Parallel persona planning for new projects. Research agent runs first to build domain context, then Architect, PM, and Security agents run in parallel. Synthesis agent combines all perspectives into a detailed GSD-style PLAN.md with Tensions section.
Run once per project: ws-skills plan
Reads BRIEF.md from the project root (or prompts for one). Asks 5 clarifying questions before planning.
Brief + Q&A
↓
Research agent (sequential) ← domain landscape, ecosystem, hidden complexity
↓
┌─────────────────────────────────────┐
│ Architect │ PM │ Security (parallel)│ ← spawn 3 subagents simultaneously
└─────────────────────────────────────┘
↓
Synthesis ← combines all into PLAN.md
Builds domain context that all other agents receive. Covers:
Output: research.md
Spawn all three simultaneously using the Agent tool. Each receives the full brief, Q&A, and research output as context.
Agent 1 — Architect
Agent 2 — PM ← launch all three in a single message, do not wait
Agent 3 — Security
Wait for all three to complete before running Synthesis.
Architect output: architect.md
PM output: pm.md
Security output: security.md
Combines research + all three persona outputs into a single PLAN.md covering:
Output: PLAN.md
| Action | Tool |
|---|---|
Read BRIEF.md | Read |
Write persona output files (architect.md, pm.md, etc.) | Write |
| Spawn Architect, PM, Security personas in parallel | Agent (3 calls in one message) |
| Search the brief for keywords | Grep |
All files written to .wednesday/plans/ in the target directory:
.wednesday/plans/
├── research.md ← domain context
├── architect.md ← technical design
├── pm.md ← phases and metrics
├── security.md ← threat model
└── PLAN.md ← combined PRD (primary output)
Each agent fails independently. If one fails, the others continue and synthesis runs with whatever data is available. Failed agents show [partial fallback] in the progress display.
CODEBASE.md for greenfield projects — it doesn't exist yet