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 anthropics/claude-tag-pluginsnpx agentmods add plugins/anthropics/claude-tag-plugins/confluencegit clone --depth 1 https://github.com/anthropics/claude-tag-pluginsGrade A, and why
confluence 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 3d 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
{
"name": "confluence",
"version": "1.0.0",
"description": "Access Confluence pages, spaces, and comments — search, read, create, and update content.",
"author": { "name": "Anthropic" },
"homepage": "https://github.com/anthropics/claude-tag-plugins"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 138 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.
- 3d ago First seen · 8 lines scan A 4b04baa05ae1
confluence is a plugin published in the GitHub repository anthropics/claude-tag-plugins (46 stars, last pushed 21d 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
google-workspace
Google Workspace for Claude Code — Gmail, Calendar, Drive, Docs, Sheets, Forms, and Tasks CLIs and skills, plus a gw api/gw schema escape hatch to any Google API. Multi-account OAuth with keyring-backed tokens.
notes-recover
Marketplace-ready starter plugin for the local NotesRecover MCP workflow on copied-evidence case roots.
mathtype-for-word
Create and validate native MathType equations in Word and PowerPoint, including Word-native equation numbers and references.
repo-to-content
Convert GitHub repos into polished content (PDF, white paper, internal doc, public-docs publication) via Typst, with optional AI banner generation and multi-target publishing.
deepread
DeepRead OCR — extract text and structured data from PDFs and images with 97%+ accuracy. Includes setup, API reference, PII redaction, form filling, and BYOK.
collate
历史论文 OCR 校对工作流：PDF 预处理去水印去角标、MinerU OCR、三类文献（繁体古籍 / 民国排印 / 现代简体）校对、公众号排版导出.