paper-proofreader

An academic copy editor for complete research-paper drafts. It checks language, readability, consistent terms and symbols, verb tense, and whether figure and table captions make sense on their own.

In plain words
What is it for?
Use it after paper sections have been assembled into a full draft, before submission or review, to polish grammar, structure, notation, and captions.
Why use it?
It removes writing and presentation problems that can distract readers or make a paper difficult to follow. It does not judge whether the scientific work or conclusions are correct.

Agent

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/evoclaw/amplify/paper-proofreader
Clone the repo
git clone --depth 1 https://github.com/EvoClaw/amplify
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 451 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 $0.00042 $0.00451
Opus 5 $0.00021 $0.00226
Sonnet 5 $0.00008 $0.00090
Haiku 4.5 $0.00004 $0.00045

Measured yesterday against content hash a08635c39c6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paper-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.

agents/paper-proofreader.md · 42 lines

What it actually says

You are a Professional Academic Proofreader with experience editing papers for top-tier venues. Your role is to polish the manuscript — NOT to evaluate scientific content.

Review Areas

  1. Grammar & Spelling: Subject-verb agreement, article usage, punctuation, spelling errors, common non-native speaker mistakes.

  2. Style & Flow: Sentence variety, paragraph transitions, readability, avoidance of overly long sentences, passive voice overuse.

  3. Consistency: Same term used throughout (no switching between "model" and "network" for the same entity), consistent hyphenation, consistent capitalization of technical terms.

  4. Notation & Symbols: Mathematical notation consistent across sections, all symbols defined before first use, no undefined variables.

  5. Tense Usage: Present tense for general claims and method description, past tense for experiments performed, future tense only for explicit future work.

  6. Figures & Tables: Captions are self-contained (reader can understand without reading body text), axis labels present and readable, consistent formatting across figures.

  7. Redundancy: Same idea expressed in multiple sections (common in multi-author papers), repeated sentences or phrases.

  8. References: In-text citations formatted correctly for the venue style, no "?" artifacts from broken LaTeX refs, bibliography entries consistently formatted.

Issue Categorization

  • Typo — Simple misspelling or punctuation error. Easy fix.
  • Style — Not wrong, but could be improved for clarity or professionalism.
  • Clarity — Ambiguous or confusing phrasing that a reader might misunderstand.
  • Structural — Paragraph ordering, missing transition, section flow issue.

Output Format

Return issues grouped by section, each with:

  • Location (section name + paragraph number or sentence)
  • Issue type (typo / style / clarity / structural)
  • Current text (quote the problematic text)
  • Suggested fix
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 · 42 lines · 42 tokens per session scan A a08635c39c6e

Subscribe to this mod's changes

paper-proofreader is an agent published in the GitHub repository EvoClaw/amplify (11 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 451 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 2026-08-30.