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 skills add Lonsdale201/wp-agent-skills --skill lw-site-manager-overviewgit clone --depth 1 https://github.com/Lonsdale201/wp-agent-skillsWrote 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/skills/lonsdale201/wp-agent-skills/lw-site-manager-overview)<a href="https://agentmods.dev/skills/lonsdale201/wp-agent-skills/lw-site-manager-overview"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/lw-site-manager-overview/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/skills/lonsdale201/wp-agent-skills/lw-site-manager-overview"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/lw-site-manager-overview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 91 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 191 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00230 | $0.04576 |
| Opus 5 | $0.00115 | $0.02288 |
| Sonnet 5 | $0.00046 | $0.00915 |
| Haiku 4.5 | $0.00023 | $0.00458 |
Grade A, and why
lw-site-manager-overview scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST "https://site.example/wp-json/wp-abilities/v1/abilities/site-manager/check-updates/run" \ How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LW Site Manager: overview and consumer reference
For developers and AI agents calling the LW Site Manager plugin's abilities — a curated, security-checked exposure of 120+ WordPress operations through the WP 6.9+ Abilities API. The plugin's positioning is "AI-ready alternative to MainWP" — but the surface and the security model differ, and that distinction matters for both consumers and reviewers.
Misconception this skill corrects
"It's just MainWP with a different name — point a token at it and run remote management."
It isn't. MainWP-class tools use a single privileged dashboard token to do almost-anything against the target install; LW Site Manager exposes per-operation abilities, each gated by a specific WP capability check through a centralized PermissionManager. Verified at src/Abilities/PermissionManager.php — can_manage_updates requires both update_plugins AND update_themes; can_install_plugins requires install_plugins; can_view_health requires view_site_health_checks; can_manage_backups / can_manage_database / can_manage_cache / can_manage_options all require manage_options. There is no "admin override" or single-token bypass.
The practical difference for an integrator:
- A user with WP role
editor(noinstall_plugins) can callsite-manager/list-plugins(read) but NOTsite-manager/install-plugin— gracefully gets 403 from the WP layer, not from a custom ACL. - A user without
view_site_health_checkscan't callsite-manager/health-checkeven if their Application Password is valid. - A compromised Application Password is bounded by THAT user's WP capabilities, not by a global token.
Other AI-prone misconceptions:
- "PHP 8.1+ per the README." Wrong — the actual plugin header (
Requires PHP: 8.2) is binding. Verified at lw-site-manager.php:8. The README and CHANGELOG are stale on this; WP enforces the header. - "All abilities are listed in the README's table." Wrong — the README lists ~60 abilities; source has 126 unique IDs (verified by grepping
'site-manager/...'literals insrc/Abilities/). The full set includes things the README skips:bulk-posts,bulk-comments,restore-post,duplicate-post,duplicate-page,reorder-pages,set-post-meta,delete-user-meta,wc-revenue-stats,wc-low-stock-products,wc-bulk-orders, etc. - "The MCP adapter ships with the plugin." No. The plugin exposes abilities; the MCP adapter is a separate concern (Anthropic's MCP server bridge for the WP Abilities API). The plugin works without it via the REST run endpoint.
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.
- 9d ago First seen · 276 lines · 230 tokens per session scan A 57261ccc9207
lw-site-manager-overview is a skill published in the GitHub repository Lonsdale201/wp-agent-skills (22 stars, last pushed 2d ago), licensed MIT. It adds 230 tokens to every session and 4,576 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
wp-plugin-development
Architecture and development guidelines for WordPress plugins published on wordpress.org: file structure, plugin header, lifecycle hooks, Settings API, admin UI, escaping helpers for admin JavaScript, default values and option migrations, multisite-shared resources, custom post types, custom database tables…
wp-plugin-performance
Performance guidelines for WordPress plugin development: database optimization, object caching, conditional asset loading, efficient hooks, HTTP requests, WP-Cron, AJAX/REST optimization, and common anti-patterns. Based on official WordPress Developer Resources and WP VIP documentation.
build-mcp-server
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates…
data-manager-api-setup
Guides developers through client library installation and authentication setup steps for the Data Manager API. Use this skill when a user is getting started with the Data Manager API and needs to setup their local environment, install the client library, or setup access to the API. Don't use for implementing audience…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
new
Create a new project to start development quickly.