Adversarial plan review agent — read-only. Systematically attacks implementation plans across 5 dimensions (Assumptions, Missing Cases, Security, Architecture, Complexity Creep), then applies refutation reasoning to eliminate false positives before reporting.
$curl -o .claude/agents/plan-challenger.md https://raw.githubusercontent.com/kumaran-is/claude-code-onboarding/HEAD/.claude/agents/plan-challenger.mdInstalls into the current project.
Install plan-challenger by running `curl -o .claude/agents/plan-challenger.md https://raw.githubusercontent.com/kumaran-is/claude-code-onboarding/HEAD/.claude/agents/plan-challenger.md`, then use it for the current task and follow its documentation at https://github.com/kumaran-is/claude-code-onboarding.