lw-firewall-custom-form-adapter

lw-firewall-custom-form-adapter is a skill for Codex from Lonsdale201/wp-agent-skills. It costs 143 tokens per session (2,515 once invoked), scanned A, original, MIT.

A design guide for connecting LW Firewall's lower-level security components to a custom public form. LW Firewall has dedicated protection for registration and password reset, but no built-in guard for arbitrary forms.

In plain words
What is it for?
Use it when designing a custom adapter for an unrelated form, deciding which token and rate-limiting components to reuse, or documenting a future generic form-guard interface.
Why use it?
It prevents developers from treating a contact, lead, or application form as if it were WordPress registration, which could apply the wrong fields and counters.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it when designing a custom adapter for an unrelated form, deciding which token and rate-limiting components to reuse, or documenting a future generic form-guard interface.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lonsdale201/wp-agent-skills/lw-firewall-custom-form-adapter
Install

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.

Any agent
npx skills add Lonsdale201/wp-agent-skills --skill lw-firewall-custom-form-adapter
Clone the repo
git clone --depth 1 https://github.com/Lonsdale201/wp-agent-skills

Made for: Codex.

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 lw-firewall-custom-form-adapter

README.md
[![agentmods](https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/lw-firewall-custom-form-adapter/github.svg)](https://agentmods.dev/skills/lonsdale201/wp-agent-skills/lw-firewall-custom-form-adapter)
Your own site
<a href="https://agentmods.dev/skills/lonsdale201/wp-agent-skills/lw-firewall-custom-form-adapter"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/lw-firewall-custom-form-adapter/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 lw-firewall-custom-form-adapter

Your own site · 80×15
<a href="https://agentmods.dev/skills/lonsdale201/wp-agent-skills/lw-firewall-custom-form-adapter"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/lw-firewall-custom-form-adapter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,515 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00143 $0.02515
Opus 5 $0.00072 $0.01257
Sonnet 5 $0.00029 $0.00503
Haiku 4.5 $0.00014 $0.00251

Measured 9d ago against content hash 15cda0c7cffa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lw-firewall-custom-form-adapter 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 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.

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.

lw-plugins/lw-firewall-custom-form-adapter/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LW Firewall custom-form adapter

LW Firewall 1.5.6 has dedicated guards for core registration and password reset. It does not expose a generic “attach this firewall to any form” service, field descriptor, render/validate interface, or form registry.

Use this skill only when a companion plugin deliberately builds an adapter from the lower-level public classes. Do not present the adapter as a built-in generic LW Firewall feature.

Choose the correct contract

Form Current LW integration
Core WordPress registration automatic RegisterGuard when its activation conditions pass
Custom user registration use lw-firewall-registration-guard
Core lost password automatic proof plus limits
Woo/custom lost password using canonical hook rate limits; proof only on core wp-login.php
Arbitrary contact/lead/application form no automatic honeypot or token
/wp-json/ form endpoint optional shared REST rate bucket only

Do not invoke RegisterGuard::validate() for an unrelated form: it reads fixed registration fields from $_POST, increments registration-specific rejection counters, and can create a misleading register_spam ban.

Reusable primitives and their limits

RegisterToken::issue() and verify() are public static methods, and RateLimiter accepts a custom storage key. They are reusable only with a version-pinned adapter and explicit fallback policy; their class names and settings remain registration-oriented.

The token format changed in 1.5.6 — this is a breaking change for adapters. The payload is now v2.<issued>.<scope>.<nonce>, HMAC-signed as a whole, where the nonce is 16 random bytes per render. Three consequences:

  • The scope is signed, not just a storage-key prefix. A token issued with one scope can no longer be presented to another form — but it also means issue() and verify() must be given the same scope. issue() defaults to 'reg', so an adapter that calls a bare issue() and verifies with its own scope now fails every submission. Always pass the scope on both sides.
  • Same-second renders are distinct. The 1.5.4 collision (identical tokens within one second, single-use rejecting all but the first, a shared page cache handing one token to everybody) is gone.
  • Scope is normalized to [a-z0-9_-] after strtolower(), and other characters are stripped — my form! and myform are the same scope. Pick a scope that is already in that alphabet.

Read the full file on GitHub · 240 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 240 lines · 143 tokens per session scan A 15cda0c7cffa

Subscribe to this mod's changes

lw-firewall-custom-form-adapter is a skill published in the GitHub repository Lonsdale201/wp-agent-skills (22 stars, last pushed 2d ago), licensed MIT. It adds 143 tokens to every session and 2,515 once invoked, about $0.0007 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.

Related

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…

fernandotellado/ai-skills · 86 tokens

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.

fernandotellado/ai-skills · 55 tokens

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…

anthropics/claude-plugins-official · 111 tokens

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…

google/skills · 86 tokens

workers-best-practices

Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.

cloudflare/skills · 25 tokens

new

Create a new project to start development quickly.

clacky-ai/openclacky · 10 tokens