Turn Jira tickets into reviewed Playwright tests with a team of agents

QA engineer Ben Weese runs seven Claude Code agents that map pages once, plan from a Jira ticket, write manual cases and Playwright specs, and heal locators, with his sign-off at each step.

Done withClaude CodeinJira· Nov 15, 2026

What they did

Weese, writing on dev.to six months after his first post on the setup, gives each agent one role. A page mapper visits a page once and saves its controls, URL params, validation messages and empty states to a file in the repo. A UI planner reads that map and the ticket and never opens the browser. Other agents write manual test steps into Xray, generate page objects and specs, plan and write API tests, and repair broken locators. A generate-tests skill takes a Jira ticket or an epic key, pulls the tickets through the API, removes duplicates and writes a brief, then pauses for his approval before the plan, the manual cases and the automation. He split his large CLAUDE.md into short per-folder guides and later packaged the agents, skills and slash commands as a Claude Code plugin so each test repo can install it. Commands also file bugs and QA tasks in Jira once he confirms.

How it went

Before the page mapper, planning one feature used 156k tokens, about 78% of his context window, because the planner rescanned the page every time. Splitting CLAUDE.md cut the root file from 12,306 to 5,177 characters, roughly 1,790 tokens saved per session. In a public rebuild against a demo site, plan review caught two tests that would have passed on broken behaviour. A full run showed 19 failures; capping workers at 2 and stopping duplicate smoke runs left only the 7 that were real mismatches with the site's own docs. He says the bottleneck moved from writing tests to reading plans.

Worth knowing

Prompt rules alone did not hold, so he moved every rule he could into lint (no XPath, no fixed waits, no hidden skips). One rule stays manual: when the plan and the ticket disagree, the test must assert the ticket. The healer gets three attempts per test and then marks it test.fixme() with a note, or it keeps chasing locators that are not the real problem, such as a site returning 503 under load.

Try it

With Claude Code· 3 parts to fill in

Act as the planner for UI tests in [my Playwright repo]. Read the ticket [Jira ticket key] and write a brief of its requirements and acceptance criteria, plus the page objects and API clients the repo already has. Use the saved page map in [path to page maps]; if a page has no map, mark its tests as test.fixme() rather than guessing. Check whether each test already exists before planning it. When the ticket and your plan disagree, assert what the ticket requires. Stop after the brief and again after the plan, and wait for my approval before writing any test code.

Square brackets are the parts to fill in. The prompt is ours; the story is theirs.

Where they said it

Related