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 chainguard-demo/claude-pluginsnpx agentmods add plugins/chainguard-demo/claude-plugins/chainguard-codegengit clone --depth 1 https://github.com/chainguard-demo/claude-pluginsGrade A, and why
chainguard-codegen 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 2d 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": "chainguard-codegen",
"description": "Generate secure Dockerfiles and apko configurations, and migrate existing Dockerfiles to use Chainguard Containers.",
"version": "0.1.0",
"author": {
"name": "Chainguard",
"email": "[email protected]",
"url": "https://chainguard.dev"
},
"homepage": "https://edu.chainguard.dev",
"repository": "https://github.com/chainguard-dev/edu",
"license": "Apache-2.0",
"keywords": [
"chainguard",
"dockerfile",
"security",
"containers",
"wolfi",
"apko",
"melange",
"codegen"
]
}
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.
- 2d ago First seen · 24 lines scan A 7417308e9250
chainguard-codegen is a plugin published in the GitHub repository chainguard-demo/claude-plugins (7 stars, last pushed 3mo 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 2026-08-31.
Other plugins, from other repositories
claude-code-toolkit
The most comprehensive toolkit for Claude Code -- 135 agents, 35 skills, 42 commands, 120 plugins, 19 hooks, 15 rules, 7 templates, and 6 MCP configs.
awesome-claude-code-toolkit
Complete developer toolkit for Claude Code.
a11y-audit
Full accessibility audit with WCAG compliance checking.
analytics-reporter
Generate analytics reports and dashboard configurations from project data.
android-developer
Android and Kotlin development with Jetpack Compose.
api-benchmarker
API endpoint benchmarking and performance reporting.