swarmx

Turn a specification into a concrete architecture with stable contracts, file boundaries, ownership, and risk analysis. Use this when acting as the architecture writer for a task.

Run the project verification stack after code changes. Trigger on code changes and stop on the first failure, fix it, then rerun the full stack from the top.

Verify that newly created files follow the repo's existing directory layout, naming conventions, and export patterns. Trigger when a new file is created.

Break architecture into execution-ready sub-tasks with clear ownership, dependencies, and contract references. Use this when acting as the planner for a task.

Use Playwright for browser automation, UI validation, E2E tests, and interaction debugging. Useful for flows that need real page navigation, assertions, screenshots, or request interception.

Final merge-readiness check after gates pass. Confirms verification is green, changed files are clean, and obvious release blockers are gone before merge.

Review schema and migration changes for safety, reversibility, rollout risk, and data integrity. Trigger when schema files or migrations change.

Write a requirements spec that is testable, scoped, and implementation-aware without turning into architecture. Use this when acting as the spec writer for a task.

Review API or route changes for backward compatibility, contract drift, and documentation impact. Trigger when endpoints, handlers, or request/response contracts change.

Use Chrome DevTools Protocol through Playwright to capture richer browser diagnostics such as console errors, failed requests, coverage, and performance metrics when normal logs are insufficient.

Audit changed dependencies for security, compatibility, lockfile hygiene, and necessity. Trigger when package manifests or lockfiles change.

Look up current third-party API docs and reference material instead of guessing from memory. Use this when external frameworks, SDKs, or platform APIs are part of the task.

Analyze failing tests before changing code. Distinguish implementation bugs, test bugs, flaky behavior, and environment problems, then explain the likely root cause.

Review task lifecycle, conductor orchestration, and restart recovery invariants before changing task states, arbiter controls, merge flow, or crash recovery. Use this for risky conductor edits.

Keep dashboard views aligned on shared query keys, polling policy, invalidation, mutation feedback, and loading/error/empty states. Use this when editing dashboard views, hooks, or task controls.

Audit code-adjacent documentation for drift after behavior changes. Use this when runtime changes may have made READMEs, dashboard notes, API docs, or active architecture docs stale.

Decide the compatibility boundary and implementation approach before changing runtime behavior, shared types, task state transitions, or HTTP/gRPC contracts. Use this before risky refactors or contract changes.

Address security findings with targeted fixes. Triggers when @security reports a blocker finding.