Slash Commands
Slash commands close the development loop inside the agent session. Building, auditing, and verifying performance happen without leaving the conversation — and every audit is checked against the thresholds you have declared in config.
Available commands
| Command | What it does |
|---|---|
/pulse-dev | Starts (or restarts) the development server. The server watches for file changes and reloads automatically. |
/pulse-stop | Stops the running development server. |
/pulse-build | Runs a production build. Bundles all specs via esbuild into public/dist/ with content-hashed filenames. |
/pulse-start | Starts the production server against the built output. Used to verify production behaviour before deploying. |
/pulse-report | Runs a Lighthouse audit against a production build and opens the performance report dashboard. Captures Performance score, web vitals, bundle sizes, and request counts. |
Using commands
Commands are typed directly into the agent chat:
/pulse-dev
/pulse-report
The agent executes the relevant CLI steps and reports back with results, including whether any Lighthouse score or Core Web Vitals metric failed a configured threshold.
/pulse-report performs a full production build before auditing. This guarantees accurate scores and correct brotli-compressed bundle sizes — development builds are unminified and serve no production metrics.Plain language prompts
Slash commands cover the most common operations. For everything else, describe the goal — the agent handles the implementation within Pulse's spec structure:
"Create a blog index page that fetches posts from an API"
"Add email validation to the contact form"
"Build a checkout flow with a Stripe payment step"
"Add a guard to the dashboard so unauthenticated users are redirected to /login"
The agent produces spec files that conform to Pulse's structure — the framework enforces correctness, so there is no manual wiring to verify.
Performance report dashboard
The report dashboard is available at /_pulse/report when the dev server is running. It shows a history of Lighthouse audits across all pages — Performance score, Core Web Vitals, bundle sizes, and request counts. Threshold failures are highlighted. Each audit is saved to .pulse/reports/ as JSON.