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.
git clone --depth 1 https://github.com/deepread-tech/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/plugins/deepread-tech/skills/deepread)<a href="https://agentmods.dev/plugins/deepread-tech/skills/deepread"><img src="https://agentmods.dev/badge/plugins/deepread-tech/skills/deepread/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/plugins/deepread-tech/skills/deepread"><img src="https://agentmods.dev/badge/plugins/deepread-tech/skills/deepread.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
deepread 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 5d 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": "deepread",
"description": "DeepRead — AI-native document processing API with 97%+ accuracy. Extract text and structured data from PDFs and images, fill PDF forms with AI vision, redact 14 types of PII (HIPAA/GDPR ready), and Bring Your Own Key for zero LLM costs. Includes pre-built schemas for invoices, medical records, legal contracts, and insurance claims. Free 2,000 pages/month.",
"version": "4.0.0",
"source": "./",
"homepage": "https://www.deepread.tech",
"repository": "https://github.com/deepread-tech/skills",
"license": "MIT-0",
"keywords": [
"ocr",
"pdf",
"document-processing",
"pii",
"form-fill",
"byok",
"ai",
"invoice",
"medical",
"legal",
"insurance",
"extraction",
"redaction"
],
"category": "data-processing",
"strict": false,
"skills": [
"./skills/setup",
"./skills/api",
"./skills/byok",
"./skills/form-fill",
"./skills/pii",
"./skills/invoice",
"./skills/medical",
"./skills/legal",
"./skills/insurance"
]
}What it installs
The manifest is a name and a version. 9 skills travel with it, and installing the plugin installs all of them — 431 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill deepread-api A 47 tokens
- Skill deepread-pii A 0 tokens
- Skill deepread-form-fill A 60 tokens
- Skill deepread-insurance A 59 tokens
- Skill deepread-invoice A 55 tokens
- Skill deepread-legal A 55 tokens
- Skill deepread-medical A 58 tokens
- Skill deepread-setup A 42 tokens
- Skill deepread-byok A 55 tokens
What ships with it
2 files beside marketplace.json#deepread 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.
- 5d ago First seen · 37 lines scan A f012f86e0257
deepread is a plugin published in the GitHub repository deepread-tech/skills (4 stars, last pushed today), 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 2026-09-12.
Other plugins, from other repositories
kolmopdf
High-fidelity PDF to Markdown parsing, layout-preserving PDF translation, and Markdown→DOCX/HTML/PDF/LaTeX conversion. Handles formulas, tables, and multi-column layouts that the built-in Read tool struggles with.
document-skills
Create, edit, and analyze PDF, Word, PowerPoint, and Excel files.
deckprobe
Inspect PDF, Microsoft Office, and Apple iWork documents with bounded, deterministic probes.
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.
carrel-documents
Document craft with the carrel CLI: /redact, /sign, /form, /proof, /color, a document-clerk agent (redact → verify → sign manifest) and a redaction-and-provenance skill.
pdf-scan-audit
A tool for checking the quality of scanned PDF files. It looks for missing or misordered pages, incorrect rotation, cropped content, and resolution problems, then reports the results in a table.