🧪 Community ✓ Claude Code ✓ Claude Desktop Standalone • Devops-pack
Devops Pack
DevOps & Reliability — cross-vendor on-call handoffs, incident postmortems, deploy health, and error-budget tracking across whatever incident-management and observability tools you have connected.
Installation
Install this plugin individually:
/plugin marketplace add wyre-technology/msp-claude-plugins --plugin devops-pack Or install all MSP plugins at once:
/plugin marketplace add wyre-technology/msp-claude-plugins Features
- Error Budget Tracking
- Incident Postmortem
- Oncall Handoff
Skills
This plugin provides 3 skills that teach Claude about Devops Pack:
| Skill | Description |
|---|---|
error-budget-tracking | Error-budget and burn-rate assessment from whatever observability tools (Sentry, Datadog, Grafana, BetterStack) are connected: SLI, SLO, error budget, and burn rate applied practically, how to compute burn rate from available SLI data and the thresholds that make it actionable, what separates a budget-threatening trend from noise, and the fallback to raw trend reporting against a trailing baseline when no formal SLO is defined. |
incident-postmortem | Assembling a blameless postmortem grounded in systems of record: timeline reconstruction merging the incident tool's event log with correlated observability anomalies (Sentry error spikes, Datadog/Grafana metric anomalies, including precursor signal that predates formal detection) and deploy history from connected platform connectors, all normalized to one stated timezone; the root-cause versus contributing-factor distinction and the test for telling them apart; and how to label a root cause that is still only a hypothesis. |
oncall-handoff | Assembling an on-call shift handoff from whatever incident-management tool (Rootly, PagerDuty, BetterStack) is connected, plus corroborating observability signal where available: the four handoff categories in priority order (currently paging, escalated without an owner, last-shift history, known-flaky watch list), why an empty open-incidents list is not an empty handoff, and the bar for calling an alert known-flaky rather than simply resolved. |
Agents
This plugin provides 3 agents for autonomous task execution:
| Agent | Description |
|---|---|
oncall-handoff-builder | Use this agent when an on-call engineer needs a structured shift handoff brief — what's currently paging or unresolved, what happened during the last shift, known-flaky alerts to watch, and anything escalated but not yet actioned — assembled from whatever incident-management tool is connected. |
postmortem-drafter | Use this agent when an engineer, SRE, or incident manager needs a full blameless postmortem drafted from a resolved incident — identified by ID or by a rough time window — reconstructed from the incident tool's event log plus correlated observability and deploy data. |
reliability-scorecard | Use this agent when a team lead, SRE, or engineering manager needs a ranked reliability status across connected services — error-budget burn rate where a formal SLO exists, degrading to raw error-rate/uptime trend reporting where it doesn't — worst service first. |
Commands
Available slash commands:
| Command | Description |
|---|---|
/error-budget | Run the reliability scorecard for one service, or every connected service if omitted - error-budget burn rate where an SLO is defined, trend reporting otherwise |
/oncall-brief | Generate the current on-call handoff brief - what's paging, what's escalated without an owner, last-shift history, and known-flaky alerts to watch |
/postmortem | Draft a blameless postmortem for a given incident (by ID or name), or the most recent significant incident within a time window |
API Reference
| Base URL | |
| Authentication | |
| Rate Limit | |
| Documentation |
Example Usage
Run the reliability scorecard for one service, or every connected service if omitted - error-budget burn rate where an SLO is defined, trend reporting otherwise
/error-budgetGenerate the current on-call handoff brief - what's paging, what's escalated without an owner, last-shift history, and known-flaky alerts to watch
/oncall-briefDraft a blameless postmortem for a given incident (by ID or name), or the most recent significant incident within a time window
/postmortemUsing Skills
/skill devops-pack:error-budget-tracking
Error-budget and burn-rate assessment from whatever observability tools (Sentry, Datadog, Grafana, BetterStack) are connected: SLI, SLO, error budget, and burn rate applied practically, how to compute burn rate from available SLI data and the thresholds that make it actionable, what separates a budget-threatening trend from noise, and the fallback to raw trend reporting against a trailing baseline when no formal SLO is defined.