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.
/plugin marketplace add appautomaton/document-SKILLsnpx agentmods add plugins/appautomaton/document-skills/marketplacegit clone --depth 1 https://github.com/appautomaton/document-SKILLsGrade A, and why
appautomaton-skills marketplace 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 3d 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.
What it actually says
{
"name": "appautomaton-skills",
"owner": {
"name": "BP",
"email": "[email protected]"
},
"metadata": {
"description": "Document processing skills for Claude Code",
"version": "1.0.0"
},
"plugins": [
{
"name": "document-skills",
"description": "Create, edit, and analyze PDF, Word, PowerPoint, and Excel files",
"source": "./",
"strict": false,
"skills": [
"./pdf",
"./docx",
"./pptx",
"./xlsx"
]
}
]
}
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.
- 3d ago First seen · 26 lines scan A 16500f03d382
appautomaton-skills marketplace is a plugin published in the GitHub repository appautomaton/document-SKILLs (156 stars, last pushed 16d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
deckprobe
Inspect PDF, Microsoft Office, and Apple iWork documents with bounded, deterministic probes.
ade-document-processing
Agent skill for LandingAI's Agentic Document Extraction (ADE): production-ready document AI with 99%+ accuracy. Parse, extract, and classify documents through the ADE REST APIs or the Python and TypeScript libraries, with full auditability and traceability.
mineru
Parse PDF / Office / image files into clean Markdown via MinerU — zero-dependency, AI-Native, auto-routing between the free Agent API and the token-gated Standard API, with 15 content-tool delivery sinks.
deepread
DeepRead OCR — extract text and structured data from PDFs and images with 97%+ accuracy. Includes setup, API reference, PII redaction, form filling, and BYOK.
md-anything
Convert any file, URL, or media to clean Markdown — PDF, EPUB, HTML, images, YouTube, audio, video, and more.
pdf-guard
Prevents PDF context crashes with extraction enforcement and cumulative read tracking.