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 levi-qiao/sherlock-claude --skill printer-xmlgit clone --depth 1 https://github.com/levi-qiao/sherlock-claudeWrote 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/levi-qiao/sherlock-claude/printer-xml)<a href="https://agentmods.dev/skills/levi-qiao/sherlock-claude/printer-xml"><img src="https://agentmods.dev/badge/skills/levi-qiao/sherlock-claude/printer-xml.svg" alt="Measured on agentmods" 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 | $0.00112 | $0.07060 |
| Opus 5 | $0.00056 | $0.03530 |
| Sonnet 5 | $0.00022 | $0.01412 |
| Haiku 4.5 | $0.00011 | $0.00706 |
Grade B, and why
printer-xml scanned grade B with 1 finding 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 8d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
### `<script>` — Execute arbitrary script code How it starts
The opening of the file, as written. The whole thing — 677 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Printer-X XML Template Guide
This guide covers how to write XML templates for the gaia-printer-x PDF rendering engine. The engine parses the XML, evaluates expressions, runs scripts, and renders each element onto a PDF page.
Document Structure
Every template has three top-level sections inside the root element.
The root element name is arbitrary (e.g., <proposal>, <document>, <report>).
<proposal>
<!-- 1. Font mappings -->
<font_mapping>
<font name="arial" value="ARIAL"/>
<font name="arialbd" value="ARIALBD"/>
<font name="tahoma" value="TAHOMA_EPOS"/>
<font name="hei" value="SIMHEI"/>
</font_mapping>
<!-- 2. Page definitions -->
<page_setting>
<page name="A4" size="epos_A4" x="0" y="0" width="2100" height="2970">
<!-- Optional page template (background applied to every paragraph using this page) -->
<template x="0" y="0" width="2100" height="2970">
<image src="'bg.jpg'" x="0" y="0" width="2100" height="2970"/>
</template>
</page>
</page_setting>
<!-- 3. Content paragraphs (one per page) -->
<paragraph page="A4">
<!-- elements -->
</paragraph>
<paragraph page="A4">
<!-- elements for second page -->
</paragraph>
</proposal>
Page Sizes
| Size name | Width × Height (units) | Notes |
|---|---|---|
epos_A4 |
2100 × 2970 | Standard A4 |
A4 |
2100 × 2970 | Same as epos_A4 |
A4Rotate |
2970 × 2100 | A4 landscape |
A3 |
2970 × 4200 | A3 portrait |
epos_A4Rotate |
2970 × 2100 | A4 landscape variant |
1 unit ≈ 0.1 mm. A4 at 2100 wide means 210 mm wide.
Elements Reference
<text> — Render text
<text x="100" y="200" width="800" height="50"
font="arial" font_size="28" color="black"
bold="true" align="center"
value="value.userName"/>
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.
- 8d ago First seen · 677 lines · 112 tokens per session scan B ada5ea5dc1a8
printer-xml is a skill published in the GitHub repository levi-qiao/sherlock-claude (6 stars, last pushed 4mo ago), licensed MIT. It adds 112 tokens to every session and 7,060 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
pdf-text-extraction-fallback-85d5ca
Fallback workflow for extracting text from PDFs when readfile returns binary data.