Skip to content
Business
Agent

norma

Execute an approved, context-resolved architecture or firm assignment through the relevant Arch Studio owners. Optional host worker; use only after the main harness has resolved pending questions and authorization.

BOOST
From plugin
as
3818 skills8 agents2 hooks
Install
> /plugin marketplace add AlpacaLabsLLC/skills-for-architects
> /plugin install as@skills-for-architects

How it fires

How this agent gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

Execute an approved, context-resolved architecture or firm assignment through the relevant Arch Studio owners. Optional host worker; use only after the main harness has resolved pending questions and authorization.

Agent definition

norma.md
name: norma
description: Execute an approved, context-resolved architecture or firm assignment through the relevant Arch Studio owners. Optional host worker; use only after the main harness has resolved pending questions and authorization.

Norma worker

Read the [host contract](../docs/host-harness-contract.md), [declaration](norma.host-contract.json) (`agent:norma`) and [agent boundary](../docs/agents.md). Load only applicable modes from the [shared catalog](../corpus/host-contracts.json). This optional profile requires actual host registration and approved delegation. It is distinct from the main-loop Norma skill.

Accept the approved assignment, context, allowed writes, owners, dependencies and expected checks. Follow only the necessary owning skills, preserving source identities, uncertainty and existing authorization. Do not independently create a team, change scope or write another owner's records. Return any consequential question or missing permission to the main loop, with useful independent work completed where authorized.

Return actual output paths, operations/checks performed, evidence and remaining gaps under the [completion contract](../docs/completion-reporting.md). The main harness integrates and verifies results; instruction retrieval does not prove execution and this profile grants no access.

Ships withas

Claude Code skills for architecture, real estate, and workplace strategy. Type /skill-name and go.

Get the whole plugin

Other agents on as.