By nuttaruj
WordPress operations toolkit for Claude Code / Cursor / Codex / Gemini — wp-cli + REST + scoped fs + 89+ MCP tools, opt-in the rolepod-wp WordPress plugin unlocks execute-php + runtime introspection + one-click pair setup. Extension Protocol v1 — runs as a child of the rolepod parent (v2.7+) when its `<git-root>/.rolepod/parent-active` marker is present, standalone otherwise.
Query the AI Change Ledger on a connected target — every write the MCP issued, categorized; toggle on/off; panic-revert recent changes. Phase = Recovery.
Open a WordPress Target on any kind (local / REST + App Password / SSH / Docker) using credentials already in the vault. Phase = Define.
Create, read, update, search posts/pages/users/options/taxonomies via the core WP REST API on a connected target. Phase = Build.
Multi-probe diagnostic + security audit of a connected target — plugin conflicts, slow queries, large autoload options, broken images, PHP errors, outdated core/plugins/themes, weak admins. Phase = Debug.
Read or modify page-builder layouts on a connected target — Elementor, Divi, Oxygen, Bricks widget trees. Phase = Build.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
🌐 New here? See what AI can actually do on your WordPress site — plain-English breakdown of the 3 setup tiers.
rolepod-wplab gives Claude Code, Cursor, Codex CLI, and Gemini CLI a full WordPress operations toolkit — so the AI can actually wp-cli, edit page builders, audit security, migrate dev→staging, and (opt-in) run guarded execute-php against any WordPress site instead of guessing.
One MCP server, 89+ tools, 14 skills, 4 connection kinds (local path / REST + App Password / SSH / Docker). Default-safe — runs wp-cli + REST + scoped fs out of the box. Install the rolepod-wp WordPress plugin to unlock execute-php + runtime introspection + the one-click pair setup wizard.
Standalone: complete WordPress operations toolkit. 14 skills + 89+ MCP tools cover the full lifecycle — connect, introspect, edit, verify, migrate. Use directly via skill commands. No external dependencies.
Combined with rolepod parent (v2.7+): wplab phase-flavored skills narrow
to WP-specific tool roles, deferring workflow orchestration to parent. Same
14 skills, smarter division of labor. Detection is a single filesystem
marker (<git-root>/.rolepod/parent-active containing v1) written by the
parent's SessionStart hook — no install-time coupling, no env-var
propagation problems across Claude Code's subprocess boundaries.
| wplab skill | standalone role | with-rolepod role |
|---|---|---|
wp-diagnose | primary debug entry | evidence for parent's debug-issue |
wp-health-check | full smoke test | snapshot for parent's check-work |
wp-changes | change audit | summary for parent's review-code |
wp-full | tour + flow | tool loader (parent owns flow) |
wp-scaffold, wp-edit-* | edit + guide + verify | edit primitives for parent's implement-plan |
wp-migrate, wp-connect, wp-pair-setup, wp-introspect, wp-execute-php, wp-content | unchanged tools | unchanged tools |
| Install | Unlocks |
|---|---|
| wplab alone | full WordPress dev toolkit |
| wplab + rolepod parent | + workflow discipline, evidence handoff, multi-phase gates |
| wplab + uiproof | + browser-verified WP changes, a11y on themes, visual diff on migrations |
| all three | full WP dev flow with verified evidence at every phase |
Evidence path convention:
.rolepod-wplab/artifacts/<ts>/.rolepod/evidence/<ts>-rolepod-wplab-<skill>/Manifest schema (Extension Protocol v1): src/lib/rolepodEvidence.ts.
connect_local, connect_rest, connect_ssh, connect_docker — same tool surface, four ways to reach a site. App Passwords stored in the OS keychain, never echoed.rolepod_wp_pair { siteurl, pair_token } and is connected with full power tools. Token single-use, 60-min TTL.divi_{read,write}, oxygen_{read,write}, bricks_{read,write}, elementor_{read,write} — all backed up before overwrite.yoast_write, rankmath_write, wpml_write (link translations, duplicate for translation), woo_write (bulk price updates), acf_write.scaffold_block, scaffold_plugin, scaffold_theme, scaffold_pattern — register-block-type-ready files into existing themes/plugins.audit_security, audit_many (consolidated report for N sites), migrate_dryrun + migrate_data (plugin version sync dev→staging), clone (full db + wp-content + URL rewrite).diagnose (plugin conflicts / slow queries / large autoloads / php errors), backup_create + backup_restore, cache_tool, cron_tool, mail_test.execute-php (companion only). AST screen on Node side AND PHP side, production-block unconditional, append-only audit log.Coordinated software-house team for AI coding CLIs — 18 specialist agents, Core 10 phase skills (1 router + 9 phase), 6-phase lifecycle. Pre-commit gates (S1-S5 simplicity / T1-T6 testing / F1-F5 failure-mode) catch bugs before ship. On Claude Code, ships as a pure marketplace plugin (agents / skills / commands / hooks) — the always-on judgment core is delivered by a SessionStart hook, so install and uninstall touch no global config. See https://github.com/nuttaruj/rolepod.
Multi-platform UI/mobile automation for AI agents — 8 shipped skills (verify-ui, check-errors, audit-a11y, visual-diff, scaffold-e2e, measure-cwv, audit-page-budget, audit-seo) + MCP server with 30 tools. Works standalone OR with the `rolepod` parent plugin: when the marker file `<git-root>/.rolepod/parent-active` is present (written by the parent's SessionStart hook), evidence routes to `<git-root>/.rolepod/evidence/` with a `manifest.json` per Extension Protocol v1, so parent's `check-work` skill can aggregate UI verify results into its phase report. v0.5 completed the UI verification surface (console + network observability, hover/drag/fill_form/upload/dialog, runtime emulation, multi-page, gated JS eval).
Data-layer safety + truth verifier for AI agents — MCP server with 5 rolepod_db_* tools + 5 shipped skills (db-introspect, db-query, db-explain, db-migrate-verify, db-write). Works standalone OR with the `rolepod` parent plugin: when the marker file `<git-root>/.rolepod/parent-active` is present (written by the parent's SessionStart hook), evidence routes to `<git-root>/.rolepod/evidence/` with a `manifest.json` per Extension Protocol v1, so the parent's check-work skill can aggregate DB state as a first-class evidence type. Not a generic SQL client — the value is safe mutation (preview→confirm→commit/rollback), schema-drift detection, and DB state as PASS/FAIL evidence.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Plugin that includes the Figma MCP server and Skills for common workflows
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.
npx claudepluginhub nuttaruj/rolepod-wplab --plugin rolepod-wplab