breeze

Use when cutting, shipping, or announcing a Breeze RMM release — "cut a release", "ship vX.Y.Z", "release notes for X", "what do self-hosters need to know", "draft the release announcement", "do the release write-up". Orchestrates the whole release-comms pass: a self-hoster-focused GitHub Release body (breaking changes, required env vars, migrations), then /update-breeze-release-notes (marketing site), /update-breeze-docs (technical docs), and a Discord announcement. Also covers the post-release deploy + agent-fleet promote steps that the tag alone does NOT do.

Quick reference for the Breeze RMM Go agent architecture, commands, configuration, build process, and data flows. Use when working on agent code, debugging agent issues, or understanding how the agent communicates with the API.

Use when implementing a fix for a known GitHub issue end-to-end on the Breeze repo — "work on issue

Use when reviewing, triaging, or managing the incoming GitHub backlog on the Breeze repo — PRs, Discussions, AND Issues. Stateful manager with a shared queue file, contributor profiles, parallel pr-review-toolkit dispatch, GraphQL discussion recipes, comment-style conventions, and session-log bookkeeping. Auto-detects object type from the request; bare invocation triages all three. Triggers on "review PR", "PR queue", "triage PRs/discussions/issues", "review discussions", "check open issues", "what's waiting on me", "gh queue", "repo queue", "review

Comprehensive security review for Breeze RMM. Multi-tenant isolation audit, authentication/authorization hardening, public exploitability assessment, input validation, rate limiting, WebSocket security, secrets management, and OWASP top-10 coverage. Use when reviewing code for security issues, hardening endpoints, auditing tenant isolation, checking for vulnerabilities, or before deploying security-sensitive changes.

Use when debugging agent issues, investigating agent errors, checking agent connectivity, or reviewing agent diagnostic logs. Use when asked to check what an agent is doing or why it is failing.

Quick reference for the Breeze RMM AI Agent system architecture, MCP tools, streaming chat, cost tracking, guardrails, and MCP server. Use when working on AI features, debugging chat issues, adding new tools, or understanding the AI data flow.

Quick reference for the Breeze Helper Tauri desktop app — architecture, Rust backend commands, React frontend, config files, IPC with the Go agent, helper chat API routes, tool approval flow, and tray integration. Use when working on helper code, debugging helper issues, adding helper features, or understanding how the Helper communicates with the API and agent.

Writing guidelines for Breeze RMM tests — API route (Vitest + Drizzle mocks), Go agent, shared validators, and the required coverage checklist for every new feature. Use when writing or modifying tests in this repo.

Use when running a broad manual/AI-driven end-to-end verification of Breeze RMM across many merged PRs or commits — "test everything since the last release", release-readiness sweeps, or resuming a partial sweep. Tracks coverage across runs so each sweep only tests the delta. NOT for single-feature post-implementation checks (use feature-testing for that).

Post-implementation end-to-end feature verification. Use after implementing a feature to verify it works across UI, API, and agent layers using Playwright MCP tools, make dev-push, diagnostic logs API, and structured test logging.

Broad regression QA of the Breeze RMM web UI via Playwright — exercising everyday MSP workflows and setup tasks like a human QA tester, logging functional PASS/FAIL plus UI/UX observations, and filing GitHub issues from findings. Use this whenever the user asks to "QA the UI", do "extensive UI testing", a "regression sweep", "test everyday flows", "act as QA", verify recently/previously merged PRs end-to-end through the browser, or walk backward through PR history checking the UI. This is the whole-app sweep — for verifying ONE just-built feature use `feature-testing` instead.

Use when an agent needs a running, seeded, Playwright-ready Breeze stack for the current git worktree. Brings up pg+redis+api+web+portal+caddy running the worktree's own code and emits a JSON descriptor.