Explore a running app on randomized unscripted paths to surface new bugs, broken flows, and confusing UX, then file deduplicated tickets. Use for "free roam", "explore the app", "monkey test", "exploratory testing", "find issues I don't know about", or "discovery loop". Respects a never-touch list and blast-radius boundary. Not for scripted regression tests.
Install the complete plugin to include its agents, hooks, commands, and runtime context.
Fastest path: hand this line to the coding agent doing the setup. It reads this page and installs the Review plugin, which ships this skill with everything it relies on.
Click anywhere on the prompt to copy.
Choose a runtime, then follow its setup steps. This installs the complete Review plugin.
COMPLETE PLUGIN
Example session using the verified commands above.
The portable SKILL.md on its own, without the plugin’s hooks, agents, commands, and companion skills. Use it only when you intentionally want the narrower path.
No required companion skills are declared.
Agent architecture specialist. Use this agent when the user asks to "design an agent", "wire up tool-calling", "add memory to my agent", "set up agent routing", "implement delegated signup", "support auth.md", or "integrate ID-JAG". Covers evals, resilient chat UIs, and delegated agent auth. Not for deploying a built agent to hosting or wiring its cron and sandbox (use devops), authoring individual skills or commands (use prompt-engineer), or auditing skill accuracy (use trainer).
Test authorship and CI automation specialist. Use this agent when the user asks to "write tests", "add test coverage", "set up e2e/Playwright tests", "fix failing tests", or "add a CI coverage gate", or when a change needs tests before merging. Covers unit, integration, e2e, mocking, and coverage reporting. Not for performance profiling (use optimizer) or security review (use code-auditor).
Pass the canonical page to a teammate or keep it close for later.