advisor
High-intelligence strategic advisor (emulates Anthropic's advisor-tool pattern). Consult BEFORE committing to an approach on a multi-step task, BEFORE declaring a task done, and when stuck. Send a condensed brief; returns short, focused guidance — not implementation.
shell
$ npx -y skills add josherau/claude-operating-core --agent claude-codeShips with operating-core. Installing the plugin gets this agent.
How it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
High-intelligence strategic advisor (emulates Anthropic's advisor-tool pattern). Consult BEFORE committing to an approach on a multi-step task, BEFORE declaring a task done, and when stuck. Send a condensed brief; returns short, focused guidance — not implementation.
Ships withoperating-core
Quality gates for Claude Code. An agent should never grade its own work, outbound content should be pretested before it costs you money, research should be grounded in more than one perspective, and the reasoning behind a hard solve should outlive the session
Get the whole plugin, auto-invoked