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.
git clone --depth 1 https://github.com/ihudak/ihudak-claude-pluginsWrote 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.
[](https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/prose-review-docs)<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/prose-review-docs"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/prose-review-docs/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.
<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/prose-review-docs"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/prose-review-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.01629 |
| Opus 5 | $0.00034 | $0.00814 |
| Sonnet 5 | $0.00013 | $0.00326 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
prose-review-docs 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.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review documentation files against the prose style rules
Reviews one or more markdown files against the active prose style rules. Reports violations and optionally applies fixes.
Arguments
The command receives its input via $ARGUMENTS. Accepted formats:
| Format | Example | Behaviour |
|---|---|---|
| File path | docs/get-started/index.md |
Reviews that single file |
| Directory path | docs/get-started/ |
Reviews all .md files recursively |
--fix |
docs/ --fix |
After reviewing, apply safe mechanical fixes |
--doc-type <type> |
--doc-type product-docs |
Severity calibration (default: product-docs) |
--severity <level> |
--severity MINOR |
Only report violations at this level or above (default: show all) |
--rules <path> |
--rules ~/style/rules |
Override overlay discovery; passed to prose-style-checker as rules_path |
Paths can be relative (resolved from cwd) or absolute. Multiple paths can be
provided: docs/setup/ docs/config/auth.md.
If no arguments are provided, ask the user: "Please provide a file or directory path to review."
Procedure
1. Parse arguments
Extract from $ARGUMENTS:
- paths: one or more file/directory paths (everything that is not a flag).
- fix_mode:
trueif--fixis present. - doc_type: value after
--doc-type, orproduct-docsif absent. - min_severity: value after
--severity, orNITif absent (show all). - rules_path: value after
--rules, or absent.
If no paths are found, ask the user for a path.
2. Resolve files
For each path in paths:
- If it's a file and ends with
.md: add it directly. - If it's a directory: recursively find all
.mdfiles:find <path> -name '*.md' -not -path '*/node_modules/*' -not -path '*/.git/*' \ -not -path '*/vendor/*' -not -path '*/build/*' -not -path '*/dist/*' \ | sort - If it doesn't exist: report a warning and continue with other paths.
Resolve all paths to absolute. Deduplicate.
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.
- 4d ago First seen · 182 lines · 67 tokens per session scan A b6b36ac3e5a4
prose-review-docs is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 1,629 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.
Other commands, from other repositories
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
csv-to-excel
Convert a CSV into a formatted Excel workbook.
csv-to-numbers
Convert a CSV into a formatted Numbers workbook.
doc-to-deck
Turn a Pages or Word document into a compelling slide deck.
sheet-report
Analyze a Numbers or Excel file and generate a report with charts.
excel-to-numbers
Convert an Excel workbook to Numbers.