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 yha9806/academic-writing-toolkit --skill readgit clone --depth 1 https://github.com/yha9806/academic-writing-toolkitWrote 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/yha9806/academic-writing-toolkit/read)<a href="https://agentmods.dev/skills/yha9806/academic-writing-toolkit/read"><img src="https://agentmods.dev/badge/skills/yha9806/academic-writing-toolkit/read/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/yha9806/academic-writing-toolkit/read"><img src="https://agentmods.dev/badge/skills/yha9806/academic-writing-toolkit/read.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.01089 |
| Opus 5 | $0.00015 | $0.00544 |
| Sonnet 5 | $0.00006 | $0.00218 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
read 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 yesterday.
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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/read — Academic PDF Reading Skill
Core Principle
Display first, restrain expansion. Show the page content, provide a terms glossary, give a brief summary and thesis connections. Do not auto-expand, auto-search, or auto-record unless the user explicitly asks. The reader controls the pace and direction.
Trigger Words
This skill activates on: read, next page, continue, skip to p.N, read p.N, /read.
PDF limits
Both are enforced in the dsh app and advisory as a plain Agent Skill. Say which one you are in rather than asserting either.
- Maximum 15 pages per invocation. In the app a wider range is denied
before it runs, with
PAGE_RANGE_EXCEEDED. - Maximum 90 pages per session — a context-health budget, counted in the
app from successful reads folded out of the session log, and denied with
PAGE_BUDGET_EXCEEDED. It counts what went through the harness; reading done outside it is invisible to the count. The fold counts calls, not distinct pages, so re-reading a page you already read spends the budget again — say so before repeating a range. - Outside the app nothing counts for you: the limits are a rule you follow imperfectly, and you should not present the budget as tracked.
- When a request approaches the budget, say so and suggest a new session.
Workflow
- Identify the PDF. If the user provides a path, use it directly. If the user names an author or title, search the project's
literature/directory using Glob to locate the file. - Read the specified page(s). In the dsh app call the
read_pdftool —file_path,first_page,last_page— which is the surface the page guards decide on. As a plain Agent Skill, use the host's own file reader with whatever page selection it offers. Default to the next unread page if the user says "next page" or "continue". - Display structured output following the format below.
- Wait for user instruction. Do not proceed to the next page, take notes, or search for related material unless explicitly asked.
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.
- yesterday Changed · +11 lines 3b4803c81fee
- 3d ago Changed · +10 lines 0fea658b17c1
- 9d ago First seen · 94 lines · 31 tokens per session scan A eaed47d5da1e
read is a skill published in the GitHub repository yha9806/academic-writing-toolkit (36 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 1,089 once invoked, about $0.0002 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
docs-generator
WHAT — Generate or update documentation from code: README.md from repo structure, CHANGELOG.md from git history, API reference from OpenAPI/GraphQL schemas, and AGENTS.md starters for new projects.
tikz-figure-review
Review and fix alignment, label collision, clipping, legend-over-data, overlap, and layout issues in TikZ and pgfplots figures inside LaTeX documents. Use when the user wants to review figures in a paper, tutorial, lecture notes, or thesis before submission; when a reviewer flags figure problems; when a rendered…
PDF → spreadsheet — extract data into Excel (Local MCP)
Use when the user wants to pull data out of one or more PDFs (invoices, bank/credit-card statements, receipts, reports, tables) and put it into a spreadsheet. pdfread is one of the most-used tools; this codifies the read-PDF → structure → write-Excel workflow. Powered by Local MCP, on-device.
latex-writer
Write, structure, and compile LaTeX documents for academic purposes. Use this skill whenever the user needs to write a LaTeX document, choose the right document class or packages, format equations, manage bibliographies, create figures and tables in LaTeX, troubleshoot errors, or prepare a journal-ready manuscript.…
data-management-plan
Write and review data management plans (DMPs) for research grants and projects. Use this skill whenever the user needs to write a DMP for NIH, NSF, UKRI, EU Horizon, or another funder; understand FAIR data principles; choose a data repository; describe data formats and metadata standards; handle sensitive or…
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…