[justin-prime1]

Summary

• reconcile newer locally authored BHE development guidance into the current six-skill architecture
• add a scaled inspect-plan-execute-verify loop and target-ADR-governed API sliced-onion guidance
• strengthen Doodle typography, test ownership, Storybook documentation, PR screenshots, review-thread closure, durable Playwright coverage, and criterion-to-evidence handoffs
• add behavioral eval coverage and bump the bloodhound-development plugin to 0.2.1

Compatibility and risk

Affects the bloodhound-development plugin for Claude Code and Codex. The deprecated bhe-dev-bootstrap compatibility entrypoint remains a routing shim, while bhe-dev-environment remains authoritative for worktrees and runtime state. No runtime implementation scripts changed and no migration is required.

Validation completed with all six skill validators, 120 maintenance tests, 13 Go-review tests, and 14 BHE workflow tests passing. Independent enterprise review is bound to the proposed head.

[Copilot]

Pull request overview

Synchronizes BHE development guidance across delivery, review, browser validation, and plugin metadata.

Changes:

• Adds inspect-plan-execute-verify and sliced-onion API guidance.
• Strengthens Playwright coverage, screenshots, evidence, UI review, and thread closure.
• Expands behavioral evals and bumps the plugin to 0.2.1.

Reviewed changes

Copilot reviewed 14 out of 14 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
bhe-ui-playwright/SKILL.md	Expands browser-validation and coverage guidance.
bhe-ui-playwright/evals/evals.json	Adds Playwright behavioral evals.
bhe-ui-playwright/agents/openai.yaml	Updates agent metadata.
bhe-enterprise-review/SKILL.md	Adds UI and API architecture review rules.
bhe-enterprise-review/evals/evals.json	Extends review eval coverage.
bhe-change-delivery/SKILL.md	Adds operating-loop and UI delivery guidance.
references/pr-readiness.md	Requires screenshots and review-thread closure.
references/development-operating-loop.md	Defines the expanded development loop.
references/api-sliced-onion.md	Defines API architecture checks.
bhe-change-delivery/evals/evals.json	Adds delivery workflow evals.
README.md	Updates Playwright skill documentation.
.codex-plugin/plugin.json	Bumps Codex plugin version.
.claude-plugin/plugin.json	Bumps Claude plugin version.
.claude-plugin/marketplace.json	Updates marketplace version.

Suppressed comments (1)

plugins/bloodhound-development/skills/bhe-ui-playwright/SKILL.md:151

• This completion requirement again blocks a valid no-playwright disposition because no pre-change Playwright baseline exists in that path. Scope the baseline/scenario requirement to dispositions that use Playwright so the completion gate agrees with the newly documented decision model.

- the pre-change baseline and required post-change Playwright scenarios pass, unless an explicitly diagnostic or coverage-baselining ticket permits known failures;

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[chrismaddalena]

The changes look good overall. Copilot flagged one discrepancy worth double checking.

[zinic]

We should tend to the nit but the rest here looks good. Merge after we fixup the nit.