prose-style-checker

prose-style-checker is an agent for Claude Code from ihudak/ihudak-claude-plugins. It costs 120 tokens per session (3,088 once invoked), scanned A, original, MIT.

A prose review tool that checks files against writing rules for terminology, tone, grammar, formatting, user-interface text, inclusive language, and accessibility. It combines a standard rule set with an organization's own style guide when available.

In plain words
What is it for?
It is used to review product requirements, architecture documents, epic drafts, release notes, and other prose files.
Why use it?
It finds writing problems that a code linter may miss and reports them in a consistent format. This helps keep product and planning documents clear and consistent.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

Good fit It is used to review product requirements, architecture documents, epic drafts, release notes, and other prose files.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ihudak/ihudak-claude-plugins
Claude Code
/plugin install prose-style

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-style-checker

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/prose-style-checker"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/prose-style-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,088 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 $0.00120 $0.03088
Opus 5 $0.00060 $0.01544
Sonnet 5 $0.00024 $0.00618
Haiku 4.5 $0.00012 $0.00309

Measured 4d ago against content hash 3385f3094161, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prose-style-checker 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-style-checker.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Check files against the active prose style rules and return violations in the docs-style-checker finding schema.

When to invoke

  • From /document (Jira mode) Phase 6.4 — dispatched inside docs-style-checker as the complementary semantic pass alongside the repo's primary linter.
  • From /epics Phase 6.2 — as the primary style checker for Epic drafts (vault-internal, no repo linter). Also from /create-prd, /update-prd, and /release-notes.
  • From /prose-review-pr and /prose-review-docs in this plugin.
  • From any command that writes planning documents (PRDs, ARDs, and similar).

Inputs

files:        [<absolute paths of files to check>]
doc_type:     epic | prd | ard | product-docs | general
rules_path:   <optional absolute path to an overlay rules directory — overrides
               discovery in step 1>

doc_type affects severity calibration (see step 5). Default: general.

Procedure

1. Resolve the active rule set

This is the plugin's overlay mechanism. It has exactly one overlay source and one baseline. Every miss at every step is a silent, non-blocking fall-through — never an error, never a gate, never a prompt.

Step 1a — baseline (always loaded).

${CLAUDE_PLUGIN_ROOT}/references/

Read all eight files: terminology.md, word-list.md, voice-and-tone.md, grammar.md, formatting.md, ui-interactions.md, accessibility.md, top-10-tips.md. This is the only step whose failure is an error — with no baseline and no overlay there is nothing to check against.

Step 1b — find the overlay source. Take the FIRST of these that resolves. Stop at the first hit; do not merge two overlays.

Order Source Resolves when
1 rules_path input, when the caller supplied one the path is a readable directory containing ≥1 .md file
2 <repo-root>/.prose-style/rules/ the directory exists, is readable, and contains ≥1 .md file
3 $PROSE_STYLE_PATH the variable is set and names a readable directory containing ≥1 .md file
4 (none) always — the baseline alone is the active rule set

Read the full file on GitHub · 229 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 · 229 lines · 120 tokens per session scan A 3385f3094161

Subscribe to this mod's changes

prose-style-checker is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 3,088 once invoked, about $0.0006 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.