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/stemma-sh/stemmaWrote 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/stemma-sh/stemma/plugin)<a href="https://agentmods.dev/plugins/stemma-sh/stemma/plugin"><img src="https://agentmods.dev/badge/plugins/stemma-sh/stemma/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/stemma-sh/stemma/plugin"><img src="https://agentmods.dev/badge/plugins/stemma-sh/stemma/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
stemma 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 1mo 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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "stemma",
"displayName": "Stemma — DOCX tracked changes",
"version": "0.6.0",
"description": "Structure-aware Microsoft Word (.docx) editing with tracked changes, for agents. Open a document, read its outline/text, apply tracked-change edits, validate, and save — all as real Word tracked changes.",
"author": {
"name": "Stemma maintainers",
"url": "https://github.com/stemma-sh/stemma"
},
"homepage": "https://github.com/stemma-sh/stemma",
"repository": "https://github.com/stemma-sh/stemma",
"license": "MIT OR Apache-2.0",
"keywords": ["docx", "ooxml", "tracked-changes", "word", "redline", "agent"]
}
What it installs
The manifest is a name and a version. 1 MCP server travel with it, and installing the plugin installs all of 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.
- 1mo ago Changed 2acb7dc7cd52
- 1mo ago First seen · 16 lines scan A 67cf04354535
stemma is a plugin published in the GitHub repository stemma-sh/stemma (21 stars, last pushed 1mo ago), licensed Apache-2.0. 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 2026-08-30.
Other plugins, from other repositories
officeagent
Inspect and edit the Word, PowerPoint and Excel files in your project: Claude previews every change before it is saved, and Word edits arrive as tracked changes you accept or reject in Word.
brand-docs
AI on-brand document generator for Claude Code & Codex: turn a company's Word, PowerPoint or Excel template into unlimited on-brand .docx/.pptx/.xlsx. Extracts a reusable Brand Profile once - off-brand output impossible by construction. Skills: brand-docx, brand-pptx, brand-xlsx.
open-agreements
Local MCP extension for OpenAgreements workspace organization and contract template drafting.
deckprobe
Inspect PDF, Microsoft Office, and Apple iWork documents with bounded, deterministic probes.
kreuzberg
Extract document text, tables and metadata with the legacy Kreuzberg 4.x CLI and MCP tools.
bilirkisi-rapor-inceleme
Bilirkişi raporu analizi: görevlendirme kapsamına uygunluk, metodoloji ve dayanak denetimi, hesap ve maddi hata kontrolü, çelişki tespiti; gerekçeli itiraz ve ek rapor/yeni bilirkişi talebi taslağı.