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.
/plugin marketplace add yojahny55/claude-wp-builder/plugin install 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-polylang)<a href="https://agentmods.dev/commands/yojahny55/claude-wp-builder/wp-polylang"><img src="https://agentmods.dev/badge/commands/yojahny55/claude-wp-builder/wp-polylang.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 | $0.00014 | $0.01459 |
| Opus 5 | $0.00007 | $0.00730 |
| Sonnet 5 | $0.00003 | $0.00292 |
| Haiku 4.5 | $0.00001 | $0.00146 |
Grade A, and why
wp-polylang 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wp-polylang
Translate an existing site into a second language through Polylang. Run from the WordPress root.
Required skill: read skills/wp-polylang/SKILL.md before doing anything. It
documents the data model and the API contract, and the failure mode this command
exists to avoid.
Step 1: Parse arguments
$ARGUMENTS is <source_lang> <target_lang>, e.g. es en. Both are required;
error and exit if either is missing:
Error: source and target language are required.
Usage: /wp-polylang <source_lang> <target_lang>
One target language per run. For a third language, run the command again.
Confirm the working directory is a WordPress root — wp-config.php must be
present. If it is not, stop and say so.
Set SCRIPTS="${CLAUDE_PLUGIN_ROOT}/skills/wp-polylang/scripts".
Step 2: Ensure Polylang is installed
# Three states, not two: active, installed-but-deactivated, absent. `install` on an
# already-installed plugin is not a reliable activator, so try activation first.
wp plugin is-active polylang \
|| wp plugin activate polylang \
|| wp plugin install polylang --activate
Step 3: Configure languages
wp eval-file "$SCRIPTS/pll-setup.php" <source_lang> <target_lang>
Creates whichever of the two languages Polylang does not already have configured,
using a sane predefined locale (en → en_US, es → es_ES, not Polylang's own
first-match, which is en_AU / es_AR). Succeeds silently — and prints
"Configured languages: …" either way — when both languages already exist, so it is
always safe to run.
Stop if it exits non-zero — it prints exactly what is wrong (Polylang not active, an unrecognised language code, or source and target being the same language).
Step 4: Export what needs translating
MANIFEST="$(mktemp -t pll-manifest-XXXXXX.json)"
wp eval-file "$SCRIPTS/pll-export.php" <source_lang> <target_lang> "$MANIFEST"
Walks every translatable post type and taxonomy — posts, terms, registered
strings, and per-language menus — and writes only what is missing or stale into
$MANIFEST. Prints Exported <n> item(s), skipped <n> already current. Read the
reported item count and the unassigned-language warning, if any.
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.
- 8d ago First seen · 157 lines · 14 tokens per session scan A 0eb8eed11805
wp-polylang is a command published in the GitHub repository yojahny55/claude-wp-builder (6 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 1,459 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
i18n-designer
Use when a product has to work in more than one language. Right-to-left layouts, German strings breaking buttons, date and number formats, or English hardcoded into the UI.
zh
A short command that switches Claude Code to Simplified Chinese. It is handled locally by a command hook.
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.
environment-setup
Use when handling secrets and config. What .env files are, which filename to use, what must never reach GitHub, and why a key works locally but not in production.