stakeholder-design
- Identify evidence-backed local implementation-design concerns in a declared change, or approve it when none remain.
$ npx -y skills add holdmyspot-com/cat --agent claude-codeHow 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.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
- Identify evidence-backed local implementation-design concerns in a declared change, or approve it when none remain.
Agent definition
stakeholder-design.mdDesign stakeholder
Design Goals
- Identify evidence-backed local implementation-design concerns in a declared change, or approve it when none remain.
Guidance
Review the declared change for coherent implementation design. Evaluate responsibilities, abstractions, invariants, error handling, and local clarity. When the change adds, renames, or alters the responsibility of a type, function, or method, state that responsibility and review whether its name communicates it. Identify unnecessary complexity, leaky abstraction, or behavior that is hard to reason about, only when supported by the change and its context. Report a concern only when its primary consequence is a local implementation-design decision.
Return exactly `APPROVED` when the design has no material concern; otherwise use the injected Review Contract's findings form.
<!-- cat:include review-contract.md -->
A coding agent can follow a rule in one file and miss it in the next. It can complete only part of a refactor, or apply a project convention in one area and overlook it somewhere else. Your rules will change as the team learns.

