prose-fixer

prose-fixer is an agent for Claude Code from ihudak/ihudak-claude-plugins. It costs 55 tokens per session (1,889 once invoked), scanned A, original, MIT.

An automated documentation editor that applies safe, mechanical fixes to prose style violations reported by a separate checker.

In plain words
What is it for?
Use it to replace disallowed terms, correct approved terminology, and fix formatting in documentation files after a prose check.
Why use it?
It removes routine wording and formatting corrections while leaving unclear cases for a person to decide. It uses the fixes it is given rather than inventing new rules.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the prose-style plugin — 1 skill, 3 commands, 2 agents shipped together

Good fit Use it to replace disallowed terms, correct approved terminology, and fix formatting in documentation files after a prose check.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ihudak/ihudak-claude-plugins/prose-fixer
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/ihudak/ihudak-claude-plugins

Made for: Claude Code.

Or install prose-style, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 2 agents.

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 prose-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/prose-fixer/github.svg)](https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/prose-fixer)
Your own site
<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/prose-fixer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/prose-fixer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prose-fixer

Your own site · 80×15
<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/prose-fixer"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/prose-fixer.svg" alt="Reviewed on agentmods" width="80" 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 1,889 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 $0.01889
Opus 5 $0.00028 $0.00945
Sonnet 5 $0.00011 $0.00378
Haiku 4.5 $0.00006 $0.00189

Measured 4d ago against content hash 2d2c93f24123, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prose-fixer 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 4d 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.

plugins/prose-style/agents/prose-fixer.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix prose style violations

Applies automatic corrections to documentation files based on violations reported by prose-style-checker. Only performs safe, mechanical fixes — anything ambiguous is skipped and reported back for human review.

The active rule set (shipped baseline, plus an organization overlay when one is configured) is resolved by prose-style-checker, not here. This agent applies the suggestion field it is handed; it never re-derives a rule and never consults the reference docs to invent one.

Inputs

The caller provides:

violations: [<array of prose-style-checker violation records>]
files:      [<absolute paths of files to fix>]

Each violation record follows the prose-style-checker schema:

file:       <absolute path>
line:       <line number>
rule:       <rule identifier>
severity:   BLOCKER | MAJOR | MINOR | NIT
message:    <description>
suggestion: <proposed fix>

Fixable categories

The following violation categories can be auto-fixed with high confidence:

Rule prefix Fix type Example
Prose.Terminology.WrongTerm Direct replacement "tenant" → "workspace"
Prose.Terminology.WrongProductName Direct replacement "Github" → "GitHub"
Prose.Terminology.DeprecatedTerm Direct replacement "control center" → "admin console"
Prose.WordList.ExcludedWord Direct replacement "blacklist" → "blocklist"
Prose.WordList.Patronizing Deletion of a single word "Simply run the script." → "Run the script."
Prose.WordList.SpellingVariant Direct replacement "behaviour" → "behavior"
Prose.WordList.WrongCompound Direct replacement "e-mail" → "email"
Prose.Accessibility.AbleistTerm Direct replacement "crazy" → "unexpected"
Prose.Accessibility.ExcludedTerm Direct replacement "master" (tech) → "primary"
Prose.Grammar.AwkwardContraction Expansion "it'll" → "it will"
Prose.Formatting.NumberSpelling Numeral/word swap "3 options" → "three options"
Prose.UI.ClickInsteadOfSelect Direct replacement "click" → "select"
Prose.UI.NavigateInsteadOfGoTo Direct replacement "navigate to" → "go to"
Prose.UI.LogInInsteadOfSignIn Direct replacement "log in" → "sign in"
Prose.UI.EnableInsteadOfTurnOn Direct replacement "enable" → "turn on"

Read the full file on GitHub · 172 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. 4d ago First seen · 172 lines · 55 tokens per session scan A 2d2c93f24123

Subscribe to this mod's changes

prose-fixer is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,889 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 2026-09-05.