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 richfrem/agent-plugins-skillsnpx agentmods add plugins/richfrem/agent-plugins-skills/agent-scaffoldersgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/agent-scaffolders)<a href="https://agentmods.dev/plugins/richfrem/agent-plugins-skills/agent-scaffolders"><img src="https://agentmods.dev/badge/plugins/richfrem/agent-plugins-skills/agent-scaffolders.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
agent-scaffolders 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": "agent-scaffolders",
"version": "2.1.0",
"description": "Meta-plugin containing ecosystem generation and evolution auditing primitives. Includes scaffolding for Agent Skills, Plugins, CLI sub-agents, custom GitHub Copilot agents, GitHub Agentic Workflows (gh-aw), CI/CD Smart Failure agents, Azure Foundry agents, and skill evolution auditing (audit-skill).",
"author": {
"name": "Richard Fremmerlid"
},
"repository": "https://github.com/richfrem/agent-plugins-skills",
"license": "MIT",
"keywords": [
"scaffolder",
"plugin-generator",
"skill-generator",
"agent-tooling",
"github-agents",
"gh-aw",
"audit-skill",
"skill-auditor"
],
"capabilities": [
"skill-scaffolding",
"plugin-scaffolding",
"code-generation",
"skill-auditing"
]
}
What it installs
The manifest is a name and a version. 33 skills, 2 plugins travel with it, and installing the plugin installs all of them — 1,997 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill audit-plugin A 135 tokens
- Skill create-command A 40 tokens
- Skill manage-marketplace A 61 tokens
- Skill analyze-plugin A 107 tokens
- Skill ecosystem-authoritative-sources A 52 tokens
- Skill eval-autoresearch-fit A 85 tokens
- Skill create-plugin A 46 tokens
- Skill create-skill A 59 tokens
- Skill fix-plugin-paths A 133 tokens
- Skill path-reference-auditor A 96 tokens
- Skill synthesize-learnings A 66 tokens
- Skill ecosystem-standards A 41 tokens
- Skill l5-red-team-auditor A 62 tokens
- Skill mine-plugins A 82 tokens
- Skill audit-skill A 35 tokens
- Skill self-audit A 76 tokens
- Skill audit-plugin-l5 A 29 tokens
- Skill create-hook A 46 tokens
- Skill mine-skill A 67 tokens
- Skill convert-plugin-to-apm A 53 tokens
- Skill create-apm-package A 62 tokens
- Skill update-ecosystem-index A 26 tokens
- Skill create-agentic-workflow A 79 tokens
- Skill create-sub-agent A 55 tokens
- Skill install-apm-package A 69 tokens
- Skill compile-apm-package A 74 tokens
- Skill create-azure-agent A 48 tokens
- Skill create-stateful-skill A 53 tokens
- Skill create-docker-skill A 45 tokens
- Skill create-github-action A 49 tokens
- Skill create-mcp-integration A 46 tokens
- Skill flawed-skill A 20 tokens
- Skill examples A 0 tokens
- Plugin gold-standard-test 1 inside A not measured
- Plugin goodhart-plugin 1 inside A not measured
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 · 27 lines scan A e7a0d56986fe
agent-scaffolders is a plugin published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), 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 2026-09-03.
Other plugins, from other repositories
rails-consultant
A collection of skills for Rails development and consulting, with an emphasis on learning, communication, and client success.
agentic-seo
Agentic SEO Skills adds project brains, data-backed SEO analysis, content workflows, and technical SEO checks to Agentic SEO.
vertex-ai-provider
Use Claude models via Google Vertex AI with real-time token tracking and cost analytics.
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.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.