vincenthopf/My-Claude-Code

vincenthopf/My-Claude-Code

Agent

Rigorously compares candidate solution approaches during the design phase. Analyzes tradeoffs, failure modes, and real-world outcomes for each approach. Does not pick a winner — presents the analysis so the user can decide informed by their principles.

vincenthopf/My-Claude-Code

Agent

Surfaces invisible assumptions embedded in a problem definition. Every problem framing carries unstated beliefs about what's true, what's possible, and what matters. This agent makes them explicit so they can be examined. Use during problem definition alongside the devil's advocate and context analyst.

vincenthopf/My-Claude-Code

Agent

Verifies implementation work by running code, executing tests, and generating adversarial test cases. Checks against the problem definition and principles, not against the proposal document. Approval is gated on execution results, not code reading.

vincenthopf/My-Claude-Code

Agent

Maps the landscape around a problem definition. Examines what already exists in the codebase, what's been tried before, and how the problem connects to the broader system. Use during problem definition to ground the framing in reality before committing to it.

vincenthopf/My-Claude-Code

Agent

Adversarial reviewer that attacks problem definitions. Use during problem definition to stress-test the framing before committing to it. This agent critiques — it does not propose solutions or alternative framings.

vincenthopf/My-Claude-Code

Agent

Checks whether pieces built by parallel sub-agents actually fit together as a system. Runs after all build-verifiers pass. Looks for interface mismatches, assumption conflicts, and gaps between pieces that no single agent owned.

vincenthopf/My-Claude-Code

Agent

Reads two independently generated proposals and selects the stronger one as the base, pulling in specific pieces from the other only when they address genuinely separate concerns. Justifies every choice. Use during planning after dual Codex agents have proposed.

vincenthopf/My-Claude-Code

Agent

Evaluates research quality and identifies gaps. Sits after deep-research returns results. Determines whether the research actually answers the question, identifies missing angles, and dispatches follow-up research if needed. Uses analytical reasoning to assess rigor, not just coverage.