bakhod1r
User109 specialist Claude Code subagents · 16 engineering teams · 11 commands · 10 skills. Architecture → build → verify → ship, with the delegation chain enforced. Installable as a plugin marketplace.
Categories
Indexed Skills (11)
adr
Write an Architecture Decision Record. Use when a decision is hard to reverse — technology choice, service boundary, data model, protocol, vendor, or anything a future engineer will ask "why on earth" about.
agent-registry
Look up which agent or team owns a kind of work in this repository. Use when deciding whom to delegate to, when the user names a role, or when asked "who handles X".
cost-review
Review a design or a running system for cost. Use before committing to an architecture, when a bill jumps, or during quarterly optimisation.
data-contract
Define or review a data contract between a producer and consumers. Use when creating a dataset, event stream, or API that another team depends on.
delegation-protocol
How to route work across teams and agents in this repository. Use when a task spans more than one domain, when you are unsure which agent owns it, or before fanning out to several agents.
marketplace
Install external Claude Code plugins from official marketplaces, and install this repository's own agent plugins. Use when the user wants a capability this roster does not cover, asks about plugins or marketplaces, or wants to share these agents with a team.
onboarding
Get a new user or contributor productive with this agent system. Use when someone asks how to start, how it works, or how to add an agent.
orchestration
Run a task end to end through the full delivery pipeline — product discovery, architecture, build, verification, release. Use when the user gives a goal rather than a specific technical instruction, or invokes /flow.
postmortem
Write a blameless incident postmortem with a timeline and tracked actions. Use after any customer-visible incident, data loss, or security event.
runbook
Write an operational runbook that an on-call engineer can execute at 3am. Use when adding an alert, launching a service, or after an incident exposed a missing procedure.
threat-model
Produce a STRIDE threat model for a system or feature. Use before building anything that handles authentication, money, personal data, file uploads, or third-party input.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.