how-to-write-skills

how-to-write-skills is a skill for Claude Code, Codex from cosmincraciun97/stonewright-wp-mcp. It costs 47 tokens per session (1,403 once invoked), scanned A, original, GPL-2.0.

A guide for creating, reviewing, importing, and testing Stonewright site skills. Skills are reusable instructions that coding agents can invoke for particular tasks.

In plain words
What is it for?
Use it when authoring or checking skill descriptions, body limits, version constraints, exposure flags, or required tests.
Why use it?
It helps ensure a skill has suitable triggers, size, version limits, exposure settings, and validation checks before agents use it.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it when authoring or checking skill descriptions, body limits, version constraints, exposure flags, or required tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cosmincraciun97/stonewright-wp-mcp/how-to-write-skills
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 cosmincraciun97/stonewright-wp-mcp --skill how-to-write-skills
Clone the repo
git clone --depth 1 https://github.com/cosmincraciun97/stonewright-wp-mcp

Made for: Claude Code, 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 how-to-write-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/cosmincraciun97/stonewright-wp-mcp/how-to-write-skills/github.svg)](https://agentmods.dev/skills/cosmincraciun97/stonewright-wp-mcp/how-to-write-skills)
Your own site
<a href="https://agentmods.dev/skills/cosmincraciun97/stonewright-wp-mcp/how-to-write-skills"><img src="https://agentmods.dev/badge/skills/cosmincraciun97/stonewright-wp-mcp/how-to-write-skills/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 how-to-write-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/cosmincraciun97/stonewright-wp-mcp/how-to-write-skills"><img src="https://agentmods.dev/badge/skills/cosmincraciun97/stonewright-wp-mcp/how-to-write-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,403 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.
Origin unknown 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 $0.00047 $0.01403
Opus 5.5 $0.00019 $0.00561
Sonnet 5.5 $0.00009 $0.00281
Haiku 4.5 $0.00005 $0.00140

Measured 12d ago against content hash 0486d957004a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

how-to-write-skills 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 12d 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.

skills/how-to-write-skills/SKILL.md · 140 lines

The source is not reproduced here

Licensed GPL-2.0

The repository is licensed GPL-2.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 12d ago Changed 0486d957004a
  2. 13d ago First seen · 140 lines · 47 tokens per session scan A 4f07150ccda3

Subscribe to this mod's changes

how-to-write-skills is a skill published in the GitHub repository cosmincraciun97/stonewright-wp-mcp (30 stars, last pushed 2d ago), licensed GPL-2.0. It adds 47 tokens to every session and 1,403 once invoked, about $0.0002 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 2026-10-11.

Related

Other skills, from other repositories

search-replace

Find and replace text across posts, pages and post meta (including Elementor data) from a previewed, approved plan, with per-post undo. Activate when the user wants to change a string, URL, domain, brand name or phone number site-wide, or fix the same typo on many pages.

wppilot-labs/wordpress-mcp-elementor-wppilot · 64 tokens

site-header

Design and build the site-wide header (logo, menu, language switcher, cart, call to action) yourself, then have the site save it in the right places and check it. Activate whenever the user asks to create, fix, redesign, modernise, tidy or "make professional" a header or top navigation, or complains that the menu…

wppilot-labs/wordpress-mcp-elementor-wppilot · 98 tokens

scheduled-audits

Set up audits the site runs by itself on a schedule (accessibility, content and SEO, media alt text) with results emailed to administrators and kept as reports that say what is new and what was fixed. Activate when the user wants recurring or automatic checks, a weekly or daily audit, monitoring of broken links or…

wppilot-labs/wordpress-mcp-elementor-wppilot · 81 tokens

a11y-audit

Audit a page of this site for accessibility against WCAG 2.2, then fix image alt text across the media library by looking at each image. Activate when the user asks about accessibility, WCAG, ADA or EAA compliance, screen readers, alt text, or an accessibility score.

wppilot-labs/wordpress-mcp-elementor-wppilot · 65 tokens

content-audit

Audit a site's published content for broken internal links, orphan pages, thin content, missing SEO meta and JSON-LD problems, then plan fixes with the person. Activate when the user asks for a content, SEO or link audit, asks what is broken on the site, or wants to find orphaned or thin pages.

wppilot-labs/wordpress-mcp-elementor-wppilot · 68 tokens

woo-basics

Read a WooCommerce store (products, variations, categories, tags, store settings, orders, customers) and make basic product edits (name, description, price, stock) that can be undone. Activate when the user asks about their products, stock levels, prices, orders or customers, or asks to rename a product, rewrite its…

wppilot-labs/wordpress-mcp-elementor-wppilot · 85 tokens