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.
/plugin marketplace add robcsaszar/prosenpx agentmods add plugins/robcsaszar/prose/marketplacegit clone --depth 1 https://github.com/robcsaszar/proseGrade A, and why
prose 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 yesterday.
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.
What it actually says
{
"name": "prose",
"owner": {
"name": "Rob Csaszar",
"url": "https://nhg.design"
},
"plugins": [
{
"name": "robcsaszar-prose",
"source": "./",
"description": "Draft and review skill for prose that detects AI writing patterns and rewrites in an authentic, channel-appropriate voice.",
"version": "0.9.0"
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 16 lines scan A d88f3ffab371
prose is a plugin published in the GitHub repository robcsaszar/prose (0 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
writing-agent-marketplace
Writing Agent 的 Claude Code 插件市场.
economist-style-plugins
Editorial-style plugins for Claude Code: apply The Economist style guide to your writing.
prose-humanizer
Install Prose Humanizer as a Claude Code plugin.
prose-humanizer
Draft, rewrite, voice-match, and audit prose without inventing facts or flattening the writer.
limitless
Plugin marketplace listing 4 plugins: limitless, after-hours, pyro-kit, codies-memory.
limitless
Pyro's curated Claude Code skill pack: article-pack, Codies Research, Surface-First Development, SFD v2 (docket-emitting contract handoff), SearXNG, Suno Pack (lyric craft, inspiration audits, rendering, experiment lanes, saga-synced journals), Hivemind, Dojo, Learn Anything (tier-gated beginner→expert curricula), and.