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.
git 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/math-olympiad)<a href="https://agentmods.dev/plugins/anthropics/claude-plugins-official/math-olympiad"><img src="https://agentmods.dev/badge/plugins/anthropics/claude-plugins-official/math-olympiad.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
math-olympiad 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- math-olympiad — 100% identical, 0 lines differ
What it actually says
{
"name": "math-olympiad",
"description": "Solve competition math (IMO, Putnam, USAMO) with adversarial verification that catches what self-verification misses. Fresh-context verifiers attack proofs with specific failure patterns. Calibrated abstention over bluffing.",
"author": {
"name": "Anthropic",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 163 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.
- 4d ago First seen · 9 lines scan A 8c74f63e67cb
math-olympiad is a plugin published in the GitHub repository anthropics/claude-plugins-official (35,987 stars, last pushed 2d 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 2026-09-03.
Other plugins, from other repositories
rust-learner
Learn Rust language features and crate updates using Actionbook + agent-browser.
evolution
Eleven agent skills for thinking better, one per method: clarify the question, learn something new, solve the problem, decide, and know yourself.
anki-connect
This skill is for interacting with Anki through AnkiConnect, and should be used whenever a user asks to interact with Anki, including to read or modify decks, notes, cards, models, media, or sync operations.
explain-this
Create distill-style interactive explainers - single-file, zero-dependency HTML with hand-built Canvas figures - from documents, web research, or a codebase, with a fact-checking gate that supports, corrects, or cuts every claim.
anthropics-example-skills
Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling.
gan-zhong-xue
A learning add-on that turns AI-made code changes into guided, explainable understanding. It uses a question-and-answer process so developers can restate the reasoning and apply it elsewhere.