latex-build-and-layout-audit

latex-build-and-layout-audit is a skill for Claude Code, Codex from VeryMath/AI4Math-Writing. It costs 48 tokens per session (760 once invoked), scanned A, original, MIT.

A checklist and audit method for building mathematical papers written in LaTeX, a document system commonly used for technical and scientific writing. It checks compilation, references, citations, layout warnings, packages, and submission readiness.

In plain words
What is it for?
Running or recommending a latexmk build, reading compiler logs, checking labels and citations, reviewing page-layout risks, and preparing a reproducible submission package.
Why use it?
It helps find build failures, missing references or files, broken bibliographies, layout problems, and portability issues before submission. It separates mechanical build problems from proof correctness.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Running or recommending a latexmk build, reading compiler logs, checking labels and citations, reviewing page-layout risks, and preparing a reproducible submission package.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/verymath/ai4math-writing/latex-build-and-layout-audit
Install

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.

Any agent
npx skills add VeryMath/AI4Math-Writing --skill latex-build-and-layout-audit
Clone the repo
git clone --depth 1 https://github.com/VeryMath/AI4Math-Writing

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for latex-build-and-layout-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/verymath/ai4math-writing/latex-build-and-layout-audit/github.svg)](https://agentmods.dev/skills/verymath/ai4math-writing/latex-build-and-layout-audit)
Your own site
<a href="https://agentmods.dev/skills/verymath/ai4math-writing/latex-build-and-layout-audit"><img src="https://agentmods.dev/badge/skills/verymath/ai4math-writing/latex-build-and-layout-audit/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.

agentmods 80×15 button for latex-build-and-layout-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/verymath/ai4math-writing/latex-build-and-layout-audit"><img src="https://agentmods.dev/badge/skills/verymath/ai4math-writing/latex-build-and-layout-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00760
Opus 5 $0.00024 $0.00380
Sonnet 5 $0.00010 $0.00152
Haiku 4.5 $0.00005 $0.00076

Measured 11d ago against content hash 4991d4f0e367, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

latex-build-and-layout-audit 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 11d 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.

skills/paper-writing/skills/latex-build-and-layout-audit/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LaTeX Build And Layout Audit

Audit whether a mathematical paper can be built and submitted reliably. This skill handles mechanical LaTeX quality, not proof correctness.

Inputs

  • Full TeX source tree, bibliography, figures, class/style files, and target venue or arXiv constraints.
  • Optional existing PDF, .log, .blg, .bbl, or build command.

Output Contract

Return:

  • Build status and exact command used or recommended.
  • Hard failures: fatal compile errors, undefined references/citations, duplicate labels, missing files, broken bibliography, or incompatible packages.
  • Soft warnings: overfull/underfull boxes, float congestion, page-limit risks, fragile macros, and arXiv compatibility concerns.
  • Submission preflight: source package portability, clean build reproducibility, TeX Live compatibility, required generated files, and submission manifest gaps.
  • Patch suggestions with file path, location, rationale, and meaning-risk label.

Workflow

  1. Inspect project structure and identify the root .tex file.
  2. Prefer latexmk -pdf -interaction=nonstopmode -halt-on-error <root>.tex when running a build is allowed.
  3. Read logs for errors, warnings, references, citations, labels, and box issues.
  4. Check source package portability before upload: absolute paths, local-only paths, spaces or fragile file names, missing style files, missing class files, missing bibliography files, missing figures, and case-sensitive path issues.
  5. Check arXiv and venue preflight risks: TeX Live version assumptions, unsupported external commands, shell escape requirements, stale .bbl, figure format/engine mismatches, \include paths that write aux files below the top directory, and policy-forbidden watermarks, referee notes, or margin comments.
  6. Produce or request a submission manifest listing root file, build command, engine, bibliography mode, custom .sty/.cls/.bst files, figures, supplements, code/data links, and unresolved risks.
  7. Separate mechanical fixes from edits that could affect mathematical meaning.

Read the full file on GitHub · 74 lines

Changes

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.

  1. 11d ago First seen · 74 lines · 48 tokens per session scan A 4991d4f0e367

Subscribe to this mod's changes

latex-build-and-layout-audit is a skill published in the GitHub repository VeryMath/AI4Math-Writing (6 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 760 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 2026-08-31.

Related

Other skills, from other repositories

cdopt-optimization

Use when Codex needs to solve, reproduce, test, compare, generate examples for, or diagnose CDOpt manifold optimization workflows, including CDOpt package smoke tests, official problem description cards, Stiefel dictionary learning, SciPy wrappers, PyTorch/JAX/NumPy CDOpt examples, dependency checks, tiny CPU…

VeryMath/AI4Math-Optimization · 80 tokens

osqp-solver

Model, solve, update, reproduce, and diagnose continuous convex quadratic programs with the OSQP Python interface, including canonical-form conversion, sparse CSC data, solver-status gates, residual checks, infeasibility certificates, warm starts, repeated parametric QPs, and academic citation. Use when a task names…

VeryMath/AI4Math-Optimization · 131 tokens

second-order-cone-programming

Models and solves second-order cone programs and problems convertible to SOCP form using cvxpy with multiple solver backends (COPT, Gurobi, MOSEK, CPLEX, CLARABEL, ECOS, SCS, CVXOPT, COSMO, OSQP). Handles linear objectives with second-order cone constraints, as well as problems reducible to SOCP such as portfolio…

VeryMath/AI4Math-Optimization · 114 tokens

mixed-integer-programming

Models and solves mixed-integer linear programs, including binary, integer, and continuous decision variables with linear objectives and constraints.

VeryMath/AI4Math-Optimization · 30 tokens

or-solver

Configure the Python environment for a solver already specified by the user or a modeling skill. Check the target interpreter and dependencies, install required packages, configure licenses and environment variables, troubleshoot setup errors, and report availability. Use for installing or repairing a named solver…

VeryMath/AI4Math-Optimization · 69 tokens

ai4math-optimization

Route AI4Math optimization tasks to the appropriate bundled skill package.

VeryMath/AI4Math-Optimization · 19 tokens