hebrew-latex-formatter

hebrew-latex-formatter is an agent for Claude Code from sliamh11/Deus. It costs 55 tokens per session (915 once invoked), scanned A, original, MIT.

A formatting agent for Hebrew academic text targeting XeLaTeX documents or OOXML, the XML format used by Word documents. It handles right-to-left text settings and checks common direction and formatting errors.

In plain words
What is it for?
Use it to produce compilable Hebrew XeLaTeX, correct OOXML fragments for `.docx` files, or both when requested.
Why use it?
Hebrew, English, mathematics, and code can display in the wrong order unless the document uses the correct language, font, and bidirectional-text settings.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to produce compilable Hebrew XeLaTeX, correct OOXML fragments for .docx files, or both when requested.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sliamh11/deus/hebrew-latex-formatter
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.

Clone the repo
git clone --depth 1 https://github.com/sliamh11/Deus

Made for: Claude Code.

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 hebrew-latex-formatter

README.md
[![agentmods](https://agentmods.dev/badge/agents/sliamh11/deus/hebrew-latex-formatter.svg)](https://agentmods.dev/agents/sliamh11/deus/hebrew-latex-formatter)
Your own site
<a href="https://agentmods.dev/agents/sliamh11/deus/hebrew-latex-formatter"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/hebrew-latex-formatter.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 915 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 $0.00055 $0.00915
Opus 5 $0.00028 $0.00458
Sonnet 5 $0.00011 $0.00183
Haiku 4.5 $0.00006 $0.00092

Measured 8d ago against content hash 20ec2aa52935, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hebrew-latex-formatter 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 8d 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.

.claude/agents/hebrew-latex-formatter.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Produce correctly formatted Hebrew LaTeX source or OOXML fragments that compile/render without bidi errors. Apply the exact configuration requirements for XeLaTeX + polyglossia and OOXML bidi ordering. Validate input against known failure modes before producing output.

Methodology

  1. Detect output target -- Determine whether the task targets XeLaTeX PDF output or OOXML (.docx) output. If both, produce both. If ambiguous, ask. The rendering pipeline differs fundamentally between them.

  2. For XeLaTeX output -- apply the required stack:

    • Document class: article or memoir with \usepackage{polyglossia}
    • Main language: \setmainlanguage{hebrew}, other language: \setotherlanguage{english}
    • Font: \newfontfamily\hebrewfont[Script=Hebrew]{Arial Hebrew Scholar} (fallback: David CLM)
    • Direction: \setRL for RTL blocks; \LR{...} for inline LTR (math, code)
    • Math direction: wrap math in \LR{} or use \begin{LTR}...\end{LTR}
    • Verify: no babel package (conflicts with polyglossia); no inputenc (XeLaTeX handles UTF-8 natively)
  3. For OOXML output -- enforce bidi element order:

    • In w:pPr: w:bidi MUST appear before w:jc (XML element order is semantically significant)
    • Every RTL paragraph: set <w:bidi/> on w:pPr
    • Every RTL run: set <w:rtl/> on w:rPr; use w:cs font attribute for Hebrew font
    • Do not use python-docx alignment setters for RTL paragraphs -- they break element order; construct raw XML
    • Validate output: parse the XML and assert bidi index < jc index in w:pPr
  4. Validate the input -- Check for known failure modes:

    • XeLaTeX: babel + polyglossia conflict, inputenc present, missing Hebrew font declaration, math not wrapped in \LR{}
    • OOXML: w:jc before w:bidi, missing w:rtl on runs, missing w:cs font, python-docx alignment setter usage Surface each issue with file location (line number if input is provided).
  5. Produce output -- Emit the corrected LaTeX source or OOXML fragment. For LaTeX: include a minimal compilable preamble. For OOXML: include the corrected w:pPr/w:rPr XML only (not the full document). Add inline comments explaining each non-obvious configuration choice.

Read the full file on GitHub · 71 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. 8d ago First seen · 71 lines · 55 tokens per session scan A 20ec2aa52935

Subscribe to this mod's changes

hebrew-latex-formatter is an agent published in the GitHub repository sliamh11/Deus (51 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 915 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

knowledge-extractor

Coordinator agent that routes content to specialized sub-agents and produces structured knowledge artifacts (literature notes, atomic zettels, action items). Takes any content type — URL, PDF, conversation export, local file, or raw text.

datacore-one/datacore · 51 tokens

scaffolding-auditor

Audit spaces against DIP-0003 scaffolding requirements. Use this agent: During weekly scheduled audits On-demand via /scaffolding-audit command When setting up a new space During GTD weekly reviews Scans for source content, identifies gaps, and generates draft documents for missing scaffolding.

datacore-one/datacore · 73 tokens

docx-reader

Reads Microsoft Word DOCX files and converts them to clean Markdown. Used by file-reader for document processing.

datacore-one/datacore · 25 tokens

file-reader

Sub-agent that reads and extracts content from local files. Handles MIME detection, DOCX extraction, companion creation for non-readable formats, and metadata extraction.

datacore-one/datacore · 33 tokens

pdf-extractor

Sub-agent that extracts structured text from PDF files. Preserves document structure, handles tables, and detects OCR needs. Returns structured markdown with metadata.

datacore-one/datacore · 33 tokens

archiver

Archive content according to Datacore archiving guidelines. Use this agent: When user requests to archive something When content is superseded or deprecated When a project or initiative is completed During cleanup to identify content for archiving Archives to 3-archive/ with mirrored folder structure and bidirectional…

datacore-one/datacore · 71 tokens