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 bahayonghang/academic-writing-skills --skill latex-defense-zhgit clone --depth 1 https://github.com/bahayonghang/academic-writing-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/bahayonghang/academic-writing-skills/latex-defense-zh)<a href="https://agentmods.dev/skills/bahayonghang/academic-writing-skills/latex-defense-zh"><img src="https://agentmods.dev/badge/skills/bahayonghang/academic-writing-skills/latex-defense-zh/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/bahayonghang/academic-writing-skills/latex-defense-zh"><img src="https://agentmods.dev/badge/skills/bahayonghang/academic-writing-skills/latex-defense-zh.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 | $0.00079 | $0.03664 |
| Opus 5.5 | $0.00032 | $0.01466 |
| Sonnet 5.5 | $0.00016 | $0.00733 |
| Haiku 4.5 | $0.00008 | $0.00366 |
Grade A, and why
latex-defense-zh 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 20d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
52 files 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.
- agents/openai.yaml 590 B
- agents/qa-committee-agent.md 2.9 KB
- evals/evals.json 5.5 KB
- evals/fixtures/mini-thesis/chapters/chapter1.tex 1.4 KB
- evals/fixtures/mini-thesis/chapters/chapter2.aux 488 B
- evals/fixtures/mini-thesis/chapters/chapter2.tex 1.1 KB
- evals/fixtures/mini-thesis/chapters/chapter3.aux 811 B
- evals/fixtures/mini-thesis/chapters/chapter3.tex 2.7 KB
- evals/fixtures/mini-thesis/chapters/chapter4.tex 1.8 KB
- evals/fixtures/mini-thesis/chapters/chapter5.aux 522 B
- evals/fixtures/mini-thesis/chapters/chapter5.tex 1.7 KB
- evals/fixtures/mini-thesis/chapters/chapter6.tex 1009 B
- evals/fixtures/mini-thesis/chapters/chapter7.tex 713 B
- evals/fixtures/mini-thesis/document_blind.tex 1.0 KB
- evals/fixtures/mini-thesis/document.tex 1.8 KB
- evals/trigger_eval.json 2.8 KB
- examples/fix-after-check.md 3.4 KB
- examples/formal-defense.md 3.2 KB
- examples/predefense-40min.md 4.4 KB
- references/content-rules.md 4.2 KB
- references/defense-framework.md 8.0 KB
- references/plan-schema.md 37 KB
- references/qa-prep.md 3.0 KB
- references/quality-gate.md 22 KB
- references/slide-layouts.md 14 KB
- references/speaker-notes.md 2.4 KB
- references/time-budget.md 4.4 KB
- references/visual-spec.md 6.3 KB
- scripts/build_deck.py 32 KB runs code
- scripts/check_deck.py 57 KB runs code
- scripts/defense_budget.py 6.4 KB runs code
- scripts/extract_thesis.py 45 KB runs code
- scripts/plan_deck.py 21 KB runs code
- scripts/render_preview.py 4.7 KB runs code
- scripts/tex_loader.py 12 KB runs code
- templates/beamer/beamerthemeGenericDefense.sty 840 B
- templates/beamer/beamerthemeYanshanDefense.sty 798 B
- templates/beamer/defense-layouts.sty 15 KB
- templates/beamer/demo-deck.tex 7.2 KB
- templates/jinja/deck.tex.j2 1.3 KB
- templates/jinja/frames/bullets.tex.j2 358 B
- templates/jinja/frames/cards.tex.j2 314 B
- templates/jinja/frames/cover.tex.j2 52 B
- templates/jinja/frames/equations-figure.tex.j2 987 B
- templates/jinja/frames/figure-bullets.tex.j2 1.0 KB
- templates/jinja/frames/figure-grid.tex.j2 708 B
- templates/jinja/frames/figure.tex.j2 373 B
- templates/jinja/frames/outlook.tex.j2 380 B
- templates/jinja/frames/paper-summary.tex.j2 433 B
- templates/jinja/frames/table.tex.j2 412 B
- templates/jinja/frames/thanks.tex.j2 53 B
- templates/jinja/frames/toc.tex.j2 69 B
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.
- 20d ago First seen · 151 lines · 79 tokens per session scan A 4d67a7986f8e
latex-defense-zh is a skill published in the GitHub repository bahayonghang/academic-writing-skills (508 stars, last pushed yesterday), with no licence file. It adds 79 tokens to every session and 3,664 once invoked, about $0.0003 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 2026-09-26.
Other skills, from other repositories
latex-compile
Compile a LaTeX document and fix every error plus aesthetic issue (overfull/underfull boxes, widows, alignment, fonts) for a clean PDF and log. Use this instead of running pdflatex/latexmk manually — it avoids the latexmk stale-log trap and silent grep failures on binary log output, and it reformats rather than…
paper-figures
Extract figures from downloaded papers and include them in survey/review reports. Use when the report covers other groups' work and benefits from their architecture diagrams, experimental plots, or system schematics. Your brain prompt supplies the absolute path to the extract-figures script as {{EXTRACTFIGURES}} — use…
bib-parse
Extract citations from a PDF and generate a validated .bib file. Use when the user asks to extract citations from a PDF and generate a validated .bib file. Reads the PDF, identifies referenced works, constructs BibTeX entries, and verifies metadata.
latex
Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality. Use when a .tex source must be built or a concrete compilation failure repaired. Not for corpus-wide build checks, visual polish after a clean build, or creating a project; use $latex-health-check, $latex-polish, or…
beamer-deck
Create an academic presentation as a LaTeX Beamer source and reviewed PDF with an original theme. Use when the requested deliverable is a conference, seminar, or lecture deck in Beamer. Not for PowerPoint or RevealJS; use $pptx or $quarto-deck.
latex-template
Compare a project's LaTeX preamble and conventions against the canonical working-paper template. Use when diagnosing template drift without converting venue formats or editing prose.