concrete idea → shipped product
The lifecycle
Four stages, owned alternately by the PO (you) and Eng (the plugin). Pick a stage to spotlight its commands.
Get started — your first feature
The engine inside every command
No command is one-shot. Each runs a loop until a machine-checkable gate is green — and,
with --codex, until a second AI agrees too.
Generate
A subagent drafts the artifact or patch in a fresh context window.
Codex pass
An independent AI critiques — write phases isolate it in its own git worktree.
Check
Automated gates run: lint, typecheck, tests, a11y, Playwright, ship-gates.
Converged?
Green + Codex approves → mirror to GitHub, swap labels, suggest the next command. Else loop.
exit = Claude self-assessment ✓ AND Codex verdict = approved | n/a AND gate green
A conjunction — the generator can never approve its own work alone. Flat 3× → PLATEAU.md; Claude ✓ vs Codex ✗ 3× → DISAGREEMENT.md.
Commands
cap iteration cap · ⌁ Codex tier · <tag> artifact mirrored to GitHub · label issue transition
No commands match that filter.
Skills
Reusable behavior modules. Universal ones load on every command; phase-specific ones power one stage.
No skills match that filter.
Agents
Specialized subagents commands fan out to — each runs in a fresh context window so the main thread stays under budget.
No agents match that filter.
What makes it FoWork-specific
The generic lifecycle is tailored to the work-ssot monorepo — its branch model, deploy signal, and demo flow.