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 agentmods add skills/renefichtmueller/papercortex/skillnpx skills add renefichtmueller/PaperCortex --skill skillgit clone --depth 1 https://github.com/renefichtmueller/PaperCortexWhat 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 | $0.00000 | $0.00444 |
| Opus 5 | $0.00000 | $0.00222 |
| Sonnet 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 2d 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.
- 2d ago First seen · 73 lines · 0 tokens per session scan A 6280c4b40aa2
skill is a skill published in the GitHub repository renefichtmueller/PaperCortex (25 stars, last pushed 1mo 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
extracting-keywords
Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting document language or generating embeddings for RAG and search. Covers the keyword config (and its feature gating), --detect-language, and the standalone embed command with real flags.
chunking-embeddings
Chunking, embeddings, and RAG pipeline integration.
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.
format-specific-extraction
Format-specific document extraction workflows.
extraction-pipeline-patterns
Change or diagnose Xberg's core extraction orchestration, cache semantics, extractor fallback, post-processing, concurrency defaults, or format-wide quality invariants. Load for pipeline work, not a single parser's syntax.
api-server-mcp
REST API server and MCP protocol integration.