feat: Claude Code plugin for becwright (AI-agent integration, phase A)#17
Conversation
becwright is the deterministic net for what an AI agent lets slip; this makes the integration official. A Claude Code session can now install becwright and drive it. - integrations/claude-code/: the plugin. A 'becwright' skill teaches agents what it is, how to install it (npm/pnpm, no Python; or pipx), how to scaffold rules and read/fix check output; a '/becwright' command exposes init/check/add/status. - .claude-plugin/marketplace.json: makes the repo installable via '/plugin marketplace add DataDave-Dev/becwright'. - The plugin installs the published package, it does not bundle the engine. - Document install in both READMEs. Validated with 'claude plugin validate'. First layer of the planned agent integration; a universal MCP server + check --json is the next step.
|
Warning Review limit reached
Next review available in: 47 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (7)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
1 participant
Summary
Makes the AI-agent integration official: a Claude Code plugin so any agent session can install and drive becwright — the deterministic, commit-blocking net for what an AI agent lets slip. This is Phase A of the planned agent integration; a universal MCP server +
becwright check --jsonis the next step.The plugin installs the published package (npm / PyPI); it does not bundle the engine. Thanks to the npm work (#16), install needs no Python.
What's included
integrations/claude-code/— the plugin:becwright— teaches the agent what becwright is, how to install it (npm/pnpm or pipx), scaffold.bec/rules.yaml, and read/fixcheckoutput. Auto-invoked when the user asks for a guardrail / pre-commit check / a rule that "can't be ignored"./becwright—init/check/add <regex-or-catalog-url>/status..claude-plugin/marketplace.json(repo root) — makes the repo installable.Install (for users)
Test plan
claude plugin validate .— marketplace passes (clean)claude plugin validate integrations/claude-code— plugin passes (clean)pyteststill 110 passing (no engine changes)/plugin installin a fresh session (not done here to avoid mutating the active session's plugin config)Follow-up (Phase B, separate PR)
becwright check --json(stdlib only) + a universal MCP server shipped as a separate package/extra, so any agent (Cursor, Windsurf, …) gets structured results.