Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/terrylica/cc-skillsnpx agentmods add skills/terrylica/cc-skills/unlimited-ocr-parse-documentWrote 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/terrylica/cc-skills/unlimited-ocr-parse-document)<a href="https://agentmods.dev/skills/terrylica/cc-skills/unlimited-ocr-parse-document"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/unlimited-ocr-parse-document/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/terrylica/cc-skills/unlimited-ocr-parse-document"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/unlimited-ocr-parse-document.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 | $0.00189 | $0.02007 |
| Opus 5.5 | $0.00076 | $0.00803 |
| Sonnet 5.5 | $0.00038 | $0.00401 |
| Haiku 4.5 | $0.00019 | $0.00201 |
Grade A, and why
unlimited-ocr-parse-document 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unlimited-OCR — parse a document locally
baidu/Unlimited-OCR (MIT, arXiv 2606.23050) is a 3B-total /
500M-activated MoE document parser. It reads a page image and returns markdown with LaTeX
mathematics, tables, and a <|det|> bounding box for every block it found.
Self-Evolving Skill: improves through use. Every number below was MEASURED on this hardware, not copied from a README — provenance in
../../references/EMPIRICAL.md. If a measurement drifts, a flag stops working, or a new failure mode appears, fix this file and the references immediately rather than deferring. Re-verify before changing a documented fact.
The one rule: Free OCR. is the only prompt mode that works
Of the three prompt modes the upstream project documents, two are broken on MLX and both are refused by this CLI with exit 2 and a printed reason:
| Mode | Measured behaviour |
|---|---|
free-ocr |
works — correct output with layout boxes in 2.4 s. The default. |
document-parsing |
decodes parsing.parsing.parsing… until max_tokens. This is the prompt the upstream README documents. |
multi-page |
deterministically hallucinates the word industrydocuments onto a single image. |
--allow-withheld-prompt-mode forces one anyway. They are kept nameable rather than deleted so the
failures stay reproducible.
This CLI sends one image per forward pass, always. The model's headline multi-page capability is deliberately unused — a five-page single-pass run dropped a page with no error, which is the worst failure mode there is for an archive. Per-page is slower and verifiable.
Use it
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.
- 8d ago First seen · 153 lines · 189 tokens per session scan A 45ccd02b58ff
unlimited-ocr-parse-document is a skill published in the GitHub repository terrylica/cc-skills (0 stars, last pushed today), licensed MIT. It adds 189 tokens to every session and 2,007 once invoked, about $0.0008 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 2026-10-08.
Other skills, from other repositories
transcript-to-pdf
Convert a GuideAnts / Code-Executor markdown conversation transcript into a styled, print-ready PDF with a cover page, role-badged turns, full tool-call inputs (heredoc-aware) and highlighted code. Use when the user wants to export, archive, or share a conversation log as a polished PDF document.
data-export
Generates data export/import infrastructure for JSON, CSV, PDF formats with GDPR data portability, share sheet integration, and file import. Use when user wants data export functionality, CSV/JSON/PDF export, GDPR compliance data portability, import from files, or share sheet for data.
document-skills
Professional document creation, editing, and analysis for Office formats (docx, pdf, pptx, xlsx). Use when working with Word documents, PDFs, PowerPoint presentations, or Excel spreadsheets.
recipe-bulk-download-folder
List and download all files from a Google Drive folder.
gws-drive-upload
Google Drive: Upload a file with automatic metadata.
document-processor
Activates DocumentProcessor for intelligent processing of Word, PDF, PowerPoint, and Excel files. Use when you need to extract, summarize, redline, or transform documents in any Office format — compare versions, extract tables, generate document outlines, convert formats, or produce structured data from unstructured…