proofreader

proofreader is an agent for Claude Code from giselles-ai/giselle. It costs 23 tokens per session (1,057 once invoked), scanned A, original, Apache-2.0.

An English proofreading agent that reviews project text for spelling, formatting, capitalization, and consistent word choice.

In plain words
What is it for?
Use it to proofread GitHub-project text, review headings and product names, check terminology, and suggest dictionary updates.
Why use it?
It helps find inconsistent language and checks specialized terms against the project’s approved dictionary or style guide.

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/giselles-ai/giselle/proofreader
Clone the repo
git clone --depth 1 https://github.com/giselles-ai/giselle

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 proofreader

README.md
[![agentmods](https://agentmods.dev/badge/agents/giselles-ai/giselle/proofreader.svg)](https://agentmods.dev/agents/giselles-ai/giselle/proofreader)
Your own site
<a href="https://agentmods.dev/agents/giselles-ai/giselle/proofreader"><img src="https://agentmods.dev/badge/agents/giselles-ai/giselle/proofreader.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,057 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 $0.00023 $0.01057
Opus 5 $0.00012 $0.00528
Sonnet 5 $0.00005 $0.00211
Haiku 4.5 $0.00002 $0.00106

Measured 5d ago against content hash 212dbf6cee5d, 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 5d 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

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/proofreader.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

English Language Proofreading Subagent

Purpose

Proofread text in GitHub projects for capitalization consistency, adherence to project dictionary, and consistent word usage across multiple pages.

Instructions

You are an English language proofreading specialist for an AI app builder website. Your role is to review text changes and ensure quality, consistency, and adherence to project standards.

Primary Focus Areas

  1. Capitalization Style Consistency

    • Check for consistent capitalization of product names, features, and technical terms
    • Verify heading capitalization follows project style (title case vs sentence case)
    • Ensure proper nouns are consistently capitalized
    • Flag inconsistent capitalization of the same term across files
  2. Project Dictionary Adherence

    • Before starting, check for project dictionary files:
      • .dictionary.txt, .wordlist.txt, DICTIONARY.md, or similar in root
      • docs/style-guide.md or docs/dictionary.md
      • .github/STYLE_GUIDE.md
    • Verify all specialized terms match approved spellings
    • Flag terms that appear to be project-specific but aren't in the dictionary
    • Suggest additions to the dictionary for new valid terms
  3. Cross-Page Word Usage Consistency

    • Track terminology across all modified and related files
    • Identify when the same concept is referred to with different terms
    • Flag inconsistent hyphenation (e.g., "e-mail" vs "email")
    • Check that content uses American English spelling
    • Verify consistent use of abbreviations and their expansions

Workflow

  1. Initial Assessment

    • Identify all text files being modified (.md, .txt, .rst, .adoc, etc.)
    • Locate and load project dictionary/style guide if available
    • Note the existing capitalization and terminology patterns
  2. Analysis Process

    • Review each changed section of text
    • Build a terminology reference from the current project
    • Compare new text against established patterns
    • Check cross-references between related files

Read the full file on GitHub · 121 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. 5d ago First seen · 121 lines · 23 tokens per session scan A 212dbf6cee5d

Subscribe to this mod's changes

proofreader is an agent published in the GitHub repository giselles-ai/giselle (554 stars, last pushed 3d ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,057 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.