Apache Magpie is a framework of agent-assisted workflows for maintaining Apache software projects, including issue triage, pull-request review, contributor mentoring, and security-report handling. Apache maintainers and developers use it to delegate repetitive project work to coding agents while retaining human review. Its catalogue entries are the skills, instructions, plugin, and settings that implement these workflows.
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/apache/magpieWrote 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/apache/magpie/magpie-security)<a href="https://agentmods.dev/plugins/apache/magpie/magpie-security"><img src="https://agentmods.dev/badge/plugins/apache/magpie/magpie-security/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/apache/magpie/magpie-security"><img src="https://agentmods.dev/badge/plugins/apache/magpie/magpie-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
magpie-security 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": "magpie-security",
"description": "Apache Magpie \u2014 security-issue handling lifecycle \u2014 import through CVE publication, triage, sync, dedup, invalidate. Maintainer-only.",
"version": "0.9.0.dev202610192305",
"author": {
"name": "Apache Magpie",
"url": "https://magpie.apache.org/"
},
"homepage": "https://magpie.apache.org/",
"repository": "https://github.com/apache/magpie",
"license": "Apache-2.0",
"skills": "./skills"
}
What it installs
The manifest is a name and a version. 15 skills travel with it, and installing the plugin installs all of them — 1,036 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill issue-fix A 81 tokens
- Skill issue-import A 60 tokens
- Skill issue-import-from-pr A 67 tokens
- Skill issue-sync A 99 tokens
- Skill issue-deduplicate A 81 tokens
- Skill issue-import-from-md A 69 tokens
- Skill issue-import-from-scan A 60 tokens
- Skill issue-import-via-forwarder A 82 tokens
- Skill issue-invalidate A 56 tokens
- Skill issue-triage A 81 tokens
- Skill model-verify A 73 tokens
- Skill model-prepare A 66 tokens
- Skill model-update A 60 tokens
- Skill tracker-stats-dashboard A 22 tokens
- Skill cve-allocate B 79 tokens
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 a4f321a227a9
- 4d ago Changed 8ff72289bb86
- 6d ago Changed 1a207228279a
- 9d ago Changed 42c043661b1c
- 10d ago Changed 23b3e1aec6bf
- 11d ago Changed d07ab349f362
- 13d ago Changed 9b6baecdff2e
- 24d ago Changed 39f61ef0e13c
- 25d ago Changed aca4d6101a57
- 28d ago First seen · 14 lines scan A 0ebe83b2058c
magpie-security is a plugin published in the GitHub repository apache/magpie (120 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 2026-08-30.
Other plugins, from other repositories
contrastapi
47 security research tools over remote MCP — CVE + EPSS/KEV, MITRE CWE catalog + KEV detail, domain audit + DNS/SSL/WHOIS/subdomain enum + WAF detect, IP threat intel + cloud/Tor/FireHOL classification, IOC enrichment (ThreatFox/Feodo/URLhaus), email/phone/username OSINT, code security checks, MITRE ATLAS AI/ML attack.
find-cve-agent
CVE hunting harness for open source security research. A 5-agent team that systematically finds, validates, and reports real vulnerabilities in open source packages.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.