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-lms-rest-frontendgit 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-lms-rest-frontend)<a href="https://agentmods.dev/skills/lonsdale201/wp-agent-skills/lw-lms-rest-frontend"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/lw-lms-rest-frontend/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-lms-rest-frontend"><img src="https://agentmods.dev/badge/skills/lonsdale201/wp-agent-skills/lw-lms-rest-frontend.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 | $0.00106 | $0.01470 |
| Opus 5.5 | $0.00042 | $0.00588 |
| Sonnet 5.5 | $0.00021 | $0.00294 |
| Haiku 4.5 | $0.00011 | $0.00147 |
Grade A, and why
lw-lms-rest-frontend 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LW LMS REST frontend
Consume the headless learner API. The plugin ships no public templates, shortcodes, or blocks.
Routes
Namespace: lms/v1.
| Method | Path | Gate |
|---|---|---|
GET |
/courses |
public; non-published status filters need matching edit capability |
GET |
/courses/{id} |
public for published; capable users can preview non-published |
GET |
/lessons/{id} |
access, visibility, and drip lock |
GET |
/progress |
current logged-in user |
GET |
/progress/course/{id} |
current logged-in user |
POST |
/progress |
login, course/lesson match, access, drip, optional quiz gate |
POST |
/lessons/{id}/quiz |
login, access, drip, attempt limits |
GET |
/download/{id} |
signed link, ownership, current access, visibility |
The React admin uses the separate lw-lms/v1/admin/* namespace. Do not call those routes from a learner frontend.
Authentication
- Public catalog: no authentication.
- Logged-in browser: WordPress cookie,
credentials: 'same-origin', andX-WP-Nonce. - Headless/mobile: Application Passwords or another reviewed authentication layer.
- Downloads: use the signed URL from the payload in the same user context.
await fetch('/wp-json/lms/v1/progress', {
method: 'POST',
credentials: 'same-origin',
headers: {
'Content-Type': 'application/json',
'X-WP-Nonce': wpApiSettings.nonce,
},
body: JSON.stringify({ course_id: 42, lesson_id: 100, status: 'completed' }),
});
Access and visibility
Course content is public marketing copy. It is not evidence of enrollment. Gate the player with access.has_access and each lesson row's accessible value.
Course list access checks do not lazily enroll a viewer in a free course. Opening the full free course can create the enrollment row.
GET /courses accepts status=publish|private|draft|any. A non-published request without the necessary type capability fails with rest_forbidden_status; authorized results are then filtered again by per-post capability. Treat the server's result as authoritative; do not emulate WordPress status capability logic in JavaScript.
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.
- 1mo ago Changed · -56 lines · -17 tokens per session 21a199ca18d2
- 1mo ago First seen · 188 lines · 123 tokens per session scan A 1e1da8f2f286
lw-lms-rest-frontend is a skill published in the GitHub repository Lonsdale201/wp-agent-skills (25 stars, last pushed 7d ago), licensed MIT. It adds 106 tokens to every session and 1,470 once invoked, about $0.0004 per session on Opus 5.5. 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
web-3d-graphics-expert
Expert guide for modern WebGPU and WebGL 3D graphics in the browser using Three.js (WebGPURenderer + TSL), Babylon.js, PlayCanvas, React Three Fiber (R3F), and 3Dviz spatial reasoning — covers object craft across 3 scales, surface continuity at joins, physical interaction envelopes, grounded scientific visualization…
micro-frontend-architect
Expert guide for designing Micro-Frontend architectures using Webpack Module Federation, Vite Federation, and Single-SPA for large scale Vue and React applications.
react-anti-patterns
Introduce React anti-patterns and common mistakes into existing React codebases for training, review, or teaching. Use when asked to intentionally degrade React performance or code quality while keeping apps functional, or to generate anti-pattern examples for junior developer education.
mock-interview
An interactive front-end interview practice guide. It acts as an interviewer, asks progressively harder questions about JavaScript, React, CSS, browser behavior, and Vue, then gives a structured review.
remotion-saas
Building video apps with Remotion - framework, rendering and Player advice.
frontend-best-practices
Coding guidance for building React or Vue front ends, where components display screens and manage user interactions. It covers component responsibilities, state placement, performance, and accessibility.