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 validatedpatterns/docs --skill doc-creategit clone --depth 1 https://github.com/validatedpatterns/docsWrote 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/validatedpatterns/docs/doc-create)<a href="https://agentmods.dev/skills/validatedpatterns/docs/doc-create"><img src="https://agentmods.dev/badge/skills/validatedpatterns/docs/doc-create/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/validatedpatterns/docs/doc-create"><img src="https://agentmods.dev/badge/skills/validatedpatterns/docs/doc-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00132 | $0.01206 |
| Opus 5.5 | $0.00053 | $0.00482 |
| Sonnet 5.5 | $0.00026 | $0.00241 |
| Haiku 4.5 | $0.00013 | $0.00121 |
Grade A, and why
doc-create 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 1mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create new documentation for the validatedpatterns.io Hugo site. Follow the workflow below precisely.
Step 1: Resolve content type and gather inputs
- If
$ARGUMENTSis empty, ask the user what content type (learnorpattern) and topic to create. - If
$ARGUMENTScontains a content type and topic, use them directly.
Learn pages
Collect:
- title (required): Page title in sentence-style capitalization.
- parent menu (optional): If this is a child page, the parent menu label (e.g. "Patterns quick start"). Leave empty for top-level learn pages.
- weight (required): Sort order (10, 20, 30, ...).
- topic summary: Brief description of what the page covers — used to generate content.
Pattern page sets
Collect:
- pattern name (required): Lowercase, dash-separated directory name (e.g.
my-new-pattern). - title (required): Human-readable pattern title.
- date (required): Publication date in
YYYY-MM-DDformat. - summary (required): One-sentence pattern description.
- tier (required):
sandbox,tested, ormaintained. - rh_products (required): List of Red Hat products used.
- industries (required): List of target industries.
- partners (optional): List of partner organizations.
- GitHub repo URL (required): Used to populate
links.githubandlinks.bugs. - Additional subpages (optional): Beyond the standard set (getting-started, cluster-sizing, ideas-for-customization, troubleshooting).
Step 2: Determine format and naming
- Always use AsciiDoc (
.adoc) unless the user explicitly requests Markdown (.md). - File names: lowercase, dash-separated (e.g.
getting-started.adoc,cluster-sizing.adoc). - Pattern directories:
content/patterns/<pattern-name>/with_index.adocand subpages. - Learn pages:
content/learn/<page-name>.adoc.
Step 3: Generate files from templates
Read the applicable reference file before generating content:
- Learn page: Read references/learn-page.md for frontmatter schema, menu hierarchy, and body structure.
- Pattern page set: Read references/pattern-set.md for index frontmatter schema, standard subpages, and body templates.
What ships with it
2 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.
- 1mo ago First seen · 90 lines · 132 tokens per session scan A b1c2815af660
doc-create is a skill published in the GitHub repository validatedpatterns/docs (20 stars, last pushed 2d ago), licensed Apache-2.0. It adds 132 tokens to every session and 1,206 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
review-doc
Reviews a docs.page page against writing checks (failing, passing, muted), prints a results table, and applies unmuted findings by default so the publisher can review the diff. Loops until failing is 0, or until only heading rewrites that would change an anchor slug remain (those wait for accept). Use when the…
Folio Content
How to write page markdown that Folio renders correctly and that stays readable as plain markdown on GitHub — syntax cheat sheet, page templates, and anti-patterns.
Folio Forms
Build and change Folio forms (kind form) with createform / updateform — fields, types, the paired data table where the answers land, public forms.
Folio Bases
Read and write Obsidian Bases (kind base) — saved queries over the pages of a space — with querybase and savebase; filters, formulas, views, an example.
atlas-report
Render agent findings as a styled HTML report in the browser. Use when asked for "full report", "detailed report", "show in browser", or when CLI output exceeds the 40-line budget.
slides-to-pdf
Use when the user asks to convert, export, or save an HTML slide deck as a PDF ("save the slides as PDF", "export the deck to PDF", "make a PDF of the presentation"). Works on decks built by the SlideOps (slideops) skill and on any single-file HTML deck that shows one slide per URL hash (#1.