Claude Code Plugins Directory is a marketplace containing plugins for Claude Code, including tools, commands, skills, agents, hooks, and model context servers. Claude Code users browse it to install Anthropic-maintained or approved third-party extensions.
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-plugins-officialnpx agentmods add plugins/anthropics/claude-plugins-official/ralph-loopgit clone --depth 1 https://github.com/anthropics/claude-plugins-officialWrote 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/anthropics/claude-plugins-official/ralph-loop)<a href="https://agentmods.dev/plugins/anthropics/claude-plugins-official/ralph-loop"><img src="https://agentmods.dev/badge/plugins/anthropics/claude-plugins-official/ralph-loop.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
ralph-loop 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- ralph-loop — 100% identical, 0 lines differ
- ralph-loop — 100% identical, 0 lines differ
- ralph-loop — 88% identical, 1 lines differ
What it actually says
{
"name": "ralph-loop",
"version": "1.0.0",
"description": "Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.",
"author": {
"name": "Anthropic",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 2 commands travel with it, and installing the plugin installs all of them — 10 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 First seen · 10 lines scan A 4a92d87b112e
ralph-loop is a plugin published in the GitHub repository anthropics/claude-plugins-official (35,912 stars, last pushed today), 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 2026-09-03.
Other plugins, from other repositories
09.-workflows-and-apps
Discover, run, build, and publish Scenario workflows, the multi-step pipelines users call apps.
paleo
🦴 paleo — personal token-saving skill collection (Claude Code / Codex / Gemini / Hermes). 7 composable skills: terse output, auto-detect, context trim, budget cap, conversation compress, summary, JSON compact.
email-assistant
Autonomous email triage and reply system. Drafts replies in your voice, saves as Gmail drafts, and learns from your corrections.
change-management
Stakeholder impact mapping, change readiness assessment, sponsor roadmaps, communications planning, and resistance diagnosis — the people side of transformation, separate from program governance and operating model design.
obshare-cli
Upload Obsidian Markdown documents to Feishu (Lark) cloud documents. Skills for environment setup, configuration, direct-share plugin workflows, uploading notes, managing permissions, and viewing upload history.
qmd-knowledge
Project-specific knowledge management system using qmd MCP server. Captures learnings, issue notes, and conventions in a searchable knowledge base.