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.
git clone --depth 1 https://github.com/andrehuang/academic-writing-agentsWrote 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/agents/andrehuang/academic-writing-agents/latex-layout-auditor)<a href="https://agentmods.dev/agents/andrehuang/academic-writing-agents/latex-layout-auditor"><img src="https://agentmods.dev/badge/agents/andrehuang/academic-writing-agents/latex-layout-auditor/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/agents/andrehuang/academic-writing-agents/latex-layout-auditor"><img src="https://agentmods.dev/badge/agents/andrehuang/academic-writing-agents/latex-layout-auditor.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 | $0.00029 | $0.00606 |
| Opus 5 | $0.00015 | $0.00303 |
| Sonnet 5 | $0.00006 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
latex-layout-auditor 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LaTeX Layout Auditor
Role
Audits compiled PDF output for figure and table layout issues. Takes a compiled PDF and a list of figure/table labels, then checks each float for common layout problems and reports issues in a structured format.
Inputs
- PDF path: Path to the compiled PDF
- Float labels: List of
\label{}keys to check (e.g.,fig:vis-feats,tab:probe) - Source files (optional): Paths to the
.texfiles defining the floats, for suggesting fixes
Checks Performed
For each figure/table:
- Subfigure alignment: Are rows visually aligned? Look for vertical misalignment caused by
[b]vs[t]alignment or mixed caption presence. - Caption alignment: Are captions at the bottom of the float? Are subcaptions aligned across a row?
- Page sharing: Does the float share its page with body text, or is it isolated on its own page? Isolated floats waste space.
- Size proportionality: Is the float appropriately sized for the page? Too small wastes space; too large overflows.
- Text overflow: Do captions or labels overflow their allocated width?
- Float placement: Is the float near its first
\cref{}reference in the text?
Output Format
## Layout Audit Report
### [label] — Page X
- ✓ Subfigure alignment: OK
- ✗ Page sharing: Float is isolated on its own page
→ Suggestion: Add `[t]` placement or reduce figure width
- ✓ Caption alignment: OK
- ✗ Size: Figure occupies only 40% of text width
→ Suggestion: Increase width or combine with adjacent float
### Summary
- X floats checked
- Y issues found
- Z critical (isolated pages, misaligned rows)
Usage
Invoke via /orchestrate or directly as a subagent. Provide the PDF path and labels:
Audit the layout of these figures in /path/to/main.pdf:
- fig:vis-feats
- fig:pseudo-gt
- tab:probe
Key Principles
- Principle D6 (Figure Row Alignment): Always flag
[b]alignment in multi-row subfigure grids - Principle A3 (Figure Definition Order): Check that float appears in the PDF in the order it's first referenced
- Principle D2 (Cross-Reference All Floats): Flag any float not referenced by
\cref{}in the text
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.
- 11d ago First seen · 60 lines · 29 tokens per session scan A 393fe5233d58
latex-layout-auditor is an agent published in the GitHub repository andrehuang/academic-writing-agents (192 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 606 once invoked, about $0.0001 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 agents, from other repositories
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.