-
Notifications
You must be signed in to change notification settings - Fork 21
Getting Started
Get claude-ops running in about 5 minutes. The only prerequisite is Claude Code 1.0+.
Inside Claude Code, run:
/plugin marketplace add Lifecycle-Innovations-Limited/claude-ops
This registers the Lifecycle Innovations marketplace with your local Claude Code instance. You only need to do this once.
/plugin install ops@lifecycle-innovations-limited-claude-ops
Claude Code downloads the plugin, wires up the 14 slash commands (/ops:go, /ops:setup, etc.), and activates the bundled Telegram MCP server declaration. No restart required.
/ops:setup
The wizard opens an interactive session that walks through every integration step by step. It starts by detecting what's already installed:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
OPS ► SETUP WIZARD
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Shell: zsh → ~/.zshrc
Core CLIs: ✓ jq ✓ git ✓ gh ✓ aws ✓ node
Channels: ✓ wacli ✓ gog ○ telegram (no token)
MCPs: ✓ linear ✓ sentry ○ slack ○ vercel
Registry: 0 projects
Preferences: not set
──────────────────────────────────────────────────────
The wizard then asks which sections to configure using structured selectors — no config files to edit manually.
| Section | What happens |
|---|---|
| Install CLIs | Installs jq, gh, aws, node, doppler, sentry-cli via Homebrew as needed |
| Configure channels | Guides you through Telegram, WhatsApp, Email, Slack setup |
| Configure MCPs | Connects Linear, Sentry, Vercel, Gmail via OAuth |
| Companion plugins | Optionally installs GSD for project roadmap tracking |
| Build registry | Registers your projects (aliases, repo names, ECS clusters, revenue stage) |
| Save preferences | Stores owner name, timezone, default channels |
| Shell env | Exports CLAUDE_PLUGIN_ROOT in your shell profile |
/ops:setup telegram
/ops:setup calendar
/ops:setup registry
/ops:setup cli
Once at least GitHub CLI (gh) is authenticated and your registry has at least one project:
/ops:go
Claude pre-gathers all data via parallel shell scripts (infra, git status, open PRs, CI failures, unread messages, calendar), then presents a unified dashboard:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
OPS ► MORNING BRIEFING — Mon 12 Apr 2026
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
FIRES none
COMMS 3 WhatsApp, 1 Slack, 0 email
PRs myapp#47 (ready to merge)
myapp#48 (CI failing)
CI myapp: passing
myother-service: 2 failures (main)
SPRINT 8 open, 3 in progress, 1 blocked
REVENUE $312 AWS this month (+8% vs last)
CALENDAR 10:00 Standup 14:00 Investor call
──────────────────────────────────────────────────────
→ /ops:next to get your first action
/ops:next
/ops:next applies the built-in priority stack — fires first, then urgent comms, then ready-to-merge PRs, then Linear sprint work, then GSD roadmap work — and routes you to the right skill.
If you want to develop the plugin or use a local checkout:
git clone https://github.com/Lifecycle-Innovations-Limited/claude-ops ~/Projects/claude-ops-marketplaceThen inside Claude Code:
/plugin marketplace add ~/Projects/claude-ops-marketplace
/plugin install ops@claude-ops-marketplace
After making changes:
/reload-plugins
- Integrations — understand every integration option
- Use Cases — see how other users run their day
- Skills Reference — full argument reference for every command