wp-contribute

wp-contribute is a command for Claude Code from yojahny55/claude-wp-builder. It costs 33 tokens per session (2,081 once invoked), scanned A, original, MIT.

A contributor command for working on the Claude WP Builder plugin itself rather than building a user's WordPress site.

In plain words
What is it for?
Use it to scaffold commands, agents, skills, or checks, verify the repository, open a pull request, or prepare a versioned release.
Why use it?
It gives repository contributors a defined way to create or check plugin files and prepare pull requests or releases.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; positional $N argument.

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 claude-wp-builder plugin — 15 skills, 30 commands, 15 agents shipped together

Good fit Use it to scaffold commands, agents, skills, or checks, verify the repository, open a pull request, or prepare a versioned release.

Compare 6 commands 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 yojahny55/claude-wp-builder
Claude Code
/plugin install claude-wp-builder

Made for: Claude Code.

Or install claude-wp-builder, the plugin that ships this one along with the rest of its 15 skills, 30 commands, 15 agents.

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-contribute

README.md
[![agentmods](https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-contribute/github.svg)](https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-contribute)
Your own site
<a href="https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-contribute"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-contribute/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.

agentmods 80×15 button for wp-contribute

Your own site · 80×15
<a href="https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-contribute"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-contribute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,081 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 $0.00033 $0.02081
Opus 5 $0.00016 $0.01040
Sonnet 5 $0.00007 $0.00416
Haiku 4.5 $0.00003 $0.00208

Measured 5d ago against content hash aedb0532a1c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wp-contribute 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 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.

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.

commands/wp-contribute.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WP Contribute — Working on the Plugin Itself

This command operates on this repository, not on a user's WordPress project. Everything below assumes the working directory is the plugin root (it contains .claude-plugin/).

Required skill: read ${CLAUDE_PLUGIN_ROOT}/skills/wp-contributing/SKILL.md before doing anything. It owns the layer rules, the grep-gate test style and the frontmatter contracts that every step here assumes.

Step 1: Parse arguments

$ARGUMENTS starts with a subcommand:

Subcommand Form
new /wp-contribute new <command|agent|skill|check> <name>
check /wp-contribute check
pr /wp-contribute pr [--title "..."]
release /wp-contribute release [major|minor|patch] — maintainers

With no subcommand, print the table above and exit 0.

Confirm the working directory is the plugin root:

[ -d .claude-plugin ] && [ -d commands ] && [ -d tests/checks ]

If not, stop: "Not in the claude-wp-builder repository root. This command edits the plugin itself — to build a WordPress site, use /wp-init and /wp-yolo."


Step 2 — new: scaffold a layer file with everything it needs

The point of this subcommand is that a new capability is never one file. Emit all of it, so the PR cannot arrive with the check or the doc row missing.

new command <name>

  1. commands/<name>.md — frontmatter carrying description, allowed-tools and argument-hint (add Agent to allowed-tools only if it will dispatch subagents), then numbered ## Step N: sections. The first step parses $ARGUMENTS; the second reads the project's .claude/CLAUDE.md for prefix, theme slug, languages, template and i18n strategy, and tells the user to run /wp-init first when it is missing.
  2. tests/checks/<name>.sh — a grep gate in the house style: a comment naming the contract it protects, set -euo pipefail, cd "$(dirname "$0")/../..", a fail() helper, assertions, echo PASS. Make it executable.
  3. A row in the README Commands Reference table (Command · Path · Required? · Description).
  4. An entry in docs/commands.md, and a step in docs/workflows.md if it belongs to a build path (A /wp-yolo, B step-by-step, C cinematic).
  5. A CHANGELOG.md entry under [Unreleased]### Added.

Read the full file on GitHub · 170 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. 5d ago First seen · 170 lines · 33 tokens per session scan A aedb0532a1c9

Subscribe to this mod's changes

wp-contribute is a command published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 2,081 once invoked, about $0.0002 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 2026-09-03.