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-firewall-management-abilitiesgit 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-firewall-management-abilities)<a href="https://agentmods.dev/skills/lonsdale201/wp-agent-skills/lw-firewall-management-abilities"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/lw-firewall-management-abilities/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-firewall-management-abilities"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/lw-firewall-management-abilities.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00125 | $0.03426 |
| Opus 5 | $0.00063 | $0.01713 |
| Sonnet 5 | $0.00025 | $0.00685 |
| Haiku 4.5 | $0.00013 | $0.00343 |
Grade A, and why
lw-firewall-management-abilities 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.
How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LW Firewall management, abilities and CLI
Use the narrowest management surface that owns the required feature. Admin,
WP-CLI, Site Manager abilities, and wp-config.php constants do not expose the
same operations.
Surface matrix
| Surface | Suitable work | Authority |
|---|---|---|
| Admin UI | full human configuration, import/export, worker, logs, alert/reset settings, automatic-ban table | manage_options |
| WP-CLI | complete automation, list edits, reset/alert operations, automatic bans | trusted shell context |
| Site Manager abilities | read options/logs and manage the manual blacklist only | can_manage_options callback |
wp-config.php constants |
environment-owned immutable overrides | server access |
Do not assume a new admin or CLI feature also exists as an ability.
Option contract
The persisted option is LightweightPlugins\Firewall\Options::OPTION_NAME,
whose value is lw_firewall.
There are now three read views, and picking the wrong one is the classic bug:
| Call | Returns |
|---|---|
Options::get_stored() |
defaults + database, no constant overlay — the editing/persistence view |
Options::get_all() |
stored values with LW_FIREWALL_* constants layered on top — the effective runtime view |
Options::get($key) |
the constant if defined, otherwise the get_all() value |
Options::overridden() |
the option keys a constant currently pins |
Since 1.5.5 get_all() applies constants (it did not in 1.5.4, which is why the
worker, the hook bootstrap, the .htaccess sync and the status screen all ran
on a configuration the operator had not chosen). Saving reads get_stored(),
so a pinned value is never written into the database and never survives the
constant's removal.
Options::save() accepts a partial array, preserves other known values, and
persists only keys present in get_defaults(). Since 1.5.6 it also runs
OptionSchema::apply() on every key — one server-side value policy that
clamps numeric ranges and allowlists enums for the form, WP-CLI and the settings
import alike. Passing a well-typed value is still good practice, but a bad one
is now clamped rather than stored:
What ships with it
1 file 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.
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 · 295 lines · 125 tokens per session scan A f0b67b01a4c5
lw-firewall-management-abilities is a skill published in the GitHub repository Lonsdale201/wp-agent-skills (22 stars, last pushed 2d ago), licensed MIT. It adds 125 tokens to every session and 3,426 once invoked, about $0.0006 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.
Other skills, from other repositories
astro-seo
Audits and improves SEO for Astro sites. Use when the user asks to audit, set up, or improve SEO on an Astro site, or mentions head metadata, structured data, JSON-LD, sitemaps, IndexNow, Open Graph images, schema endpoints, NLWeb, hreflang, or search engine indexing in an Astro project. Produces drop-in code routed…
static-seo
Audits and improves SEO for static HTML sites. Use when the user asks to audit, set up, or improve SEO on a static site (Hugo, Jekyll, 11ty, Gatsby, Next.js static export, hand-rolled HTML, or wp-static-clone output), or mentions head metadata, structured data, JSON-LD, sitemaps, IndexNow, Open Graph images, schema…
readability-check
Runs a readability audit on a blog post draft or other multi-paragraph prose, calibrated for readers who read English as a second language. Checks ten categories — overall structure and topic order, paragraph structure, opening paragraph strength, tiered sentence length, passive voice, difficult words, filler and…
content-seo
Audits a blog post draft or page copy for content-level SEO: search intent fit, focus keyphrase placement, E-E-A-T signals (experience, expertise, authoritativeness, trustworthiness), helpfulness and originality, content freshness, and internal linking. Use when the user asks "will this rank", "SEO check this post"…
wp-static-clone
Clones a live WordPress (or other CMS-driven) site into a static HTML site deployable on any static host (Cloudflare Pages, Netlify, Vercel, S3+CloudFront, plain Apache/nginx). Use when the user wants to "scrape", "freeze", "archive", "static-ify", or "move to [host]" a WordPress site, or asks to turn a sitemap into…
metadata-check
Reviews short high-value strings — page titles, meta descriptions, schema description fields, FAQ answers, GitHub repo taglines, profile bios, social-card copy, and other metadata where Flesch and paragraph-level readability checks don't apply. Checks front-loading, concreteness, filler, active voice…