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.
npx agentmods add commands/yojahny55/claude-wp-builder/wp-creategit clone --depth 1 https://github.com/yojahny55/claude-wp-builderWrote 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/commands/yojahny55/claude-wp-builder/wp-create)<a href="https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-create"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-create.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.06395 |
| Opus 5 | $0.00012 | $0.03197 |
| Sonnet 5 | $0.00005 | $0.01279 |
| Haiku 4.5 | $0.00002 | $0.00639 |
Grade B, and why
wp-create scanned grade B with 2 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 5d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo bin/wp-env-setup.sh native-setup \ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"extensions": ["mysql", "curl", "mbstring", "xml", "gd", "zip", "intl"] How it starts
The opening of the file, as written. The whole thing — 735 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WP Create — Environment Setup Orchestrator
Create a full local WordPress development environment: detect available tools, download WordPress, create the database, configure the web server, install plugins, and generate the .wp-create.json manifest. Supports native (Nginx/Apache/Caddy), Docker, DDEV, Lando, and wp-env environments.
$WP convention: Throughout this command, $WP refers to the WP-CLI wrapper determined by the chosen environment. For native installs it is wp --path=<path>, for Docker it is docker exec <container> wp --allow-root, for DDEV it is ddev wp, for Lando it is lando wp, for wp-env it is npx wp-env run cli wp. Substitute the correct wrapper in every WP-CLI command below.
Step 0: Parse Arguments
Extract the --path= value from $ARGUMENTS.
- If
$ARGUMENTScontains--path=<value>, use<value>as the target project path. - If
$ARGUMENTSis a bare path (no flag), treat it as the target path. - If no path is provided, ask the user:
"Where should the WordPress project be created? Provide an absolute path (e.g., /var/www/html/my-project):"
- Resolve the path to an absolute path.
- Store it as
PROJECT_PATHfor use in all subsequent steps.
Step 1: Environment Detection
Run the detection script to discover what tools are available on the system.
bash -c "${CLAUDE_PLUGIN_ROOT}/bin/wp-env-setup.sh detect"
Parse the JSON output. The structure is:
{
"os": "fedora",
"package_manager": "dnf",
"web_servers": {
"nginx": { "installed": true, "version": "1.24.0", "running": true },
"apache": { "installed": true, "version": "2.4.58", "running": false },
"caddy": { "installed": false }
},
"php": {
"versions": ["8.2", "8.3"],
"active": "8.3",
"extensions": ["mysql", "curl", "mbstring", "xml", "gd", "zip", "intl"]
},
"docker": {
"installed": true,
"version": "24.0.7",
"compose": true
},
"tools": {
"ddev": { "installed": false },
"lando": { "installed": false },
"wp-env": { "installed": false },
"wp-cli": { "installed": true, "version": "2.9.0" }
},
"database": {
"mariadb": { "installed": true, "version": "10.11", "running": true },
"mysql": { "installed": false }
}
}
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.
- 5d ago First seen · 735 lines · 24 tokens per session scan B 794fe5dc75b0
wp-create is a command published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 6,395 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
setup
SoDam-Design-Kit 설정 마법사 — config.json 생성 + shadcn 컴포넌트 스캔으로 component-map 초기 시드.
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
design-enforce
Use when code has drifted off the design system. Raw hex values and pixel numbers written where a token already exists, one-off components, library defaults left untouched. Finds every bypass and fixes it.
design-grill
Use when a design keeps getting reinvented every session. Interviews you until you share one understanding, then writes the vocabulary and the binding decisions into the repo so they survive the next context window.
design-triage
Use when a dwic audit report is full of findings and there is no plan. Ranks them into an order someone can work through, then works through it.
audit
Run a full UI/UX design audit on the current project. Scores 12 dimensions and produces a markdown report with prioritized findings.