<!-- Generated by mstack from Misbah's Build Like This workflow. Regenerate instead of editing. -->

verify-journey

Run the browser-verification skill. Turn the requested journey into a reproducible browser run with deterministic setup, full state coverage, and captured traces.

This prompt follows Misbah Khursheed's Build Like This workflow: establish the user outcome and reasoning before generating implementation, then preserve that reasoning in contracts, boundaries, tests, and documentation.

Project identity and sources of truth

The repository where this prompt is installed is the host project being built. Build Like This is the engineering method used to build it, while mstack only installs and reconciles the method's resources. Do not mistake mstack or Build Like This for the host product unless project-owned sources explicitly say this repository develops mstack itself.

Project-owned docs/, decisions, executable code, and tests are the sources of truth. .mstack/templates/ are reference scaffolds that may be copied and adapted into project-owned documents; they are not requirements and do not replace docs/.

Treat the invocation arguments and current repository state as task input. Discover local instructions and relevant product, architecture, decision, contract, and test context before making material assumptions.

Method

1. Restate the journey, acceptance criteria, seeded users and data, target browsers and viewports, and the base URL or preview deployment.
2. Confirm the backend contract or build a faithful typed mock before exercising browser behavior.
3. Set up deterministic state with isolated users, fixed viewports, and explicit wait conditions instead of sleeps.
4. Exercise the critical path, then validation, denial, empty, degraded-network, and failure/recovery states.
5. Verify keyboard reachability, focus order, visible focus, landmark and label semantics, contrast, and reduced-motion behavior.
6. Capture screenshots, console errors, failed requests, and traces; rerun suspected flakes in isolation before reporting.

Deliverables

• A pass/fail matrix per journey, browser, and state with linked screenshots, traces, and console/network evidence.
• Reproducible defect reports with steps, seeded state, expected versus actual behavior, and severity.
• The exact verification command, environment, residual coverage gaps, and flake assessment.

Constraints

• Do not verify against production data or mutate shared environments without explicit authorization and isolation.
• Do not use fixed sleeps or nth-match selectors that hide race conditions.
• Do not report a green run that skipped authentication, denial, or failure states as full verification.

Delegation and parallel safety

• For a material lifecycle task, the active lead must delegate at least one bounded specialist lane when subagents are available; prefer two or more concurrent lanes only when their evidence or file ownership is independent.
• The active lead owns acceptance criteria and final integration. Supporting agents must not recursively delegate unless explicitly promoted to lead a named lane.
• Give each delegate distinct inputs, outputs, and ownership. Serialize shared documents, contracts, schemas, migrations, deployments, external writes, and overlapping file edits.
• If subagents are unavailable, perform the named specialist passes sequentially and report the limitation; do not imply parallel verification.
• Delegation does not authorize outreach, paid resources, destructive changes, consequential external writes, or production deployment.

Finish with what changed or was decided, exact verification evidence, remaining risks, and the next decision only if one is genuinely required.

User arguments: $ARGUMENTS