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/travsteward/openwriterWrote 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/plugins/travsteward/openwriter/claude-plugin)<a href="https://agentmods.dev/plugins/travsteward/openwriter/claude-plugin"><img src="https://agentmods.dev/badge/plugins/travsteward/openwriter/claude-plugin/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/plugins/travsteward/openwriter/claude-plugin"><img src="https://agentmods.dev/badge/plugins/travsteward/openwriter/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
openwriter 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": "openwriter",
"displayName": "OpenWriter",
"version": "0.47.0",
"description": "A local markdown editor your agent writes in. Claude drafts and edits documents through MCP tools, and you accept or reject each change in your browser. Plain .md files on your disk.",
"author": {
"name": "OpenWriter",
"url": "https://github.com/travsteward/openwriter"
},
"homepage": "https://github.com/travsteward/openwriter",
"repository": "https://github.com/travsteward/openwriter",
"license": "MIT",
"icon": "./logo.png",
"keywords": [
"writing",
"editor",
"markdown",
"documents",
"review"
]
}
What it installs
The manifest is a name and a version. 1 skill, 2 agents, 1 MCP server travel with it, and installing the plugin installs all of them — 294 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 Changed aff88ddd9c2c
- 8d ago Changed 2f0416392ac2
- 9d ago First seen · 22 lines scan A 97b3412b608d
openwriter is a plugin published in the GitHub repository travsteward/openwriter (35 stars, last pushed today), 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 2026-10-07.
Other plugins, from other repositories
humanize-pro
Make AI-drafted text read like a person wrote it, for the channel it ships in. De-AI pass, channel fit, voice profiles, and a two-gate audit before delivery.
ai-writing-rules
Makes Claude write like a sharp, plain-spoken human. Loads 29 researched anti-AI-writing patterns at session start and checks every file it writes for tells.
writing-humanizer
A writing tool that removes common signs of AI-generated text and makes prose sound more natural, mainly in Traditional Chinese used in Taiwan.
linkedin-maxxing
17 skills for substance-first LinkedIn growth. Refuses templates, refuses scaled outreach, optimizes for dwell time and comment quality instead of detection-evasion. Includes a Wikipedia-based humanizer that the writing skills invoke as a final polish step.
before-you-build
Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts.
git-sidebar
A lazygit-style side pane: every worktree of the repository and its local branches as rows you click. A worktree row moves the session there with /cd; a branch row shows its last commits and offers switch (clean tree only) or open worktree. Docked floor to ceiling beside the transcript in the fullscreen layout, above…