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 2362094903-ops/study-assistant-skills --skill study-imggit clone --depth 1 https://github.com/2362094903-ops/study-assistant-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/2362094903-ops/study-assistant-skills/study-img)<a href="https://agentmods.dev/skills/2362094903-ops/study-assistant-skills/study-img"><img src="https://agentmods.dev/badge/skills/2362094903-ops/study-assistant-skills/study-img/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/2362094903-ops/study-assistant-skills/study-img"><img src="https://agentmods.dev/badge/skills/2362094903-ops/study-assistant-skills/study-img.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 | $0.00084 | $0.00624 |
| Opus 5 | $0.00042 | $0.00312 |
| Sonnet 5 | $0.00017 | $0.00125 |
| Haiku 4.5 | $0.00008 | $0.00062 |
Grade B, and why
study-img scanned grade B with 1 finding 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 9d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
First-use configuration: ask for provider type, base URL/API key, and vision model. Store config in `~/.config/study-img/config.json`, `chmod 600`, and never repeat the full API key in conversation. How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Study Image Reading
Output language: ALL learner-facing content MUST be Simplified Chinese.
Try native vision first
Use the available image-reading capability directly when possible.
- If you can see the image, produce the required mode output below.
- If image reading fails or the model has no vision, use the external vision API script.
One failed native attempt per session is enough evidence; do not retry every image.
External vision API
python3 ~/.claude/skills/study-img/scripts/recognize.py <image> --mode <mode>
First-use configuration: ask for provider type, base URL/API key, and vision model. Store config in ~/.config/study-img/config.json, chmod 600, and never repeat the full API key in conversation.
Modes
| Scenario | Mode | Required output |
|---|---|---|
| Scanned textbook page / photographed paper / handout | --mode ocr |
Structured Markdown transcription; formulas as LaTeX; figures as [图：...] placeholders with enough detail to locate them. |
| Textbook/courseware figure, coordinate plot, table image, flowchart, chart | --mode figure |
Teaching-grade description complete enough to redraw or convert into a lecture figure/table. Include axes, labels, variables, trends, data rows, and the conclusion. |
| Learner handwritten answers | --mode answer |
Verbatim transcription; preserve errors; LaTeX formulas; use 【?】 for illegible characters. |
| Unsure | no mode | Comprehensive recognition. |
Workflow hookups
- Scanned PDFs: render flagged pages with
extract_pdf.py --render-scanned, recognize, and merge intointernal/textbook/chapter-XX.md. - Image-heavy PPT slides: export with
extract_pptx.py --render-images, recognize, and merge intointernal/textbook/chapter-XX.md. - Lecture figures: when a
[图：...], chart, curve, or table is important for understanding, recognize it with--mode figure; then study-teach must include the useful visual/table/formula in the lecture JSON withsource_ref. - Handwritten answer grading: transcribe with
--mode answer, show uncertain parts to the learner, then hand to study-quiz for grading.
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.
- 9d ago First seen · 47 lines · 84 tokens per session scan B d9c2648a6c4e
study-img is a skill published in the GitHub repository 2362094903-ops/study-assistant-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 624 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-tutor
Turn any coding agent into a structured personal tutor with a markdown knowledge vault. Interviews the learner to build a personal learning profile (how they think, which explanations they receive best, tone and pace preferences), builds a phased plan shaped by that profile, writes complete lesson notes in the…
agent-tutor-visualize
Build diagrams and visual explanations for learning notes - Mermaid diagram selection and syntax rules plus SVG illustration guidelines for lesson notes in a markdown vault. Use when a concept needs a picture such as flows, hierarchies, timelines, comparisons, or spatial layouts, and when creating or embedding…
agent-tutor-review
Spaced-repetition review sessions and retention tracking for subjects learned with the agent-tutor skill. Recall-first practice over lesson notes, adaptive FSRS-style interval scheduling (uncapped by default), honest retention verdicts, and a mixed mini-quiz per session. Use when the user wants to revise or practice…
doceo
Turn anything the user wants to learn into a short, visual, plain-language teachable artifact (one HTML lesson page + a markdown lesson note), calibrated to what they already know and improving with every use. Use when the user runs /doceo, says "teach me X", "I don't understand X", "explain this simply", "make this…
knowledge-point-tree
Build a flat, exhaustive "point tree" of every enumerable knowledge point in a bounded body of material (a textbook, a certification syllabus, a spec, an API surface, a legal code), so a learner facing a brand-new field can see the whole board at once instead of drowning in unknown unknowns. Use this whenever someone…
codetrain
Use when the user wants to be taught/walked through code one tiny step at a time — triggers like "teach me this code", "walk me through this", "hold my hand", "explain step by step", "tutor me", "guide me through", "I want to learn this", or asks for a safe practice exercise to learn a concept.