os.Claude

in production since 2026-06-03

One designer.
Nine agents.
A working practice.

os.Claude is a six-layer operating model that runs a real design practice on Claude Code. Agents triage, build, review, and merge. Routines run overnight. Every skill, convention, and profile that makes it work is documented here — and free to take.

12

agents and operators

94

canon artefacts

123

pull requests merged

36

days in production

What this is

Not a product. A practice, made legible.

It runs. This is not a concept or a demo. The agents on this site ship the software, sweep the pipeline, plan the week, and write the morning brief for a working design practice — every day, on schedules.

It is documented. Every behaviour is written down as an artefact: skills, tasks, routines, agent profiles, conventions. The system reads its own documentation to run; the site is generated from the same source.

It is yours to take. All 94 artefacts are downloadable as plain markdown. Use them as a starting point for your own operating model — the ideas hold beyond one practice.

Layer 03

The fleet

Each agent is a named role with a mission, a remit, and hard boundaries. No human names — an addition to the ways of working, not a person replaced.

A1-DEagent

Aide

personal chief-of-staff

the Owner-serving personal chief-of-staff: sweeps the committed cycle for what needs Aled, sizes it, and books it into his work.Hold calendar window (propose-and-confirm)

ATL-4Sagent

Atlas

planning / strategy

planning and strategy: goals, prioritisation, and cycle commitment

F0-RGEagent

Forge

implementation

implementation: builds a ticket and opens a PR, never merges

P1-XELagent

Pixel

Agent

brand and design: the design system, brand identity, and visual production across the ventures

PR-1SMagent

Prism

review and quality

review and quality: the independent verdict and good-to-merge signal

PUL-5Eagent

Pulse

system health and self-improvement

ops and self-improvement: parity, friction capture, task health, optimisation review, and the model-and-schedule efficiency of the scheduled layer; propose-only

R3-ACHagent

Reach

Agent

marketing and go-to-market: strategy, content, channels, lifecycle, and discovery across the ventures

R3-LAYagent

Relay

delivery management

delivery management: triage, routing, blocker resolution, and the post-approval merge

SC-0UTagent

Scout

pipeline: relationships and opportunities

pipeline: captures people and opportunities into Linear and qualifies them

SO-N4Ragent

Sonar

design strategy and discovery

design strategy, discovery and service design: building a consulting-grade understanding of who a venture serves, the jobs they are trying to do, and how well the experience and serv…

CONTENT-ENGINEagent

Content-engine

Agent

Three-stage content pipeline — truth capture to case study to article — governed by cos-tov throughout

operator-baraoperator

Bara

vertical owner, BARA relaunch

The Operator of the BARA vertical — owns BARA's relaunch outcome end-to-end within a granted mandate, commanding the functional fleet through Relay and reporting to the Owner

Layer 04

How a ticket becomes shipped software

01

R3-LAY

Relay triages the ticket and routes it

02

F0-RGE

Forge builds it and opens a pull request

03

PR-1SM

Prism reviews it and writes the verdict

04

R3-LAY

Relay merges on approval, marks it Done

The operator gates what matters; a clean pass routes itself. QA bounces are capped at two strikes before a human looks. Overnight routines drain the backlog on cheap tokens.

The model

Six layers, two of them read-only

The story

"The unlock wasn't automation. It was writing the practice down precisely enough that something else could run it."

Open canon

Take the artefacts

Every skill, agent profile, convention, and routine — plain markdown, no sign-up, no licence theatre. If it helps you build your own operating model, it has done its job twice.