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/fprochazka/claude-code-pluginsWrote 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/fprochazka/claude-code-plugins/agent-roles)<a href="https://agentmods.dev/plugins/fprochazka/claude-code-plugins/agent-roles"><img src="https://agentmods.dev/badge/plugins/fprochazka/claude-code-plugins/agent-roles/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/fprochazka/claude-code-plugins/agent-roles"><img src="https://agentmods.dev/badge/plugins/fprochazka/claude-code-plugins/agent-roles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-roles 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 12d 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
{
"$schema": "https://anthropic.com/claude-code/plugin.schema.json",
"name": "agent-roles",
"version": "0.4.0",
"description": "Three roles injected at the start of every agent — the top-level session orchestrates and delegates, a task worker ends its turn with findings, a resident worker stays alive and reports by message",
"author": {
"name": "Filip Procházka",
"url": "https://github.com/fprochazka"
},
"license": "MIT",
"homepage": "https://github.com/fprochazka/claude-code-plugins/tree/master/plugins/agent-roles",
"dependencies": [
"noisy-tools-in-subagent"
],
"userConfig": {
"resident_agent_types": {
"type": "string",
"multiple": true,
"title": "Resident agent types",
"description": "Agent types that stay alive for a whole run and report through SendMessage; they get the resident worker role instead of the task worker role. glab:mr-watch is always included."
}
}
}
What it installs
The manifest is a name and a version. 2 hooks travel with it, and installing the plugin installs all of 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.
- 12d ago Changed 0404a2f3a620
- 1mo ago Changed · +8 lines 33a23fdca90a
- 1mo ago Changed a5cb8b688494
- 1mo ago Changed 4a643832aae1
- 1mo ago First seen · 16 lines scan A 3d05846fce84
agent-roles is a plugin published in the GitHub repository fprochazka/claude-code-plugins (15 stars, last pushed 12d ago), licensed MIT. 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 2026-09-06.
Other plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.