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 agentmods add skills/trtmn/agent-plugins/wp-custom-themenpx skills add trtmn/agent-plugins --skill wp-custom-themegit clone --depth 1 https://github.com/trtmn/agent-pluginsWhat 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 | $0.00143 | $0.09060 |
| Opus 5 | $0.00072 | $0.04530 |
| Sonnet 5 | $0.00029 | $0.01812 |
| Haiku 4.5 | $0.00014 | $0.00906 |
Grade C, and why
wp-custom-theme scanned grade C 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 yesterday.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- wp:query {"queryId":0,"query":{"perPage":10,"pages":0,"offset":0,"postType":"post","order":"desc","orderBy":"date","inherit":true}} --> How it starts
The opening of the file, as written. The whole thing — 1,118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custom WordPress Theme Skill
A comprehensive guide for creating and maintaining custom WordPress themes at an intermediate level, covering theme structure, PHP hooks & template tags, CSS/Gutenberg, and performance & security.
0. Discovery Interview (Start Here for New Themes)
Before writing any code, interview the user to understand their requirements. Use the answers to recommend the right theme approach (FSE, Classic, or Hybrid) and tailor the implementation.
Interview Questions
Ask these questions — you can combine them into a single message, but keep it conversational:
- Site type — What kind of site is this? (blog, portfolio, business/marketing, e-commerce, membership, news/magazine, or other)
- Client editing — Will the site owner / client edit pages and layouts themselves after launch, or is this developer-managed?
- Dynamic PHP logic — Does the theme need complex server-side logic in templates? (e.g. conditional content based on user roles, custom WP_Query loops, real-time data from external APIs)
- WordPress version — What WP version will this run on? (or: is the host keeping WP up to date?)
- Existing base — Starting from scratch, extending an existing theme, or building a child theme?
- Plugins — Any must-have plugins? (WooCommerce, ACF, Elementor, etc. — some conflict with FSE)
- Design complexity — Is this a pixel-perfect custom design, or is an opinionated block-based layout acceptable?
You do not need to ask all seven at once. Start with 1–4; follow up if answers are ambiguous.
FSE Recommendation Logic
After gathering answers, apply this decision table:
| Signal | Favours |
|---|---|
| Client will edit layouts/pages themselves | FSE |
| New project on WP 6.4+ | FSE |
| Design-focused, visually rich site | FSE |
| No complex PHP needed in templates | FSE |
| Complex PHP logic in templates (conditional output, custom queries) | Classic |
| Legacy/existing classic theme being extended | Classic |
| Page-builder plugin (Elementor, Divi) in use | Classic |
| WooCommerce without FSE-compatible theme | Classic (or verify plugin FSE support first) |
| Wants block editor design system, but keeps some PHP templates | Hybrid |
| Migrating gradually from classic → FSE | Hybrid |
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.
- yesterday First seen · 1,118 lines · 143 tokens per session scan C 7b9e51ef5472
wp-custom-theme is a skill published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 5d ago), licensed Unlicense. It adds 143 tokens to every session and 9,060 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…