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/optimeta/paideia/vision-ocrnpx skills add OPTIMETA/PAIDEIA --skill vision-ocrgit clone --depth 1 https://github.com/OPTIMETA/PAIDEIAWrote 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/optimeta/paideia/vision-ocr)<a href="https://agentmods.dev/skills/optimeta/paideia/vision-ocr"><img src="https://agentmods.dev/badge/skills/optimeta/paideia/vision-ocr.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 | $0.00100 | $0.02061 |
| Opus 5 | $0.00050 | $0.01030 |
| Sonnet 5 | $0.00020 | $0.00412 |
| Haiku 4.5 | $0.00010 | $0.00206 |
Grade B, and why
vision-ocr scanned grade B with 2 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- ❌ Don't pass base64 via `curl -d <arg>` — ARG_MAX overflow. Use stdlib `urllib` with POST body. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- ❌ Don't pass base64 via `curl -d <arg>` — ARG_MAX overflow. Use stdlib `urllib` with POST body. How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vision-OCR
When to load
/gradeneeds to convertanswers/*.pdf→answers/converted/*.md- Any hand-written / scanned document whose previous tesseract pass was garbled
answer-processingskill's step-2 conversion
Engine choice
.course-meta holds a single line OCR_ENGINE: <engine> written by /paideia:init-course. The grade command reads it and dispatches. Users can override per-call with /paideia:grade --ocr=<engine> [path].
| Engine | Default? | How it runs | When to pick it |
|---|---|---|---|
claude |
Yes | pdftoppm → Claude reads each PNG via the Read tool → synthesizes markdown inline. No external model. No subprocess. |
The out-of-the-box path. Nothing to install. Highest fidelity on messy handwriting because Claude vision handles mixed-script (English/Korean) prose with LaTeX well. |
ollama |
opt-in | python3 ${CLAUDE_PLUGIN_ROOT}/scripts/vision_ocr.py --engine=ollama <pdf> <md> — local Qwen3-VL 8B, with an automatic tesseract fall-back if ollama is unreachable. Reads INTERFACE_LANG from .course-meta to set the prose-language rule. |
You want the PDF to never leave the machine and you don't want to burn Claude tokens on OCR. Requires one-time ollama pull qwen3-vl:8b (~6 GB). |
tesseract |
opt-in | python3 ${CLAUDE_PLUGIN_ROOT}/scripts/vision_ocr.py --engine=tesseract <pdf> <md> — pytesseract (eng for en, eng+kor for ko, derived from .course-meta). |
Zero cloud + no GPU/VRAM budget. Lowest fidelity on handwriting; fine for typed scans. |
All three emit answers/converted/<stem>.md with a <!-- SOURCE: ... --> / <!-- TIER: ... --> header comment that lets /grade caveat the confidence.
Tier 0 — Claude native vision (default)
Pipeline (driven by the /grade command, not this script):
answers/<stem>.pdf
↓ pdftoppm -r 200 -png <pdf> <tmpdir>/page # rasterize to PNG per page
↓ Claude reads <tmpdir>/page-1.png, page-2.png, ... via the Read tool
↓ Claude synthesizes clean MD following the prompt contract below
answers/converted/<stem>.md
└── header: <!-- SOURCE: <stem>.pdf, claude-vision (native), N pages -->
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 · 134 lines · 100 tokens per session scan B 22b3c0bb7498
vision-ocr is a skill published in the GitHub repository OPTIMETA/PAIDEIA (91 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 2,061 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
final-review
期末一键复习。考前72小时，把课件(PPT)、课堂笔记、阅读材料、PDF、图片、扫描件等多模态资料自动发现→多模态归一化→逐章分类整合→生成可打印的逐章期末复习稿PDF。面向期末突击党和中英双语课程学生。Use when user mentions anything about organizing or generating final-exam review materials — "期末复习", "考前冲刺", "考前72小时", "期末突击", "整理复习资料", "一键复习", "帮我整理XX课复习", "生成XX课复习", "把课件整理成复习", "把笔记整理成复习", "PPT转复习", "PDF复习"…
note-single-lecture
Create high-fidelity study notes for one lecture PDF/PPT using a generated mind map first. Store intermediate artifacts in note-single-lecture-work/ / and final notes in note-single-lecture/. Write descriptive prose mainly in Chinese, preserve key English terms and important English descriptive source sentences, and…
closed-book-full-course-highlights
Produce page-ordered highlight summaries for all lecture PDFs in a course, marking multi-page topics as high-priority. Use for closed-book full-course review, 全课要点, examlecturestat, complete slide coverage reports, or closed-book-full-course-highlights.
closed-book-single-lecture-analysis
Perform in-depth analysis of one or more lecture PDFs with logic reordering and tiered depth by topic frequency. Use for closed-book single-lecture study, 单讲分析, conceptual deep dives, batch continuation across lecture numbers, or closed-book-single-lecture-analysis.
open-book-layered-index
Construct hierarchical open-book exam indexes that map topics to lecture PDF file names and page numbers. Use for open-book revision, 开卷索引, revisionexam.md, course map, slide page lookup, or open-book-layered-index without explanatory prose.
note-organizer
Use this skill whenever the user wants to organize course materials, lecture notes, PPT/PDF/DOCX files, textbooks, personal notes, senior-student notes, historical exams, review questions, standards, manuals, or scattered study resources into a structured Markdown note library. Use it even when the user only says…