wolfram-agent-skills

Install

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.

Security

Grade A, and why

wolfram-agent-skills 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.

.claude-plugin/marketplace.json · 32 lines

What it actually says

{
	"name":"wolfram-agent-skills",
	"owner":{
		"name":"Richard Hennigan",
		"email":"[email protected]"
	},
	"metadata":{
		"description":"A collection of Wolfram agent skills",
		"version":"2.2.10"
	},
	"plugins":[
		{
			"name":"wolfram-language-development",
			"description":"A full Wolfram Language development environment with code evaluation, documentation search, symbol inspection, static analysis, and test execution.",
			"source":"./AgentSkills/Skills",
			"strict":false,
			"skills":[
				"./wolfram-language",
				"./wolfram-notebooks"
			]
		},
		{
			"name":"wolfram-alpha",
			"description":"Wolfram|Alpha queries and context retrieval.",
			"source":"./AgentSkills/Skills",
			"strict":false,
			"skills":[
				"./wolfram-alpha"
			]
		}
	]
}

Changes

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.

Related

Other plugins, from other repositories