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 matteotitta/genesys-skills --skill metadata-lintgit clone --depth 1 https://github.com/matteotitta/genesys-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/matteotitta/genesys-skills/metadata-lint)<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/metadata-lint"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/metadata-lint/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/matteotitta/genesys-skills/metadata-lint"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/metadata-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 44 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Agent Snooping · line 44 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 50 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 265 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00127 | $0.02573 |
| Opus 5 | $0.00063 | $0.01287 |
| Sonnet 5 | $0.00025 | $0.00515 |
| Haiku 4.5 | $0.00013 | $0.00257 |
Grade A, and why
metadata-lint 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 9d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metadata lint
Audits HTML head metadata against a priority-ordered rule set and proposes minimal, scoped fixes. The output is the audit report — not a refactor, not a strategy doc. Pair with /website-pm-score (broader page audit) or /aeo-strategy (search-visibility strategy) to act on the findings.
Sourced from ibelick/ui-skills under MIT (Julien Thibeaut, 2026). Adapted to the Genesys Phase 4 SKILL.md schema; substantive content preserved.
Design-contract exemption note: This skill carries
primitive: websitebut is NOT a design-output skill (thedesign-production.mdapplies to skills that produce visual deliverables — landing pages, wireframes, dashboards, decks). Metadata-lint produces a text audit report listing HTML head violations and code-level fixes; there is no DESIGN.md token consumption, no visual surface, no design-cycle phases to walk. The validator's design-contract warning is an expected false positive driven by theprimitive: websitetaxonomy heuristic.
Triggers
Run when:
- Adding or changing page titles, descriptions, canonical URLs, robots directives
- Implementing Open Graph or Twitter card metadata
- Setting favicons, app icons, manifest, theme-color
- Building shared SEO components or layout metadata defaults
- Adding structured data (JSON-LD)
- Changing locale, alternate languages, or canonical routing
- Shipping new pages, marketing pages, or shareable links
Do NOT run for:
- Strategic decisions about what TO put in metadata (that's
/aeo-strategyor/messaging) - Whole-page audits — use
/website-pm-scoreinstead; metadata-lint is the head-tags slice
Inputs
| Input | Required | Notes |
|---|---|---|
| HTML file path or live URL | Yes | One target per run; loop the skill for multi-page audits |
| Brand context | Recommended | Read projects/consulting/{client}/CLAUDE.md if reviewing client work — title format + voice should match |
| Existing metadata system | Inferred from code | Next.js metadata API, react-helmet, manual <head>, Astro frontmatter — match the project's pattern |
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.
- 9d ago First seen · 269 lines · 127 tokens per session scan A b2e9da3f0d00
metadata-lint is a skill published in the GitHub repository matteotitta/genesys-skills (36 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 2,573 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 2026-09-03.
Other skills, from other repositories
ui-ux-gtm
Design GTM UI/UX patterns — landing pages (hero, proof, CTA), forms (progressive disclosure, inline validation), signup flows (activation, time-to-value), dashboards (KPI hierarchy, trend indicators), and accessibility (WCAG 2.2 AA). Use when designing or auditing GTM tool interfaces, landing pages, conversion flows…
landing-pages
Audit and optimize landing pages for conversion — hero/offer/proof/CTA patterns, CRO audits, A/B testing, signup flow optimization. Use when the user wants to improve conversion rates, audit a landing page, optimize a signup flow, or increase demo requests. Triggers on: "landing page", "conversion rate", "CRO"…
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.