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/fuyuxiang/echo-agent/ocr-documentnpx skills add fuyuxiang/echo-agent --skill ocr-documentgit clone --depth 1 https://github.com/fuyuxiang/echo-agentWhat 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 | $0.00027 | $0.00483 |
| Opus 5 | $0.00014 | $0.00242 |
| Sonnet 5 | $0.00005 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
ocr-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 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
OCR & Document Processing
Extract text from PDFs, scanned images, and documents.
PDF Text Extraction (PyMuPDF)
Best choice for text-based PDFs:
pip install pymupdf
import pymupdf
doc = pymupdf.open("file.pdf")
for page in doc:
text = page.get_text()
print(text)
# All pages at once
full_text = "\n".join(page.get_text() for page in doc)
PDF → Markdown (marker-pdf)
High-quality conversion preserving structure:
pip install marker-pdf
marker_single file.pdf output_dir/ --output_format markdown
Image OCR
Surya OCR (Modern ML-based, best for Chinese)
pip install surya-ocr
surya_ocr image.png --langs zh,en
Pytesseract (Traditional, widely available)
# Install Tesseract engine first
brew install tesseract tesseract-lang # macOS
apt install tesseract-ocr tesseract-ocr-chi-sim # Linux
pip install pytesseract Pillow
import pytesseract
from PIL import Image
text = pytesseract.image_to_string(
Image.open("scan.png"),
lang="chi_sim+eng"
)
Script
python3 scripts/extract_document.py document.pdf
python3 scripts/extract_document.py scan.png
python3 scripts/extract_document.py report.pdf --output extracted.txt
Auto-detects format by extension: PDF → pymupdf, DOCX → python-docx, Image → pytesseract.
OCR language is controlled by system Tesseract config (e.g., chi_sim+eng default).
Tips
- For scanned PDFs, extract images first then OCR each page
- Preprocessing (deskew, contrast) improves OCR accuracy
- Chinese OCR: surya-ocr > pytesseract for accuracy
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.
- 2d ago First seen · 87 lines · 27 tokens per session scan A d241da684ed9
ocr-document is a skill published in the GitHub repository fuyuxiang/echo-agent (988 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 483 once invoked, about $0.0001 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
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
nano-pdf
Edits PDF files using natural-language instructions via the nano-pdf CLI. Supports modifying text, changing titles, fixing typos, and updating content on specific pages. Use when the user wants to edit a PDF, modify PDF content, update PDF text, fix a typo in a PDF, change a PDF title, or rewrite part of a PDF page.