opsphere

Plugin opsphere from marketplace opsphere in opsphere-io/opsphere-plugin. Commands read from the repo's manifest — 2 days ago.

Skills (18)

• ci-investigation

  CI and pipeline failure investigator for GitHub Actions, Bitbucket, and GitLab. Use when workflows or pipelines fail.

• configure-deployment-catalog

  Help users configure how Opsphere knows their deployment sources — work context (Community) vs admin Cloud Catalog (Team). Use when deployment_status returns gaps, user asks about deployment sources, or latest-deploy queries fail for missing catalog config.

• configure-integration

  Connect an eligible provider (Datadog, Vercel, GitHub, Cloudflare, Jira, Confluence, Sentry, Bitbucket, GitLab, Railway, …) when ops_list_integrations marks it available_to_connect — step-by-step guided setup from the chat. AWS is excluded (Cloud Catalog admin only). Use when the user wants to add,

• connect-another-client

  Connect the same Opsphere account to another MCP app without sharing tokens or changing workspace.

• endpoint-health

  Single-host endpoint health — DNS, HTTP, and TLS. Use when the user asks if a URL is up, SSL expiry, or DNS resolution.

• evidence-backed-verdict

  After macro_* or investigation_close, read the Veredicto section from tool text; do not re-parse JSON sections or raise confidence without explicit rejects/supports.

• incident-investigation

  Site-down and incident triage. Use when the user reports outages, downtime, 5xx errors, degraded SLOs, or widespread failures.

• opsphere-onboarding

  Get started with Opsphere in Antigravity; discover tools, account and workspace without changing configuration.

• postmortem-writer

  Structured incident post-mortem writer. Use after an outage when the user wants RCA summary or to save lessons learned.

• qa-release-readiness

  Assess whether a release or current deployment for a named environment and optional site, product, service, or workspace is ready to promote using matching evidence.

• qa-test-investigation

  Design focused QA cases and investigate suspected product defects with Opsphere evidence. Use for feature validation, reproduction, regression checks, and deciding whether a reported behavior is a bug.

• set-work-context

  Read or update Opsphere provider and account context from Antigravity; not workspace selection or credential setup.

• link-account
• noibu-analytics
• open-work-context
• plan-and-usage
• reconnect
• run-macro-workflows

Slash commands (9)

• /opsphere:execution-budget

  Show the current Cursor investigation budget, remaining capacity, and reset time for the authenticated user and active workspace

• /opsphere:integration-status

  Show which integrations are configured, available to connect on your plan, require upgrade, or are unavailable — and suggest a safe next configure step

• /opsphere:link-account

  Link or unlink an external workspace on Connection Hub. Community gets upgrade CTA — Personal Workspace is already included.

• /opsphere:noibu-analytics

  Noibu store health, conversion KPIs, and issue search via Opsphere (OAuth-linked). Use for Store Pulse-style snapshots, domain lookup, and ecommerce analytics.

• /opsphere:open-work-context

  Switch to an external linked workspace (paid Hub). Not needed for Community Personal Workspace.

• /opsphere:opsphere-connect-another-client

  Connect your existing Opsphere account to another MCP client.

• /opsphere:opsphere-reconnect

  Recover OAuth when Opsphere disconnects, tools fail with 401, or Cursor/Codex reports invalid_grant or an OAuth refresh error.

• /opsphere:opsphere-setup

  First-run setup — authenticate via OAuth and connect your first provider in under 2 minutes. Run after install; for a lighter start use /opsphere-welcome first.

• /opsphere:opsphere-welcome

  Quick start — what Opsphere can do, example prompts, and links to setup. Run after installing the plugin (type /opsphere-welcome in chat).

Subagents (6)

• ci-investigator

  CI and pipeline failure investigator for GitHub Actions, Bitbucket, and GitLab. Use when the user reports failed workflows, red pipelines, or asks to diagnose CI — not for simple single-tool status checks.

• endpoint-health

  Single-host endpoint health checker — DNS, HTTP reachability, and TLS certificate validation. Use when the user asks if a URL or hostname is up, SSL expiry, DNS resolution, or edge health for one target (not full multi-service outages).

• outage-triage

  Site-down and incident triage specialist. Use proactively when the user reports outages, downtime, 5xx errors, "is X down", degraded SLOs, or widespread failures across services.

• postmortem-writer

  Structured incident post-mortem writer — gathers facts, drafts a post-mortem, and optionally saves distilled incident memory. Use after an outage or investigation when the user wants a post-mortem, RCA summary, or to save lessons learned for next time.

• qa-release-readiness

  QA release readiness assessor — evaluates a release or current deployment for a named environment and optional site, product, service, or workspace using tenant-scoped evidence.

• qa-test-investigator

  QA test and bug investigator — designs focused test cases, checks available operational evidence, distinguishes product defects from environment, data, permission, and network issues, and returns a ticket-ready report.

MCP servers (1)

• opsphere

  connects to: https://mcp-cursor.opsphere.io/mcp

Similar plugins