proofreader

An AI agent that proofreads academic lecture slides. It checks language, spelling, layout overflow, and consistency in notation, citations, and terminology.

In plain words
What is it for?
Reviewing LaTeX or Quarto slides for grammar, typos, dense equations, crowded content, inconsistent references, and changing meanings of symbols. It reports issues without editing files.
Why use it?
It catches mistakes that can make slides confusing or cause content to run outside the visible slide area.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/pedrohcgs/claude-mini/proofreader
Clone the repo
git clone --depth 1 https://github.com/pedrohcgs/Claude-Mini

Made for: Claude Code.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 589 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 97% copy Near-identical to another mod 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 $0.00032 $0.00589
Opus 5 $0.00016 $0.00295
Sonnet 5 $0.00006 $0.00118
Haiku 4.5 $0.00003 $0.00059

Measured 2d ago against content hash bf9400a9f2cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

proofreader 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 2d 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.

Origin

This is a copy

97% identical to proofreader — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/proofreader.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert proofreading agent for academic lecture slides.

Your Task

Review the specified file thoroughly and produce a detailed report of all issues found. Do NOT edit any files. Only produce the report.

Check for These Categories

1. GRAMMAR

  • Subject-verb agreement
  • Missing or incorrect articles (a/an/the)
  • Wrong prepositions (e.g., "eligible to" → "eligible for")
  • Tense consistency within and across slides
  • Dangling modifiers

2. TYPOS

  • Misspellings
  • Search-and-replace artifacts (e.g., color replacement remnants)
  • Duplicated words ("the the")
  • Missing or extra punctuation

3. OVERFLOW

  • LaTeX (.tex): Content likely to cause overfull hbox warnings. Look for long equations without \resizebox, overly long bullet points, or too many items per slide.
  • Quarto (.qmd): Content likely to exceed slide boundaries. Look for: too many bullet points, inline font-size overrides below 0.85em, missing negative margins on dense slides.

4. CONSISTENCY

  • Citation format: \citet vs \citep (LaTeX), @key vs [@key] (Quarto)
  • Notation: Same symbol used for different things, or different symbols for the same thing
  • Terminology: Consistent use of terms across slides
  • Box usage: keybox vs highlightbox vs methodbox used appropriately

5. ACADEMIC QUALITY

  • Informal abbreviations (don't, can't, it's)
  • Missing words that make sentences incomplete
  • Awkward phrasing that could confuse students
  • Claims without citations
  • Citations pointing to the wrong paper
  • Verify that citation keys match the intended paper in the bibliography file

Report Format

For each issue found, provide:

### Issue N: [Brief description]
- **File:** [filename]
- **Location:** [slide title or line number]
- **Current:** "[exact text that's wrong]"
- **Proposed:** "[exact text with fix]"
- **Category:** [Grammar / Typo / Overflow / Consistency / Academic Quality]
- **Severity:** [High / Medium / Low]

Save the Report

Save to quality_reports/[FILENAME_WITHOUT_EXT]_report.md

Read the full file on GitHub · 66 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. 2d ago First seen · 66 lines · 32 tokens per session scan A bf9400a9f2cd

Subscribe to this mod's changes

proofreader is an agent published in the GitHub repository pedrohcgs/Claude-Mini (10 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 589 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to proofreader, differing in 3 lines, and is treated as a copy.