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 renefichtmueller/PaperCortex --skill skillgit clone --depth 1 https://github.com/renefichtmueller/PaperCortexWrote 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/renefichtmueller/papercortex/skill)<a href="https://agentmods.dev/skills/renefichtmueller/papercortex/skill"><img src="https://agentmods.dev/badge/skills/renefichtmueller/papercortex/skill/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/renefichtmueller/papercortex/skill"><img src="https://agentmods.dev/badge/skills/renefichtmueller/papercortex/skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00444 |
| Opus 5.5 | $0.00000 | $0.00178 |
| Sonnet 5.5 | $0.00000 | $0.00089 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
skill 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.
What it actually says
PaperCortex -- Document Intelligence Skill
A Claude Code skill for interacting with your Paperless-ngx document archive through AI-powered semantic search, classification, receipt extraction, and accounting export.
Prerequisites
- PaperCortex MCP Server running (see project README)
- Paperless-ngx instance with API access
- Ollama with
qwen2.5:14bandnomic-embed-textmodels
Available Tools
papercortex_search
Search documents by meaning, not just keywords.
Search for: "office lease agreements from last year"
Search for: "tax-relevant receipts over 500 EUR"
Search for: "correspondence with insurance companies"
papercortex_classify
Auto-classify a document with AI-suggested tags, type, and correspondent.
Classify document #1234
Classify document #1234 and apply suggested tags
papercortex_receipt
Extract structured data from receipt documents.
Extract receipt from document #5678
Returns: vendor, date, amounts, tax breakdown, line items, category.
papercortex_query
Ask natural language questions about your document archive.
"How much did I spend on office supplies in Q1 2024?"
"Which invoices are still unpaid?"
"Summarize all contracts expiring this year"
papercortex_export
Export receipt data for accounting software.
Export documents #100, #101, #102 as DATEV CSV
Export documents #200, #201 as generic CSV
Workflow Examples
Monthly Bookkeeping
- Search for all receipts from the current month
- Extract data from each receipt
- Export as DATEV CSV
- Import into accounting software
Document Organization
- Find unclassified documents (no tags)
- Auto-classify each document
- Review and approve suggested tags
Expense Analysis
- Query: "What were my top 5 expense categories last quarter?"
- Drill into specific categories with follow-up queries
- Export relevant receipts for documentation
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 · 73 lines · 0 tokens per session scan A 6280c4b40aa2
skill is a skill published in the GitHub repository renefichtmueller/PaperCortex (30 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 444 tokens. 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
xberg
Extract text, tables, metadata, and images from 107 document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg. Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format)…
xberg-extracting-tables
Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.
format-specific-extraction
Format-specific document extraction workflows.
xberg-batch-extraction
Use when extracting from many files at once with shared config, bounded parallelism, per-file overrides, and error recovery. Covers the batch command, --file-configs, --max-concurrent, and output layout.
xberg-picking-a-format
Use when choosing an output format for extracted documents — plain text, markdown, djot, HTML, JSON, or DocTags. Maps consumer (LLM, parser, archive) to the right --format / --content-format pair.
feature-flag-policy
Cargo feature flags for crates/xberg — ORT-incompatible targets (WASM, Android x8664 emulator), type-only and tract inference companion features, WASM/Android-safe variants, PDF backend, mutually-exclusive ORT variants, platform-conditional deps, aggregate feature sets, and build profiles. Load when adding, wiring, or…