armanisadeghi/matrx-ship

work-loop

Use whenever adding work to, coordinating, or working an Autonomous Work Loop campaign: atomic claims, full in-scope autonomy, routine-blocker repair, evidence-gated closure, and independent verification.

campaign-pattern

The Campaign Pattern — how a vision becomes a finished, verified, deployed system with near-zero owner involvement. READ BEFORE launching or coordinating any large build, module, campaign, or multi-agent project: the owner's five launch moves, the…

consolidate

Take ONE registry node (Domain, Feature, or Sub-feature) and end its documentation sprawl: census every repo, extract everything that carries MEANING into the node's doc kit in common-docs, and DELETE it from the repos it came from — proven by a re-grep, not…

aws-production-operations

Operate, inspect, diagnose, and safely deploy the AI Matrx ECS/Fargate production platform in AWS us-east-1 without browser access. Use for AWS platform status, ECS services/tasks, CloudWatch logs, alarms, ECR images, ECS Exec, Terraform changes, failover…

supabase-region-migration

Safely inspect, rehearse, verify, and cut over the AI Matrx Supabase Postgres region migration from Matrx Main in us-west-1 to the prepared AI Matrx project in us-east-1. Use for Supabase region-move status, logical backup/restore, project capacity,…

fleet-incident

Diagnose and durably fix anything broken on the Matrx fleet (deploys stuck, services behind/unreachable, red fleet-health, sandboxes misbehaving). Use whenever the operator reports "X isn't working / isn't updating / shows behind" on the /srv host, the EC2…

add-managed-service

Add a new PyPI-published aidream package as a fully-managed microservice — auto-deploy from PyPI, fleet check, Secrets store, Services page — like matrx-files and matrx-seo. Use when the user says "set up <package> to autodeploy / be managed on the ship…