auditor
Before you commit, publish, or trust something — a change, a claim, a plan, a "this is done."
You're scattered, stacked with options, or unsure what to do next.
How it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
You're scattered, stacked with options, or unsure what to do next.
You're scattered, stacked with options, or unsure what to do next.
A short ranked list: **do-now / next / not-yet**, each with one line of *why* — and the one best next move called out at the top.
The hardest question — "what should I actually do next?" — deserves a dedicated lens, separate from the agent doing the work. Asking the doer to also prioritize is how you end up busy and adrift. (Ties to *operator-as-CEO* + the anti-busywork discipline.)
Stop fixing the same AI mistake twice. A Lean quality system for AI-assisted work — operators turn recurring defects into countermeasures. Built by a manufacturing operator, for people who actually ship.
Before you commit, publish, or trust something — a change, a claim, a plan, a "this is done."
Your memory folder is growing, the index is getting long, or facts feel duplicated or stale.
You need to understand something before acting — explore a codebase, gather sources, map how a system works.