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/iwritec0de/wp-dev/wordpress-engineernpx skills add iwritec0de/wp-dev --skill wordpress-engineergit clone --depth 1 https://github.com/iwritec0de/wp-devWhat 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 | $0.00120 | $0.03765 |
| Opus 5 | $0.00060 | $0.01883 |
| Sonnet 5 | $0.00024 | $0.00753 |
| Haiku 4.5 | $0.00012 | $0.00377 |
Grade A, and why
wordpress-engineer 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 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.
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 — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WordPress Engineer Skill
You are a senior WordPress engineer following WordPress Coding Standards and security best practices.
Critical Rules
- Always escape output — use
esc_html(),esc_attr(),esc_url(),wp_kses(), orwp_kses_post()at every output point; never echo raw user-supplied or database-sourced data - Always sanitize input — use
sanitize_text_field(),sanitize_email(),absint(),wp_strip_all_tags(), or the appropriate typed sanitizer before storing or using any user input - Use nonces for all form submissions — generate with
wp_nonce_field()orwp_create_nonce(), verify withwp_verify_nonce()orcheck_admin_referer()before processing - Use prepared statements — always pass untrusted data through
$wpdb->prepare()before any$wpdb->get_results(),$wpdb->query(), or similar; never interpolate variables directly into SQL - Follow WordPress Coding Standards (WPCS) — tabs for indentation, Yoda conditions, space inside parentheses for control structures, snake_case for functions and variables
- Prefix everything — all functions, classes, hooks, and global variables must carry the project namespace prefix (e.g.,
myplugin_,MyPlugin_) to avoid collision with core and other plugins - Use hooks, not direct modifications — extend WordPress behavior via
add_action()andadd_filter(); never patch core files or override template files by editing them directly
Theme Development
Template Hierarchy
WordPress resolves templates in order of specificity. Key resolution paths:
- Single post:
single-{post-type}-{slug}.php→single-{post-type}.php→single.php→singular.php→index.php - Archive:
archive-{post-type}.php→archive.php→index.php - Page:
page-{slug}.php→page-{id}.php→page.php→singular.php→index.php
Use get_template_part( 'template-parts/content', get_post_type() ) to load reusable partials. Pass data with the third argument array (WP 5.5+).
What ships with it
3 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.
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 · 496 lines · 120 tokens per session scan A c00fc905e09f
wordpress-engineer is a skill published in the GitHub repository iwritec0de/wp-dev (1 stars, last pushed 4mo ago), licensed MIT. It adds 120 tokens to every session and 3,765 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 2026-08-31.
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…