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/protonium-labs/protonium-marketplaceWrote 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/protonium-labs/protonium-marketplace/marketplace)<a href="https://agentmods.dev/plugins/protonium-labs/protonium-marketplace/marketplace"><img src="https://agentmods.dev/badge/plugins/protonium-labs/protonium-marketplace/marketplace/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/protonium-labs/protonium-marketplace/marketplace"><img src="https://agentmods.dev/badge/plugins/protonium-labs/protonium-marketplace/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
protonium marketplace 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": "protonium",
"owner": {
"name": "Protonium",
"email": "[email protected]"
},
"metadata": {
"description": "Protonium plugin marketplace - AI agents and productivity tools for Claude.",
"version": "1.1.0"
},
"plugins": [
{
"name": "axiomcore",
"source": {
"source": "url",
"url": "https://github.com/protonium-labs/axiomcore-plugin.git"
},
"description": "Dedicated project management agent for professional and personal use: enforced structure, plan-approve-execute discipline, agile or WBS-based project creation, wiki memory, optional voice/brand/todos/dev-planning modules.",
"category": "productivity"
},
{
"name": "axiombuild",
"source": {
"source": "url",
"url": "https://github.com/protonium-labs/axiombuild-plugin.git"
},
"description": "Bookkeeping for spec-driven coding projects: owns the inbox of feature documents waiting to be built, records which one is open, and archives each with a changelog line when it lands. It does not plan, implement or verify - the superpowers plugin does that, with the repository readable. Pairs with AxiomCore, which writes the feature documents.",
"category": "development"
}
]
}
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 1eda91859468
- 11d ago First seen · 32 lines scan A e216df13062c
protonium marketplace is a plugin published in the GitHub repository protonium-labs/protonium-marketplace (0 stars, last pushed 2d 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 2026-08-31.
Other plugins, from other repositories
neo4j-skills
Agent skills for Neo4j — Cypher queries, graph modeling, drivers, imports, GraphRAG, GDS, vector indexes, Aura provisioning, and more.
neo4j-skills
Agent skills for Neo4j graph database — Cypher queries, graph modeling, drivers, imports, GraphRAG, GDS, vector indexes, and Aura provisioning.
labyrinth-analytics-claude-plugins marketplace
Plugin marketplace listing 2 plugins: loreconvo, loredocs.
loreconvo
Vault your Claude conversations. Captures session decisions, artifacts, and context across Code, Cowork, and Chat. Organizes memory by project, skill, and persona. Never re-explain yourself again.
loredocs
Searchable, organized, version-tracked knowledge base for your AI projects. Store documents, tag them, search across them, and inject context into any Claude conversation.
damascus-ink marketplace
A collection of three open legal skills for Russian law, covering grammar, logic, and rhetoric. It is released under the MIT licence, which permits broad reuse with the licence notice kept.