCKER / WARNING / SUGGESTION findings.

🌐 Playwright
Author
Haiku

Documentation specialist. Updates README, docstrings, CHANGELOG after reviewer sign-off.

Opus · Deep reasoning
Sonnet · Balanced
Haiku · Fast & efficient

.claude/ Structure

.claude/ ├── agents/ │ ├── architect.md · Opus │ ├── author.md · Haiku │ ├── backend.md · Sonnet │ ├── critic.md · Opus │ ├── explorer.md · Haiku │ ├── frontend.md · Sonnet │ ├── ideator.md · Opus │ ├── orchestrator.md · Opus │ ├── researcher.md · Sonnet │ ├── reviewer.md · Sonnet │ ├── storage.md · Sonnet │ └── tester.md · Sonnet ├── commands/ │ ├── build.md │ ├── explore.md │ ├── plan.md │ └── review.md └── skills/ ├── agent-team-ways-of-working/ ├── brainstorming/ ├── frontend-design/ └── token-analyser/

When to Use What

Scenario Command Notes
New feature from scratch /plan → /build Run /plan first to generate a design plan, then hand it to /build for full pipeline execution.
Clear spec, just build it /build <plan> Passes plan directly to the full pipeline — Explorer, Architect, and builders all run in sequence.
Harden existing code /review Runs explorer → critic → adversarial loop → reviewer; no new code is written, only issues surfaced.
Explore options before deciding /plan Activates the brainstorming skill, then ideator and architect agents to produce options for human review.
Quick everyday task Lite mode (auto) Default mode — no command needed. Runs explorer → builder → reviewer automatically for routine asks.
Large multi-domain feature /build (full pipeline) Full pipeline: explorer → architect → builders → adversarial critic loop → tester → reviewer → author.