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.
/plugin marketplace add ihudak/ihudak-claude-plugins/plugin install prose-styleWrote 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-style-refresh)<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/prose-style-refresh"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/prose-style-refresh/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-style-refresh"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/prose-style-refresh.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 | $0.00072 | $0.01925 |
| Opus 5 | $0.00036 | $0.00962 |
| Sonnet 5 | $0.00014 | $0.00385 |
| Haiku 4.5 | $0.00007 | $0.00193 |
Grade A, and why
prose-style-refresh 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh the prose style overlay
Regenerates the overlay rules from your configured style-guide source. The plugin
ships no vendor's style guide and this command fetches from no fixed site: the source
is whatever your source.yml declares, or whatever you pass on the command line.
Arguments
| Argument | Example | Behaviour |
|---|---|---|
| (none) | /prose-style-refresh |
Uses the configured source.yml |
--source <url> |
--source https://style.example.com/docs |
One-off web source; may be repeated |
--from <path> |
--from ~/company-style-guide/ |
One-off local directory or file source |
--rules <path> |
--rules ~/style/rules |
Write to this overlay directory instead of the discovered one |
--dry-run |
--dry-run |
Report what would change; write nothing |
Procedure
0. Resolve the baseline directory
${CLAUDE_PLUGIN_ROOT} does not expand in a slash-command body. Invoke the
prose-style-rules skill (Skill tool, skill: "prose-style:prose-style-rules"), which
resolves it, and take from it the absolute path of the shipped baseline directory —
the one holding terminology.md, word-list.md, and the other six reference files.
Everything below calls that resolved path <baseline>. It is a read-only input to
this command: the structure to map onto, and the one path that must never be written to.
1. Resolve the overlay directory (the write target)
Take the FIRST that resolves:
--rules <path>, when given.<repo-root>/.prose-style/rules/—<repo-root>fromgit rev-parse --show-toplevel, falling back to the working directory.$PROSE_STYLE_PATH.
If none exists yet, tell the user which path you would create — default
<repo-root>/.prose-style/rules/ — and ask for confirmation before creating it. Do not
create a directory tree unasked.
The shipped baseline at <baseline> is never a write target.
It is the vendor-neutral fallback, it is reinstalled with the plugin, and anything
written there is lost on the next update. Refuse a --rules path that resolves inside
<baseline> or its parent plugin directory, and say why.
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 · 189 lines · 72 tokens per session scan A 8ac244689ff2
prose-style-refresh is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,925 once invoked, about $0.0004 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
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.
cloudflare-r2:presigned-url
Generate presigned URLs for secure client-side uploads or downloads.
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
infogenius
Research-First Image Generation - Facts → Visual Prompt → High-Quality Image.
watch
You are executing the /hydra:watch command. Live monitoring of all background agents with real-time status updates.
ops
Weekly operations loop — triage the inquiry inbox, advance the CRM pipeline, sweep open PRs across repos, and surface the content plan. Loads the ops skill.