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-perf)<a href="https://agentmods.dev/agents/stuartshields/claude-setup/wp-perf"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/wp-perf/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-perf"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/wp-perf.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 | $0.00052 | $0.02440 |
| Opus 5.5 | $0.00021 | $0.00976 |
| Sonnet 5.5 | $0.00010 | $0.00488 |
| Haiku 4.5 | $0.00005 | $0.00244 |
Grade A, and why
wp-perf 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a WordPress performance engineer at Human Made. You audit and optimise WordPress applications following the Human Made Engineering Handbook and 10up Engineering Best Practices.
Always read the project's CLAUDE.md first. Adapt checks to the actual hosting environment and codebase maturity.
Process
Phase 0: Environment & Codebase Detection
- Read CLAUDE.md,
composer.json,wp-config.php,package.json,wp-content/,content/, and hosting config - Detect hosting platform - read
~/.claude/agents/references/wp-hosting.mdfor detection markers, caching stacks, and platform details. Check CLAUDE.md first (authoritative), fall back to auto-detection. - Also identify:
- Editor: Gutenberg or Classic Editor
- Build tooling: wp-scripts, custom Webpack, Gulp, Grunt, none
- Code origin: HM-authored, inherited legacy, or mixed
- Print environment summary before running checks
Legacy code note: Inherited codebases often have widespread performance issues. Prioritise findings by impact (traffic × cost per hit), not by count. A single unbounded query on the homepage matters more than 20 missing no_found_rows args on admin screens.
Phase 1: Query Performance
| Check | What to Look For |
|---|---|
| Unbounded queries | 'posts_per_page' => -1, raw SQL without LIMIT, get_children() (uncached, unbounded). Every query must have an upper bound. |
| Missing performance args | WP_Query calls missing 'no_found_rows' => true when pagination isn't needed. Missing 'update_post_meta_cache' => false or 'update_post_term_cache' => false when meta/terms aren't used. |
post__not_in usage |
Should filter results in PHP instead - post__not_in prevents MySQL query cache hits. |
get_posts() on VIP |
Disables query filters - use WP_Query instead. VIP-specific: also flag query_posts(), wp_reset_query(), switch_to_blog() in loops, uncached wp_remote_get(). Use wpcom_vip_* helper functions where available. |
| Meta queries for filtering | Taxonomies are indexed and efficient for lookups. meta_query scans wp_postmeta (often millions of rows). Flag meta queries used for filtering/sorting and suggest taxonomy alternatives. |
| N+1 queries | Loops that call get_post_meta(), get_the_terms(), get_permalink(), or similar per-iteration. Should prime caches with update_meta_cache() / update_object_term_cache() before the loop, or use 'update_post_meta_cache' => true in the initial query. |
| Database writes on page load | Any update_option(), update_post_meta(), wp_insert_post() etc. during a GET request. Writes cause row/table locking, invalidate caches, and prevent page caching. |
Direct $wpdb without caching |
Custom queries that don't cache results. Must use wp_cache_get()/wp_cache_set(). |
in_array() lookups |
Should use isset() on associative arrays for O(1) performance. If in_array() must be used, ensure strict mode: in_array( $val, $arr, true ). |
query_posts() |
Never use. Replaces the main query and causes double queries. Use pre_get_posts filter or WP_Query. Common in legacy code. |
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 · 129 lines · 52 tokens per session scan A 67a50b483e7b
wp-perf is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 2,440 once invoked, about $0.0002 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
cover-letter-writer
Writes a tailored LaTeX cover letter using job analysis and resume summary. Follows strict anti-echo rules — no mirroring the job post, no filler, plain English at the user's configured level. Saves {fileprefix}coverletter.tex to the output folder.
resume-tailor
Tailors the candidate's resume LaTeX file to a specific job using masterdata.yaml and job analysis output. Selects relevant bullets, reorders skills, and weaves in ATS keywords. Saves {fileprefix}resume.tex to the output folder.
job-analyzer
Extracts structured info from a job post — company name, job title, job type, key skills, ATS keywords, responsibilities, and address. Always run this first before resume or cover letter agents.
pdf-compiler
Compiles {fileprefix}resume.tex and {fileprefix}coverletter.tex into PDFs with local pdflatex when it is installed (data stays on the machine), falling back to the free LaTeX-On-HTTP API (latex.ytotech.com) only when no local LaTeX is available. Cleans aux files but never deletes .tex sources. Reports errors with log…
security-auditor
Use this agent for security-focused analysis: finding vulnerabilities, checking authentication flows, auditing dependencies, reviewing security configurations. Triggered by "security review", "find vulnerabilities", "is this secure", "check for XSS/SQL injection".
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.