Skip to main content

living-architecture

A Claude Code plugin (la) plus its command-line tools that keep agent-written code from drifting into spaghetti, and keep each change on a reviewed plan.

  • An architecture that is enforced, not just drawn. A LikeC4 model maps nodes to code modules, and its arrows decide which module may import which. la-arch-check measures the real imports against the model. Grandfathered arrows are marked #legacy and only ever shrink. Each node carries arc42 principles with status tags, and agents treat the model and the principles like tests: changes need your approval.
  • A four-stage PR flow. /la:pr interviews you into a Codex-reviewed OpenSpec plan, writes the failing tests, implements until they pass, and then loops CI, Codex, CodeRabbit and Sonar reviews until every gate is clean. Each stage resumes from the branch name alone, and the plan is archived with the code.
  • Refactoring without import churn. Python moves and renames rewrite every import automatically, and the type checker proves nothing was left dangling.

The longer version is in Living architecture, explained.

Install

# the plugin
/plugin marketplace add MotleyAI/living-architecture
/plugin install la@living-architecture

# the commands (la-*, dr-*), pinned to the same version as the plugin
uv tool install living-architecture==0.2.3

The commands ship as a PyPI package and as an npm package of the same name; each serves its own ecosystem and calls the other for mixed repos (details). Skills check that the installed commands match the plugin before they run.

Quick start

In the repo you want to onboard, run:

/la:init

It detects your tracker, test, lint and type-check commands, Codex, Sonar and any existing OpenSpec or architecture setup, then proposes a living-architecture.yaml and asks only about what it cannot detect. It then offers to set up OpenSpec, record the type-check baseline and build the architecture model with /la:arch-init. After that, start each change with /la:pr on a branch named after its issue.

Skills

Skill Purpose
la:init Onboard a repo: detect its tools, write living-architecture.yaml, offer the next setup steps
la:pr Run a change through plan → failing tests → implementation → review
la:arch-init Build the first architecture model from the measured code, then its principles
la:arch-cleanup Retire a batch of #legacy arrows, or carve a new boundary, with verified moves
la:deterministic-refactor Rename or move Python code, proven complete by the type checker

These skills call helper skills that you can also run on their own; see Skills.

Prerequisites

Always: git, bash, gh (authenticated) and jq.

Per gate, as living-architecture.yaml enables it:

Gate Needs
tracker: linear the Linear MCP server
tracker: github nothing beyond gh
openspec: true npx (the OpenSpec CLI)
architecture: true npx (the LikeC4 CLI); the npm twin for TypeScript code
reviewers.codex: true the Codex MCP server (mcp__codex__codex)
Sonar on your PRs the SonarQube MCP server
type-check gate the repo's type checker (basedpyright, tsc)

Documentation

Metadata

Release files for living-architecture 0.2.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for living-architecture 0.2.3
File Size Uploaded
living_architecture-0.2.3.tar.gz 85.3 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for living-architecture 0.2.3
File Interpreter ABI Platform
living_architecture-0.2.3-py3-none-any.whl Python 3 none any Details

Total release size: 205.7 kB

Release files / living_architecture-0.2.3.tar.gz

Download URL living_architecture-0.2.3.tar.gz
Size 85.3 kB
Tags Source
SHA-256 checksum
How to use checksums
eec5d8b0b2101a29930d5d3d3b665e95b88a74223c99ab1493e9816af48aaa5c
BLAKE2b-256 checksum
How to use checksums
b9fc5ec753c21b2139acb516d66a6bb54316a6f3ce6a5d2ecf3e7695f49a9731
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 5, 2026.

Transparency log

Release files / living_architecture-0.2.3-py3-none-any.whl

Download URL living_architecture-0.2.3-py3-none-any.whl
Size 120.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
88609c5de06dedb3545b8e57d934c17e026fc3e17e5764e9835b26f682b7aeac
BLAKE2b-256 checksum
How to use checksums
64b4a18927cdf385cb46b0c1c531738c36d2e56d8755d9b94922eae8f793b510
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 5, 2026.

Transparency log

Release history Release notifications | RSS feed

0.3.1

2 release files

0.3.0

2 release files

This release

0.2.3 This release

2 release files

0.2.2

2 release files

0.2.1

2 release files

0.2.0

2 release files

0.1.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page