Getting started
From nothing to a supervised repository: install the tool, create the layer, project every worker's instruction file from the one policy, and read the briefing the next worker is given.
-
1
Install
Nothing outside two places, and never as root.
-
curl -fsSL https://majordomus.dev/install.sh | sh
-
-
2
Create the layer
Writes .ai/ and refuses an existing one.
-
majordomus init
-
-
3
Project
Every instruction file from the one policy.
-
majordomus update
-
-
4
Brief
What the next worker needs to know now.
-
majordomus context
-
Verify the install
It checks governance only: is Majordomus itself healthy, and is every enforcement it declares actually wired here?
-
majordomus version -
majordomus doctor
The first briefing
What majordomus context printed in a run the generator recorded, with the machine and the clock redacted.
$ majordomus context
# Majordomus context — <time> # a projection of durable state, not a source of truth: validate every line against git ## GIT repository <repo> branch main head <sha> working_tree dirty task_record exact (recorded head <head>) ## TASK id t-<id> task narrow the parser profile implementation owner <owner> outcome active scope lib started <time> (<age> ago) checkpoint <time> (<age> ago, interval 15m)