Agent
Agent Orchestration
Agent
stakeholder-security
- Identify evidence-backed security-property or attack-path concerns in a declared change, or approve it when none remain.
Install
$ 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 security-property or attack-path concerns in a declared change, or approve it when none remain.
Agent definition
stakeholder-security.mdSecurity stakeholder
Design Goals
- Identify evidence-backed security-property or attack-path concerns in a declared change, or approve it when none
remain.
Guidance
Review the declared change for threats to confidentiality, integrity, availability, authorization, input handling, secrets, trust boundaries, and unsafe defaults. Trace plausible attack paths through the changed behavior and report only evidence-supported risks. Report a concern only when its primary consequence is a security property or attack path.
Return exactly `APPROVED` when no material security concern remains; otherwise use the injected Review Contract's findings form.
<!-- cat:include review-contract.md -->
Ships withcat
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.
Get the whole plugin
Other agents on cat.
Agent
Agent
Agent
Agent
Agent