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 tmj-90/gaffer --skill schema-markupgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/tmj-90/gaffer/schema-markup)<a href="https://agentmods.dev/skills/tmj-90/gaffer/schema-markup"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/schema-markup/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/tmj-90/gaffer/schema-markup"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/schema-markup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00091 | $0.01028 |
| Opus 5 | $0.00046 | $0.00514 |
| Sonnet 5 | $0.00018 | $0.00206 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
schema-markup 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 6d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement structured data that earns rich results
JSON-LD is the recommended format (Google's preference). Schema.org types are the vocabulary. Rich results in Google and citations in AI search engines are the outcomes.
High-value schema types (implement these first)
| Type | Rich result earned | Required fields |
|---|---|---|
Organization |
Knowledge panel, sitelinks search | name, url, logo |
WebSite |
Sitelinks search box | url, potentialAction (SearchAction) |
FAQPage |
FAQ dropdowns in SERP | mainEntity → Question → acceptedAnswer |
Article |
Top stories, rich snippet | headline, author, datePublished, image |
Product |
Product snippet with price/rating | name, offers, aggregateRating |
HowTo |
How-to steps in SERP | name, step array |
BreadcrumbList |
Breadcrumb in SERP URL | itemListElement array |
LocalBusiness |
Local pack, knowledge panel | name, address, telephone |
JSON-LD placement
Prefer <head> as a <script type="application/ld+json"> block. Google also supports JSON-LD placed in the <body> (including markup injected by JavaScript), so in-body placement is valid when <head> injection isn't practical — <head> is simply the cleaner default. One <script> block per schema type per page (or a @graph array for multiple types).
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "FAQPage",
"mainEntity": [
{
"@type": "Question",
"name": "What is your refund policy?",
"acceptedAnswer": {
"@type": "Answer",
"text": "We offer a 30-day full refund, no questions asked."
}
}
]
}
</script>
Common mistakes that block rich results
- Content mismatch — schema claims a
priceorratingthat doesn't appear on the page. Google requires visible content to match. - Missing required fields — check Google's required/recommended fields per type at developers.google.com/search/docs/appearance.
- Incorrect
datePublishedformat — must be ISO 8601 (2026-06-17T09:00:00+00:00). - Markup on 404/noindex pages — Google won't process structured data on non-indexable pages.
- Multiple conflicting types — use
@grapharray to combine without conflict.
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.
- 6d ago First seen · 79 lines · 91 tokens per session scan A 712e5beabfbf
schema-markup is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,028 once invoked, about $0.0005 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
bulwark-brainstorm
Role-based brainstorming with dual modes: --scoped (sequential Task tool, 5 roles) and --exploratory (Agent Teams peer debate, 4 roles). Use for feasibility assessment and idea validation.
plan-creation
Create structured implementation plans via a 4-role scrum team (Product Owner, Architect, Eng/Delivery Lead, QA/Critic) with optional Agent Teams peer debate mode.
anthropic-validator
Validates Claude Code assets (skills, hooks, agents, commands, MCP servers, plugins) against official Anthropic standards. Fetches latest docs dynamically and produces structured validation reports.
create-subagent
Generates single-purpose Claude Code sub-agents for use via the Task tool. Use when creating dedicated sub-agents, scaffolding agent definitions, or generating agents with diagnostics and permissions setup.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
code-review
Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.