chore: enhancements to claude code

[carlosthe19916]

Summary by Sourcery

Introduce a structured Claude E2E testing workflow with Playwright-specific agents, hooks, and skills, and integrate automatic execution of relevant tests on file changes.

Enhancements:

• Revise the e2e-test command to orchestrate planning, generation, and verification phases for Playwright UI tests.
• Add specialized agents for Playwright test planning, generation, execution, and healing to standardize E2E test authoring and maintenance.
• Define a GitHub assistant skill and a Playwright quality-check skill to streamline repository operations and Playwright code conventions.
• Introduce reusable scripts to start and stop a remote Playwright container and to run linting and formatting checks via npm.

Tests:

• Add a PostToolUse hook that detects newly written or edited Playwright and API test files and automatically runs only the affected tests with targeted execution.

[sourcery-ai]

Reviewer's Guide

Adds a Claude E2E testing workflow centered around Playwright, including new planner/generator/healer/executor agents, containerized Playwright remote server management hooks, an auto-execution PostToolUse hook, lint/format automation, and a refined e2e-test command plus GitHub/Playwright skills metadata.

Sequence diagram for the new Playwright E2E testing workflow

sequenceDiagram
    actor Developer
    participant Claude
    participant e2e_test_command
    participant playwright_test_planner
    participant playwright_test_generator
    participant playwright_test_executor
    participant playwright_test_healer
    participant lint_and_format_hook
    participant playwright_remote_start
    participant playwright_remote_stop
    participant PlaywrightServer

    Developer->>Claude: Request E2E Playwright tests
    Claude->>e2e_test_command: Invoke e2e-test command

    e2e_test_command->>playwright_test_planner: Plan test strategy
    playwright_test_planner-->>e2e_test_command: Test plan

    e2e_test_command->>playwright_test_generator: Generate Playwright tests
    playwright_test_generator-->>e2e_test_command: Test code

    e2e_test_command->>lint_and_format_hook: Run lint-and-format.sh
    lint_and_format_hook->>lint_and_format_hook: npm run format:fix
    lint_and_format_hook->>lint_and_format_hook: npm run check:write
    lint_and_format_hook->>lint_and_format_hook: npm run check
    lint_and_format_hook-->>e2e_test_command: Lint/format results

    e2e_test_command->>playwright_remote_start: Run playwright-remote-start.sh
    playwright_remote_start->>PlaywrightServer: Start containerized server
    PlaywrightServer-->>playwright_remote_start: Ready on port 5000
    playwright_remote_start-->>e2e_test_command: Runtime info

    e2e_test_command->>playwright_test_executor: Execute tests (PostToolUse hook)
    playwright_test_executor->>PlaywrightServer: Run Playwright tests
    PlaywrightServer-->>playwright_test_executor: Test results

    alt Tests failed
        playwright_test_executor->>playwright_test_healer: Request healing
        playwright_test_healer-->>playwright_test_executor: Updated tests/fixes
    end

    e2e_test_command->>playwright_remote_stop: Run playwright-remote-stop.sh
    playwright_remote_stop->>PlaywrightServer: Stop container
    PlaywrightServer-->>playwright_remote_stop: Stopped
    playwright_remote_stop-->>e2e_test_command: Stop confirmation

    e2e_test_command-->>Claude: Final E2E report
    Claude-->>Developer: Summarized results and next steps

Loading

File-Level Changes

Change	Details	Files
Redefine the e2e-test Claude command to use a multi-phase workflow with dedicated Playwright planner, generator, healer, and executor agents.	Rename and expand metadata for the e2e-test command, clarifying it generates Playwright E2E tests from a message argument. Replace previous manual guidance with a three-phase process: gather context from app and existing tests, plan via playwright-test-planner, generate via playwright-test-generator, then verify via healer and executor agents. Constrain execution to only new or edited tests and require final output to include coverage summary, per-file status, and recommendations.	.claude/commands/e2e-test.md
Introduce a PostToolUse hook that automatically runs only the touched Playwright or API E2E tests using a remote Playwright server container.	Add a Bash hook that parses JSON tool responses with jq to detect written/edited test files and their session IDs. Match file paths against Playwright UI and API test patterns, track tested files per session to avoid re-running, and build targeted npm commands (including optional grep by new test names extracted from structured patches). Start and stop a remote Playwright server container via helper scripts, run tests with timeout and proper env vars, and emit structured success JSON or blocking failure output with logs. Use a per-session tracking file under /tmp to remember which files have been tested and avoid duplicates. Handle both Write and Edit tool_name cases with different command construction strategies.	.claude/hooks/execute-playwright-test.sh
Add Claude agents for planning, generating, healing, and executing Playwright tests, wired to custom MCP tools and container orchestration.	Define playwright-test-planner agent that explores the UI via browser tools, designs comprehensive test plans, and persists them as markdown using planner_setup_page and planner_save_plan. Define playwright-test-generator agent that consumes a plan, uses generator_setup_page and browser tools to execute each step, reads the generator log, and writes single-test spec files under describes matching top-level plan items. Define playwright-test-healer agent that runs tests, debugs failures with test_run/test_debug and browser inspection tools, edits tests via Edit/MultiEdit/Write, and can mark flaky cases with test.fixme(). Define playwright-test-executor agent that validates file paths, detects test type, manages a claude-playwright-{session_id} container, builds a grep-filtered npm command, runs with timeout, parses results, and reports structured success/failure guidance and cleanup behavior.	.claude/agents/playwright-test-executor.md .claude/agents/playwright-test-generator.md .claude/agents/playwright-test-planner.md .claude/agents/playwright-test-healer.md
Provide container lifecycle hooks to start and stop a shared Playwright remote server in podman or docker.	Add a start script that detects podman/docker, runs the official Playwright image with network host, pwuser user, and run-server on port 5000, and supports a configurable container name. Add a stop script that detects podman/docker, stops a given container by name, and exposes simple CLI usage with help flags.	.claude/hooks/playwright-remote-start.sh .claude/hooks/playwright-remote-stop.sh
Add Claude skills metadata for GitHub and Playwright code quality plus an npm-based lint/format hook.	Introduce a GitHub skill that wraps gh CLI usage with concise communication rules, conventional commit conventions, branch naming guidelines, and PR comment TODO checkbox format. Introduce a Playwright skill that defines local Playwright testing patterns and anti-patterns (fixtures, custom expect, type-safe abstractions, and where assertions should live). Add a lint-and-format hook script that runs npm format:fix, check:write, and check sequentially under strict bash options. Create base Claude settings JSON file (currently empty or default-config placeholder).	.claude/skills/github/SKILL.md .claude/skills/playwright/SKILL.md .claude/hooks/lint-and-format.sh .claude/settings.json

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 63.91%. Comparing base (9e82125) to head (076e89a).

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #904      +/-   ##
==========================================
- Coverage   64.40%   63.91%   -0.49%     
==========================================
  Files         187      187              
  Lines        3295     3295              
  Branches      746      746              
==========================================
- Hits         2122     2106      -16     
- Misses        875      891      +16     
  Partials      298      298              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.