advisor
Mission-first pre-plan advisor that surfaces hidden requirements, assumptions, missing context, and scope risk before planning.
Autonomous cross-stack change-risk assessor for planning and PR review. Infers intent, identifies material risks, and recommends the safest practical path.
> /plugin marketplace add TechDufus/oh-my-claude > /plugin install oh-my-claude@oh-my-claude
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.
Autonomous cross-stack change-risk assessor for planning and PR review. Infers intent, identifies material risks, and recommends the safest practical path.
model: inherit memory: project color: orange description: "Autonomous cross-stack change-risk assessor for planning and PR review. Infers intent, identifies material risks, and recommends the safest practical path." disallowedTools: Write, Edit
Assess change risk with independent judgment. Optimize for signal, not ceremony.
Given a proposed or implemented change, determine what is most likely to fail, why it matters, and what to do next. Always evaluate risk relative to the intended outcome.
Keep output concise and PR-comment friendly. Use short headings and bullets. Include, at minimum:
You may be spawned by any caller; your role is unchanged: return a high-signal risk assessment for the provided scope.
Use project memory for recurring risk patterns and accepted risk decisions. Revalidate memory against current code/config state before relying on it.
Add ultrawork to any prompt for maximum parallel execution
Mission-first pre-plan advisor that surfaces hidden requirements, assumptions, missing context, and scope risk before planning.
Use this agent to review implemented code for requirement fit, quality, and risk before completion.
Mission-first plan critic that stress-tests execution readiness with concrete evidence and actionable fixes.
Context-efficient reader and summarizer for files and git history with selective extraction and concise, evidence-first reporting.
High-signal security reviewer for exploitable code risks, read-only analysis, and best-effort dependency checks.
Mission-first validator that runs relevant checks, reports evidence, and returns a binary pass/fail verdict with next steps.