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 moonlight-lupin/agent-skills --skill document-convertergit clone --depth 1 https://github.com/moonlight-lupin/agent-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/moonlight-lupin/agent-skills/document-converter)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/document-converter"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/document-converter/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/moonlight-lupin/agent-skills/document-converter"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/document-converter.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 | $0.00072 | $0.02170 |
| Opus 5 | $0.00036 | $0.01085 |
| Sonnet 5 | $0.00014 | $0.00434 |
| Haiku 4.5 | $0.00007 | $0.00217 |
Grade A, and why
document-converter 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 10d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Converter
Overview
Use this skill when you need to convert common document and data formats while preserving as much structure as the source format allows. The bundled CLI covers lightweight, local conversions between Markdown, HTML, CSV, JSON, YAML, TOML, plain text, Excel, and PDF output.
The core conversions use the Python standard library: JSON, CSV, HTML parsing, Markdown heuristics, TOML reading via tomllib, and custom TOML/YAML writers. PDF output uses pandoc and Excel reading uses openpyxl — both are required dependencies for those conversion paths. If a dependency is missing, the tool exits with a clear installation hint instead of failing with a traceback.
Conversion matrix
| From | To | Command shape | Dependency | Notes |
|---|---|---|---|---|
| Markdown | HTML | --from markdown --to html |
stdlib | Headers, paragraphs, lists, fenced code, bold/italic/code, links. |
| HTML | Markdown | --from html --to markdown |
stdlib | Common block/inline tags; complex CSS/layout is discarded. |
| HTML | text | --from html --to text |
stdlib | Strips tags, decodes entities, preserves paragraph/list breaks. |
| CSV | JSON | --from csv --to json |
stdlib | Header row becomes object keys; values remain strings. |
| JSON | CSV | --from json --to csv |
stdlib | Flattens nested objects with dot notation; arrays are JSON strings. |
| CSV | Markdown | --from csv --to markdown |
stdlib | Produces a GitHub-style pipe table. |
| Markdown | CSV | --from markdown --to csv |
stdlib | Reads the first pipe table. |
| YAML | JSON | --from yaml --to json |
stdlib fallback; PyYAML optional | Basic YAML only without PyYAML. |
| JSON | YAML | --from json --to yaml |
stdlib | 2-space YAML, no anchors. |
| YAML | TOML | --from yaml --to toml |
stdlib fallback; PyYAML optional | Single YAML document; TOML-compatible values only. |
| TOML | YAML | --from toml --to yaml |
stdlib | TOML tables become nested YAML mappings. |
| TOML | JSON | --from toml --to json |
Python 3.11+ tomllib |
TOML dates/times become strings for JSON. |
| JSON | TOML | --from json --to toml |
stdlib | Strings, numbers, bools, arrays, and nested tables. |
| XLSX | CSV | --from xlsx --to csv |
openpyxl | Reads the first worksheet only. |
| Markdown | --from markdown --to pdf |
pandoc | Write-only PDF target; requires --output. |
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.
- 10d ago First seen · 153 lines · 72 tokens per session scan A e57bf4bda098
document-converter is a skill published in the GitHub repository moonlight-lupin/agent-skills (60 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 2,170 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
document-converter-suite
Convert local PDF, Office, Markdown, HTML, text, CSV, TSV, and JSON files; batch-convert folders, extract tables, fill templates, and edit PDF pages.
Create, inspect, extract, merge, split, rotate, and render PDF files with local open-source tools, including structural and visual verification.
pptx
Create, inspect, extract, edit, render, and verify PowerPoint presentations with python-pptx and optional LibreOffice.
rylai-ppt
Create editable PowerPoint decks from a local JSON specification using Rylai's visual system, python-pptx, deterministic slide types, and optional rendering.
docx
Create, inspect, edit, and verify Word DOCX files with python-docx, including Markdown conversion, text replacement, metadata inspection, and optional PDF render.
markdown-converter
Convert local PDF, Office, HTML, text, data, image, archive, or audio files to Markdown through MarkItDown with guarded input and overwrite handling.