Skills For Architects

 █████╗ ██████╗  ██████╗██╗  ██╗    ███████╗████████╗██╗   ██╗██████╗ ██╗ ██████╗
██╔══██╗██╔══██╗██╔════╝██║  ██║    ██╔════╝╚══██╔══╝██║   ██║██╔══██╗██║██╔═══██╗
███████║██████╔╝██║     ███████║    ███████╗   ██║   ██║   ██║██║  ██║██║██║   ██║
██╔══██║██╔══██╗██║     ██╔══██║    ╚════██║   ██║   ██║   ██║██║  ██║██║██║   ██║
██║  ██║██║  ██║╚██████╗██║  ██║    ███████║   ██║   ╚██████╔╝██████╔╝██║╚██████╔╝
╚═╝  ╚═╝╚═╝  ╚═╝ ╚═════╝╚═╝  ╚═╝    ╚══════╝   ╚═╝    ╚═════╝ ╚═════╝ ╚═╝ ╚═════╝

Arch Studio

A local-first framework for architecture firms to build, govern, and share their own AI-assisted workflows—use with Codex or Claude Code.

Arch Studio provides a governance layer, persistent studio and project memory, and clear extension points for firm-wide and project-specific skills. The bundled AEC skills and agents are working reference implementations and starting templates: use them directly, study their patterns, or build procedures that reflect how your own practice works.

Firm-created skills remain in the user-owned studio workspace, outside the installed plugin cache. They can stay private to a firm or project, or be developed for contribution back to the open-source project.

One plugin—as v1.5.2—with a shared skill catalog for Codex and Claude Code. The repository contains 4 hooks: Claude Code loads three handlers across two events, while Codex loads one ambient SessionStart hook. Claude Code also loads 8 agents and 8 rules. Created by Federico Negro in 2026 and built by ALPA (hello@alpa.llc). Copyright © 2026 Alpaca Design Lab LLC; MIT-licensed.

What’s new in 1.5.2

The daily update check is now on by default, and its request carries an anonymous usage ping: a random install ID generated once and stored locally, plus the plugin version. No names, account, firm, file paths, project content or user text are sent. Set AS_TELEMETRY_DISABLED=1 to turn the ping off; set AS_UPDATE_CHECK_DISABLED=1 or run /as:studio updates disable to turn the update check off. This replaces the earlier "disabled by default" promise; see Data and privacy below. The Codex package installs no lifecycle hook, so it sends neither.

Skill Maker now requires an observed fresh policy read and a separate observed read of the actual destination after publication; a claimed read or a prepared file compared with itself no longer counts as verification. Upgrading from 1.5.1.2 requires nothing.

What’s new in 1.5.1.2

The first product pillar is now Studio, replacing the retired Governance pillar name. Studio is the product control plane for Account and access, Configuration, Standards, and Assurance. Tooling, Knowledge and Memory are unchanged. This is a content-only terminology correction: technical identifiers, directories, schemas, protocols, skills, agents, record kinds and behavior do not change. Lowercase governance remains in use when it names an actual responsibility, process, rule, policy or data-governance topic.

What’s new in 1.5.1.1

A maintenance patch: the CSI commit hook (pre-commit-spec-lint) is removed. It blocked unrelated commits whenever a date-based ID sat next to the word “spec”. CSI formatting in spec-writer and epd-to-spec is unchanged. Upgrading from 1.5.1 requires nothing.

What’s new in 1.5.1