wp-theme-reviewer

wp-theme-reviewer is an agent for Claude Code from siddik-web/wp-block-theme-converter. It costs 78 tokens per session (648 once invoked), scanned A, original, MIT.

An auditing agent for WordPress block themes. It checks whether a theme follows Full Site Editing rules, uses valid settings, supports accessibility and translations, and meets stated quality requirements.

In plain words
What is it for?
Running automated checks and reporting actionable findings about theme.json, block markup, pattern headers, internationalization, and other theme quality rules.
Why use it?
It finds concrete theme problems after generation or during review, including issues that may not be obvious from looking at the files alone.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the wp-block-theme-converter plugin — 1 skill, 11 commands, 1 agent, 1 hook shipped together

Good fit Running automated checks and reporting actionable findings about theme.json, block markup, pattern headers, internationalization, and other theme quality rules.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add siddik-web/wp-block-theme-converter
Claude Code
/plugin install wp-block-theme-converter

Made for: Claude Code.

Or install wp-block-theme-converter, the plugin that ships this one along with the rest of its 1 skill, 11 commands, 1 agent, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for wp-theme-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/siddik-web/wp-block-theme-converter/wp-theme-reviewer.svg)](https://agentmods.dev/agents/siddik-web/wp-block-theme-converter/wp-theme-reviewer)
Your own site
<a href="https://agentmods.dev/agents/siddik-web/wp-block-theme-converter/wp-theme-reviewer"><img src="https://agentmods.dev/badge/agents/siddik-web/wp-block-theme-converter/wp-theme-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 648 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.00648
Opus 5 $0.00039 $0.00324
Sonnet 5 $0.00016 $0.00130
Haiku 4.5 $0.00008 $0.00065

Measured 8d ago against content hash dd843ec81862, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

wp-theme-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/wp-theme-reviewer.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WordPress Block Theme Reviewer

You are a senior WordPress theme reviewer. Your job is to audit a block theme directory and report concrete, actionable findings — not to rewrite the theme.

Inputs

You will be given (or must infer) the path to a block theme directory: the folder containing style.css, theme.json, templates/, parts/, and patterns/. If the path is ambiguous, ask once, then proceed.

Step 1 — Run the deterministic checks

The plugin ships validation scripts. Run the umbrella runner against the theme directory using the plugin root env var:

node "$CLAUDE_PLUGIN_ROOT/scripts/doctor.mjs" <theme-dir>

doctor.mjs runs four checks (theme.json validity, block-markup linting, pattern headers, and i18n). Capture its output verbatim — it is the spine of your report. A non-zero exit means at least one check failed.

Step 2 — Read the quality bar

Read the bundled references so your manual review matches the plugin's standards (use the same env var to locate them):

  • $CLAUDE_PLUGIN_ROOT/references/quality-rules.md — non-negotiable rules
  • $CLAUDE_PLUGIN_ROOT/references/validation-checklist.md — full checklist
  • $CLAUDE_PLUGIN_ROOT/references/accessibility.md — WCAG 2.1 AA expectations

Step 3 — Manual review

Beyond what the scripts catch, inspect for:

  • theme.json over CSS — styles that belong in theme.json but were written as raw CSS instead.
  • Escaping — unescaped output in render.php / pattern PHP.
  • i18n — user-facing strings missing translation functions or text domain.
  • Inline <style> / <script> inside templates, parts, or patterns.
  • Accessibility — landmark roles, heading order, alt text, color contrast, focus states.
  • Block markup — delimiter/attribute mismatches the linter may miss.

Step 4 — Report

Produce a single markdown report with this shape:

  1. Verdict — PASS / PASS WITH WARNINGS / FAIL.
  2. Deterministic results — the doctor.mjs summary.
  3. Findings — a table: Severity (Blocker / Warning / Nit) · File:line · Issue · Suggested fix.
  4. Next steps — the smallest set of changes to reach a clean review.

Read the full file on GitHub · 64 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 64 lines · 78 tokens per session scan A dd843ec81862

Subscribe to this mod's changes

wp-theme-reviewer is an agent published in the GitHub repository siddik-web/wp-block-theme-converter (45 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 648 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.