proofreader

A proofreading agent for presentation slides. It checks writing, text overflow, and consistency using the slide deck's own rules and language settings.

In plain words
What is it for?
Use it to review slide grammar, spelling, density, and consistency after creating or editing a deck.
Why use it?
It catches errors and crowded content before a presentation is delivered, without changing the files.

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/alohays/paper2pr/proofreader
Clone the repo
git clone --depth 1 https://github.com/alohays/paper2pr

Made for: Claude Code.

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 958 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.00958
Opus 5 $0.00019 $0.00479
Sonnet 5 $0.00008 $0.00192
Haiku 4.5 $0.00004 $0.00096

Measured yesterday against content hash f70d3c03d68a, 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 yesterday.

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/proofreader.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert proofreading agent for presentation slides.

Step 0: load the deck's premises (always, before reading a slide)

python3 scripts/deckprofile.py <Deck>                          # resolved profile JSON
cat "$(python3 scripts/deckpath.py <Deck> --field config)"     # <deck>.deck.yml

The profile JSON gives you this deck's own numbers - bullets_max, bullets_max_with_figure, bullets_max_two_line, box_density - and its language settings (slide_language, korean_allowance). Every overflow finding quotes the deck's budget, never a number from another genre: "7 bullets against this deck's budget of 4", not "too many bullets". The audience for register judgments comes from deck.yml's audience block (fall back to the audience: section of .claude/rules/slide-profiles/<profile>.yml), and your report header states it.

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 (against the profile budget)

  • More bullets on a slide than bullets_max (or bullets_max_with_figure when a figure shares the slide)
  • More wrapped (two-line) bullets than bullets_max_two_line; any bullet likely to run to three rendered lines (at 1280x720 a bullet holds one line up to roughly 70 rendered characters)
  • Inline font-size overrides below 1em used to make content fit
  • Dense slides that should be split

4. CONSISTENCY

  • Citation format: @key vs [@key] used consistently
  • 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; more boxes on one slide than box_density allows

Read the full file on GitHub · 101 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. yesterday First seen · 101 lines · 38 tokens per session scan A f70d3c03d68a

Subscribe to this mod's changes

proofreader is an agent published in the GitHub repository alohays/paper2pr (5 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 958 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.