Write an end-to-end integration test that exercises a runtime path against the REAL Claude Code CLI driven by a mock Anthropic API. Use to prove a behavioural acceptance criterion actually works (session spawn, agent tools, permission flow, scheduled jobs, model selection, system-prompt injection) rather than that the code merely exists. This is how you catch "code is present and renders but the feature is dead" bugs that unit tests and static review miss.
$npx -y skills add alexjbarnes/cockpit --skill integration-testInstalls into the current project.
Run `npx skills use "https://github.com/alexjbarnes/cockpit" --skill "alexjbarnes/cockpit/integration-test"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/alexjbarnes/cockpit" that are relevant to the current task. Run `npx skills add "https://github.com/alexjbarnes/cockpit"` and select the relevant skills, then follow their instructions.