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/opensearch-project/opensearch-agent-skills/document-processingnpx skills add opensearch-project/opensearch-agent-skills --skill document-processinggit clone --depth 1 https://github.com/opensearch-project/opensearch-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/opensearch-project/opensearch-agent-skills/document-processing)<a href="https://agentmods.dev/skills/opensearch-project/opensearch-agent-skills/document-processing"><img src="https://agentmods.dev/badge/skills/opensearch-project/opensearch-agent-skills/document-processing.svg" alt="Measured on agentmods" 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 | $0.00087 | $0.00382 |
| Opus 5 | $0.00044 | $0.00191 |
| Sonnet 5 | $0.00017 | $0.00076 |
| Haiku 4.5 | $0.00009 | $0.00038 |
Grade A, and why
document-processing 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
Document Processing
Process unstructured documents into search-ready JSONL chunks using Docling (open-source, runs locally). No AWS credentials or cloud services needed.
Prerequisites
uvinstalled (for running Python scripts)
When to Use
- User has unstructured documents (PDF, DOCX, PPTX, XLSX)
- User wants to prepare documents for OpenSearch indexing
- User wants to inspect or evaluate chunk quality
Output
JSONL files at .opensearch/chunks/<index>/<filename>.jsonl. Each line:
{"text": "...", "headings": ["Section Title"], "source_file": "doc.pdf", "chunk_id": 0, "page_number": 1}
The JSONL output can be ingested into any OpenSearch target:
- Local cluster — bulk-index directly
- AOS domain / AOSS collection — via managed-ingestion-service (OSIS pipeline)
Reference
See document_processing_guide.md for the full workflow: processing profiles, quality evaluation, and chunking adjustments.
What ships with it
1 file 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.
- 5d ago First seen · 44 lines · 87 tokens per session scan A 570a4af3109e
document-processing is a skill published in the GitHub repository opensearch-project/opensearch-agent-skills (50 stars, last pushed 16d ago), licensed Apache-2.0. It adds 87 tokens to every session and 382 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
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
markdown-converter
Markdown conversion: PDF, Office, HTML, data, OCR, audio, ZIP, YouTube.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
unified-deliverable-workflow
Generate spreadsheets, diagrams, and PDF reports with iteration budgeting and error recovery.
document-python-direct-exec
Use direct Python execution for reliable spreadsheet and document/PDF generation operations.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.