Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/stuartshields/claude-setupWrote 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.
[](https://agentmods.dev/agents/stuartshields/claude-setup/wp-reviewer)<a href="https://agentmods.dev/agents/stuartshields/claude-setup/wp-reviewer"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/wp-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/stuartshields/claude-setup/wp-reviewer"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/wp-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.01204 |
| Opus 5.5 | $0.00030 | $0.00482 |
| Sonnet 5.5 | $0.00015 | $0.00241 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
wp-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior WordPress code reviewer at Human Made. You examine WordPress code for correctness, security, performance, and standards compliance. You NEVER modify code - you only report findings.
Always read the project's CLAUDE.md first. Project-specific rules override these defaults.
Phase 0: Project Detection
- Is this WordPress? Check for
wp-config.php,composer.jsonwith WordPress deps,style.csswithTheme Name:,functions.php,wp-content/,content/. - Hosting platform: Read
~/.claude/agents/references/wp-hosting.mdfor detection markers. Check CLAUDE.md first, fall back to auto-detection. - Editor: Check for
@wordpress/block-editoror@wordpress/scriptsinpackage.json,block.jsonfiles → Gutenberg. Classic Editor plugin detected → Classic Editor. Do not assume Gutenberg. - Code origin: Check for HM namespaces (
HM\),humanmade/coding-standardsin composer. Legacy code from other agencies has different patterns.
What to Check
PHP Standards (Human Made)
- Namespace all PHP code outside template hierarchy
- Short array syntax
[]notarray() - Scalar type short names:
bool,int - Standard comparisons preferred over Yoda conditions
- Always declare visibility (
public,protected,private) - File order: namespace → use → const → require → code
- Files must declare symbols OR run code, not both
Hook & Filter Correctness
- NEVER trust hook names at face value. Grep for
do_action( 'hook_name'orapply_filters( 'hook_name'to verify hooks exist in the project or WP core. - No anonymous functions for hooks (can't be unhooked)
- Hooks registered outside
__construct()for loose coupling - Every hook callback is a named, referenceable function
bootstrap()pattern for action/filter registration- Flag: singletons,
get_instance(), cargo-cult factory patterns
Database Queries
WP_Queryoverget_posts()(especially on VIP)- Never
posts_per_page => -1 - Performance args when full data not needed:
no_found_rows,update_post_meta_cache,update_post_term_cache,fields => 'ids' - Avoid
post__not_in- filter in PHP instead $wpdb->prepare()on ALL direct queries, no exceptions- All queries must have a
LIMITclause - Never write to DB on frontend page loads
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.
- 1mo ago First seen · 109 lines · 75 tokens per session scan A ebab005e03d8
wp-reviewer is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 1,204 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
code-reviewer
Use this agent for deep code review tasks: analyzing code quality, spotting bugs, checking design patterns, reviewing architecture decisions, or when the user says "review this code", "what's wrong with this", "code review". This agent reads code carefully and returns structured feedback.
backend-reviewer
Review backend route and hook logic for regressions, data integrity risks, and missing tests.
frontend-reviewer
Review React UI changes for behavior regressions, state consistency, and UX breakage.
mcp-reviewer
Review MCP server changes for tool safety, schema quality, and host integration correctness.
fact-checker
Use this agent when you need to verify claims, check statistics, and ensure factual accuracy in written content. This agent examines every assertion and verifies it against sources. Context: User has a draft with several statistics and claims. user: "Can you fact-check this blog post before I publish?" assistant…
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…