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 Calix-L/awesome-latex-skills --skill latex-rescuegit clone --depth 1 https://github.com/Calix-L/awesome-latex-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/calix-l/awesome-latex-skills/latex-rescue)<a href="https://agentmods.dev/skills/calix-l/awesome-latex-skills/latex-rescue"><img src="https://agentmods.dev/badge/skills/calix-l/awesome-latex-skills/latex-rescue/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/calix-l/awesome-latex-skills/latex-rescue"><img src="https://agentmods.dev/badge/skills/calix-l/awesome-latex-skills/latex-rescue.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 | $0.00041 | $0.01120 |
| Opus 5.5 | $0.00016 | $0.00448 |
| Sonnet 5.5 | $0.00008 | $0.00224 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
latex-rescue 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 19d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Repair the requested project with the smallest change that addresses the actual failure. Compilation success does not establish mathematical correctness.
Establish the failing build
- For a pasted error, give a diagnosis using the supplied context. Request source or logs only when they are needed to distinguish plausible fixes; a project directory is not required for a useful diagnosis.
- For a local project, identify its root document from the build command,
configuration, magic comments, and
\documentclass. A file namedmain.texis a candidate, not proof that it is the root. Resolve ambiguous roots before editing. - Respect the engine, auxiliary/output directories, bibliography backend, and
any custom build steps.
fontspecrequires XeLaTeX or LuaLaTeX. Checkbiblatex's backend option rather than assuming Biber in every project. - Reproduce the failure with the existing build command where available. Retain exit codes and the final engine/backend logs. A stale PDF is not build evidence. Missing tools or project files mean compilation remains unverified.
For manual builds, use the actual root and engine, for example:
pdflatex -no-shell-escape -interaction=nonstopmode -file-line-error main.tex
Use the shell's own exit-status handling when capturing output. Bash pipelines
need set -o pipefail; do not assume Bash syntax works in PowerShell. Do not
enable shell escape merely to silence an error; follow the project's actual
requirements and the user's execution permissions.
Diagnose and repair
Read the first causal error, its source context, and subsequent diagnostics.
File-line diagnostics may appear as file.tex:line: rather than starting with !.
Undefined references and overfull boxes are generally warnings, not syntax failures.
Consult only the relevant resources:
- Error catalog: known typos, missing packages, encoding, references, and environment errors.
- Package conflicts: option clashes or competing definitions; preserve the official template's package choices.
- Debug workflow: cascading errors and failures that remain after an initial contextual fix.
What ships with it
7 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.
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.
- 19d ago Changed 30e3195567df
- 21d ago Changed d50caa10008d
- 22d ago Changed · +3 lines 77609e881d1f
- 23d ago Changed 621b16d72e5b
- 24d ago Changed · -201 lines · +4 tokens per session 39d026e150ae
- 1mo ago First seen · 302 lines · 37 tokens per session scan A 84a0d825c49e
latex-rescue is a skill published in the GitHub repository Calix-L/awesome-latex-skills (184 stars, last pushed 20d ago), licensed MIT. It adds 41 tokens to every session and 1,120 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
overleaf
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
fetch-paper
Fetches a legal open-access copy of a paper from its DOI or arXiv ID — resolves through Unpaywall, arXiv PDF/HTML, and the open-access ACM Digital Library. Use when the user wants to fetch, download, read, or get the PDF or full text of a specific paper. Single polite fetch, transient processing only: it never stores…
figure-drawing
MANDATORY skill for creating any figure, diagram, chart, table visualization, or TikZ graphic in a paper. Must be activated BEFORE writing any drawing code. Produces standalone .tex → compiled PDF/PNG → \includegraphics in paper. Never inline TikZ code directly into paper sections.
read-paper-to-notes
Read an academic-paper PDF or supplied full text and turn it into a faithful, structured Markdown deep-reading note. Use when the user provides a research paper and asks to read, explain, summarize, take notes, extract its problem, method, equations, experiments, results, limitations, or research implications, or fill…
user-preview
Compile the current project's LaTeX files and send the generated PDF to the user for preview. Use when the user wants to check typesetting results or confirm the effect of recent edits.
awesome-ieee-report
Generates IEEE-format LaTeX technical reports from project requirements and codebase evidence, using academic prose, pseudocode-only explanations, BibTeX references, and IEEEtran formatting.