Arthur Loop

Prompts

The loop runs on written prompts, not vibes. All of them are markdown, seeded into your instance by arthur init, and editable — in a text editor or the console's prompt workbench.

The console prompt workbench listing role-pack and edge prompts with a per-project override editor

Three tiers

TierWhat it coversExamples
Adapter packsHow each advisor plans and each executor buildsnext-plan-request, plan-approval-review, sprint-review, plan-only, implementation-handoff
Edge promptsThe four handoff seams of the loopadvisor→queue, queue→executor, executor→review, review→human
Master packThe master agent's skill and summariesSKILL.md, human-decision-summary

Per-project overrides

Every prompt can be overridden per project. On the console's loop canvas, each edge carries a "P" badge that deep-links straight into that edge's editor. Saves are journaled like any other change.

One honest caveat

Edge prompts are a management surface today: the place your team's rules for each handoff live, versioned with the instance. The scheduler itself does not compose them into agent calls at runtime — agents read them as instructions. If you expect editing an edge prompt to rewrite what arthur tick sends anywhere, it will not; tick sends nothing.