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 GalaxyRuler/Galactic-skills --skill latex-professionalgit clone --depth 1 https://github.com/GalaxyRuler/Galactic-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/galaxyruler/galactic-skills/latex-professional)<a href="https://agentmods.dev/skills/galaxyruler/galactic-skills/latex-professional"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/latex-professional/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/galaxyruler/galactic-skills/latex-professional"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/latex-professional.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 | $0.00142 | $0.03053 |
| Opus 5.5 | $0.00057 | $0.01221 |
| Sonnet 5.5 | $0.00028 | $0.00611 |
| Haiku 4.5 | $0.00014 | $0.00305 |
Grade A, and why
latex-professional 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LaTeX Professional Skill
<when_to_use> Use for LaTeX, TeX, BibTeX, BibLaTeX, Biber, natbib, latexmk, arXiv packaging, academic papers, theses, books, reports, Beamer slides, equations, tables, figures, captions, labels, citations, publisher templates, .tex/.bib/.bst/.sty/.cls files, or LaTeX compile errors. </when_to_use>
Resources (progressive disclosure — load only what the task needs)
Scripts (scripts/, read-only, Python 3.10+; run with python scripts/<name>):
| Script | Use |
|---|---|
find-main-tex.py [root] [--json] |
Rank likely main .tex files. |
latex-project-inventory.py [root] [--json] |
Full read-only inventory: sources, engine hints, bib backend, assets, build systems, submission artifacts. |
parse-latex-log.py <file.log> [--json] |
Extract the first meaningful error + all findings from a build log. |
check-latex-assets.py [main.tex] [--json] |
Verify \includegraphics/\input/\include/bibliography files exist. |
check-bib.py [paths…] [--json] |
Lint .bib for duplicate keys, unbalanced braces, missing fields. |
build-latex-safe.sh / build-latex-safe.ps1 |
Safe latexmk wrapper — no shell escape unless explicitly flagged. |
Reference playbooks (references/, load on demand):
| Playbook | Load when |
|---|---|
compile-error-playbook.md |
Diagnosing a build failure or .log. |
main-file-discovery.md |
Identifying the main file in an unfamiliar project. |
bibliography-backends.md |
Any citation / bibliography-backend work. |
math-preservation.md |
Editing equations or mathematical text. |
package-compatibility.md |
Option clashes, load-order errors, engine choice. |
tables-and-figures.md |
Building or fixing tables and figures. |
submission-arxiv.md |
Preparing an arXiv upload. |
journal-template-modes.md |
IEEE / ACM / Springer / Elsevier / RevTeX / thesis targets. |
What ships with it
57 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 128 B
- README.md 3.3 KB
- references/bibliography-backends.md 7.2 KB
- references/compile-error-playbook.md 11 KB
- references/journal-template-modes.md 9.7 KB
- references/main-file-discovery.md 7.4 KB
- references/math-preservation.md 6.6 KB
- references/package-compatibility.md 9.1 KB
- references/submission-arxiv.md 8.1 KB
- references/tables-and-figures.md 7.4 KB
- scripts/build-latex-safe.ps1 624 B runs code
- scripts/build-latex-safe.sh 1.1 KB runs code
- scripts/check-bib.py 11 KB runs code
- scripts/check-latex-assets.py 14 KB runs code
- scripts/find-main-tex.py 2.9 KB runs code
- scripts/latex-project-inventory.py 21 KB runs code
- scripts/parse-latex-log.py 2.9 KB runs code
- templates/academic-paper/figures/.gitkeep 68 B
- templates/academic-paper/latexmkrc 377 B
- templates/academic-paper/main.tex 2.9 KB
- templates/academic-paper/README.md 1.9 KB
- templates/academic-paper/refs.bib 933 B
- templates/article/figures/.gitkeep 87 B
- templates/article/latexmkrc 377 B
- templates/article/main.tex 2.3 KB
- templates/article/README.md 1.2 KB
- templates/article/refs.bib 857 B
- templates/article/sections/.gitkeep 84 B
- templates/beamer/main.tex 2.8 KB
- templates/beamer/README.md 1.4 KB
- templates/beamer/refs.bib 679 B
- templates/book/chapters/chapter1.tex 625 B
- templates/book/latexmkrc 500 B
- templates/book/main.tex 2.2 KB
- templates/book/README.md 1.8 KB
- templates/book/refs.bib 894 B
- templates/latexmkrc/latexmkrc-biber 614 B
- templates/latexmkrc/latexmkrc-bibtex 802 B
- templates/latexmkrc/latexmkrc-lualatex 388 B
- templates/latexmkrc/latexmkrc-pdflatex 454 B
- templates/latexmkrc/latexmkrc-xelatex 384 B
- templates/latexmkrc/README.md 2.2 KB
- templates/report/figures/.gitkeep 68 B
- templates/report/latexmkrc 377 B
- templates/report/main.tex 1.6 KB
- templates/report/README.md 1.3 KB
- templates/report/refs.bib 827 B
- templates/report/sections/intro.tex 628 B
- templates/snippets/equations.md 3.5 KB
- templates/snippets/figures.md 4.2 KB
- templates/snippets/tables.md 3.9 KB
- templates/thesis/chapters/introduction.tex 670 B
- templates/thesis/figures/.gitkeep 68 B
- templates/thesis/latexmkrc 377 B
- templates/thesis/main.tex 3.6 KB
- templates/thesis/README.md 1.8 KB
- templates/thesis/refs.bib 852 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.
- 2mo ago First seen · 175 lines · 142 tokens per session scan A bcc9e3b40223
latex-professional is a skill published in the GitHub repository GalaxyRuler/Galactic-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 142 tokens to every session and 3,053 once invoked, about $0.0006 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 2026-08-31.
latex-professional compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| latex-professionalGalaxyRuler/Galactic-skills | Skill | 5 | 2mo ago | MIT | A | 142 | Codex |
| nature-paper2wordYuan1z0825/nature-skills | Skill | 53k | yesterday | Apache-2.0 | A | 233 | Codex |
| pydicomK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 52 | Claude Code, Codex |
| nature-paper-transYuan1z0825/nature-skills | Skill | 53k | yesterday | Apache-2.0 | A | 68 | Codex |
| pptx-postersK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 59 | Claude Code |
| extracting-lab-tablesmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 210 | Claude Code |
| figuressynthetic-sciences/openscience | Skill | 4.4k | today | Apache-2.0 | A | 99 | Claude Code |