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 CodeInfinity1/Stram --skill ocr-document-extractiongit clone --depth 1 https://github.com/CodeInfinity1/StramWrote 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/codeinfinity1/stram/ocr-document-extraction)<a href="https://agentmods.dev/skills/codeinfinity1/stram/ocr-document-extraction"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/ocr-document-extraction/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/codeinfinity1/stram/ocr-document-extraction"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/ocr-document-extraction.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 | $0.00030 | $0.00419 |
| Opus 5.5 | $0.00012 | $0.00168 |
| Sonnet 5.5 | $0.00006 | $0.00084 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
ocr-document-extraction 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
OCR Document Extraction
Purpose
Handle scanned documents carefully. OCR is error-prone and sensitive, so the assistant must use native OCR support when available or clearly report the implementation gap.
When To Use
Use for scans, images of documents, receipts, screenshots, forms, and PDFs where normal text extraction fails.
Inputs And Evidence
- Image/PDF path, target fields, language, table requirements, and confidence needs.
- Existing extraction errors or screenshot metadata.
Tool Map
read_pdfocr_provider_statusscreenshot_capturescreen_capturespython_interpretertool_searchwrite_note
Workflow
- Try native text extraction when the input is a PDF.
- Run
ocr_provider_statusbefore claiming OCR. - If OCR providers are missing, describe the exact local setup needed or use approved interpreter packages if available.
- Extract fields with confidence/uncertainty labels.
- Preserve source page/image references.
- Verify critical numbers manually where possible.
Native Implementation Boundaries
- Do not import external reference OCR or upstream document scripts directly.
- OCR adapters must be Stram-owned and tested; readiness checks do not equal extraction.
- Upstream OCR workflows are reference only.
Safety And Approval
- Documents may include IDs, financials, or private data.
- Do not send images to cloud OCR without explicit user approval.
- Avoid storing sensitive extractions as memory unless requested.
Verification
- Distinguish native text extraction, OCR readiness, and OCR extraction.
- Report confidence and uncertain fields.
- Confirm output notes/artifacts.
Failure Modes
- Treating OCR output as exact.
- Missing table structure.
- Claiming OCR ran when only PDF text extraction ran.
References
- Shortlist item:
ocr-document-extraction.
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 · 67 lines · 30 tokens per session scan A c6ae21b2f58b
ocr-document-extraction is a skill published in the GitHub repository CodeInfinity1/Stram (11 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 419 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
omh-long-document-reading
This is a Hermes-native long-document-reading workflow skill.
omh-report-package
This is an OMH report-package workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
Generate, inspect, assemble, and render vector-quality PDF documents with precise page geometry, print typography, page breaks, and PDF/A standards. Use when generating downloadable reports, invoices, printable whitepapers, combining PDF pages, or rendering HTML to vector PDF.
product-spec-pdf-parser
Extract sourced FF&E specifications from supplied product PDFs into reviewable structured data. Use for fact sheets, spec sheets and price books; not web-page capture, EPD extraction or automatic schedule adoption.
epd-parser
Extract GWP, life-cycle stages, certifications, and impact metrics from an EPD PDF. Use when given a declaration to parse; not to find or compare EPDs.
bib-parse
Extract citations from a PDF and generate a validated .bib file. Use when the user asks to extract citations from a PDF and generate a validated .bib file. Reads the PDF, identifies referenced works, constructs BibTeX entries, and verifies metadata.