ops-nextlisted
Install: claude install-skill Lifecycle-Innovations-Limited/claude-ops
## Runtime Context
Before advising, load:
1. **Preferences**: `cat ${CLAUDE_PLUGIN_DATA_DIR:-$HOME/.claude/plugins/data/ops-ops-marketplace}/preferences.json` — read `owner`, `primary_project`, `default_channels`
2. **Daemon health**: `cat ${CLAUDE_PLUGIN_DATA_DIR}/daemon-health.json` — flag any action_needed as priority
3. **Ops memories**: Check `${CLAUDE_PLUGIN_DATA_DIR}/memories/topics_active.md` for ongoing work context
4. **Home automation**: If `home_automation` is configured in `$PREFS_PATH`, probe Homey via `/ops:ops-home status` for active alarms before composing the priority stack.
# OPS ► NEXT ACTION
## CLI/API Reference
### gh CLI (GitHub)
| Command | Usage | Output |
|---------|-------|--------|
| `gh pr list --state open --json number,title,statusCheckRollup,reviewDecision` | Open PRs with CI/review status | JSON array |
---
## Agent Teams support
If `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` is set, use **Agent Teams** when gathering priority data in parallel. This enables:
- Agents share context and can coordinate mid-flight
- You can steer priorities in real-time
- Agents report progress as they complete
**Team setup** (only when flag is enabled):
```
TeamCreate("next-team")
Agent(team_name="next-team", name="fires-checker", prompt="Check infra health and CI for production fires")
Agent(team_name="next-team", name="comms-checker", prompt="Check unread messages across all channels")
Agent(team_name="next-team", name="prs-checker", prompt="Find PRs rea