Agent
WordPress performance specialist following Human Made and 10up standards. Use for auditing query performance, caching strategy, asset loading, Core Web Vitals, and database optimization in WordPress projects. Handles both greenfield and inherited legacy codebases.
Agent
WordPress code reviewer following Human Made and 10up standards. Use when reviewing PHP, hooks, queries, REST endpoints, or block code in a WordPress project — lighter context than the full wp agent. Read-only. Reports correctness, security, and standards-compliance issues by severity with file:line references. For…
Agent
WordPress security specialist following Human Made and 10up standards. Use for auditing input sanitisation, output escaping, nonce verification, SQL injection, authentication, authorisation, REST API security, and WordPress-specific vulnerabilities. Prioritises exploitable issues in legacy codebases.
Agent
Principal WordPress developer following Human Made and 10up engineering standards. Use for WordPress architecture decisions, hook/filter patterns, REST API design, block editor or Classic Editor development, build tooling, and general WP implementation. For read-only WP code review, use wp-reviewer instead. Adapts to…
Skill Claude CodeCodex
Use when the user asks to audit, review, investigate, check, scan, "look at", or "find issues in" code — anything that sounds like a diagnostic request without an explicit fix authorization. Enforces findings-only output with severity tiering, forbids in-place fixes during audit, and blocks the…
Skill Claude CodeCodex
Discover all files for a block or component, trace the editorial and front-end user journeys, and write a journey document to docs/journeys/.
Skill Claude CodeCodex
Remove stale agent worktree directories and their orphaned branches. Run after parallel agent work or when .claude/worktrees/ accumulates cruft.
Skill Claude CodeCodex
Diagnose which rules loaded, which didn't, and why. Reads the InstructionsLoaded audit log and compares against expected rules.
Skill Claude CodeCodex
Starts a structured interview to diagnose WordPress issues, then proposes a ranked list of solutions.
Skill Claude CodeCodex
Structured debugging protocol. Use when investigating a bug, failing test, regression, unexpected behavior, or any scenario where code is not doing what it should. Trigger phrases include "broken", "not working", "bug", "error", "it worked before", "still broken", "why is this failing", "trace", or "/trace".
Skill Claude CodeCodex
Figma-to-code workflow using MCP tools. Fetches design context, screenshots, variables, and Code Connect mappings before implementation.
Skill Claude CodeCodex
Write or update a handoff document so the next agent with fresh context can continue this work.
Skill Claude CodeCodex
Use when reviewing whether module boundaries earn their keep — finding shallow modules that should be consolidated into deep ones. Triggers on phrases like "is this over-modularised?", "should these be one module?", "too many small files doing related work", "interface feels as complex as implementation", "review the…
Skill Claude CodeCodex
Playwright MCP browser automation workflow. Snapshot-first approach for page interaction, visual verification, form filling, and debugging.
Skill Claude CodeCodex
Auto-detects the project's tech stack, then audits for Accessibility, Performance, and Code Quality. Works across WordPress/PHP, Python, Node/JS, and static web projects.
Skill Claude CodeCodex
Review auto-memory for the current project. Shows accumulated learnings, identifies noise, and helps promote permanent patterns to CLAUDE.md, rules, or skills.
Skill Claude CodeCodex
Use when reviewing Swift 5.5+ code containing await, actor, Task { }, @MainActor, @unchecked Sendable, cancellable timer/deadline handles, or long-lived for await AsyncStream consumers — especially diffs extending existing actors with new methods. Catches post-await state-overwrite races, TOCTOU around Task spawn…
Skill Claude CodeCodex
Generate a user-facing test checklist from git diff, or execute an existing test plan via Playwright. Two modes: generate (default) creates the plan, execute runs it in the browser.
Skill Claude CodeCodex
Recovery protocol for tool failures and search budgets. Use when Edit fails repeatedly on the same target, when hooks may have modified file contents between operations, or when WebSearch/WebFetch is not converging on an answer.
Skill Claude CodeCodex
Open an app in Playwright and explore it as a real user with no prior knowledge. Report UX findings per page, test core flows, and suggest improvements.