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/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/cloud-inference-skills)<a href="https://agentmods.dev/plugins/gaelic-ghost/socket/cloud-inference-skills"><img src="https://agentmods.dev/badge/plugins/gaelic-ghost/socket/cloud-inference-skills/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/gaelic-ghost/socket/cloud-inference-skills"><img src="https://agentmods.dev/badge/plugins/gaelic-ghost/socket/cloud-inference-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cloud-inference-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 1mo 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": "cloud-inference-skills",
"source": "./plugins/cloud-inference-skills",
"description": "Cloud AI inference, training, conversion, and GPU workflows.",
"category": "developer-tools",
"tags": [
"ai",
"cloud",
"mcp"
],
"mcpServers": "./.mcp.json",
"strict": false
}What it installs
The manifest is a name and a version. 4 skills travel with it, and installing the plugin installs all of them — 160 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside marketplace.json#cloud-inference-skills in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 13 lines scan A dfc6b90cc307
cloud-inference-skills is a plugin published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 1mo 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 2026-09-03.
Other plugins, from other repositories
data-analytics
Data governance, warehouse and semantic modeling, business intelligence, and AI/ML governance.
superb
Personal skill collection for Claude Code and Codex, invoked as superb: . setup installs what the others need; craft turns a vague product idea into a decision-rich brief; pipeline v2 drives a settled idea through approved file-backed plans and durable execution state to a finished branch; pipeline-auto does the.
embedded-systems-architect
Evidence-driven embedded systems & edge-AI development skill: vendor-doc intake, cross-layer feasibility reasoning, model deployment compatibility, performance estimation, and hard-gated flashing/recovery guidance.
security
Web application firewall management as code with Doorman: create rules, block IPs, rate limit, protect against bots, and deploy WAF configs to Vercel and Cloudflare.
agile-ledger
Plain-Markdown Scrum/Agile product management for Claude Code — backlog, sprints, board, velocity, releases, and GitHub traceability from slash commands. The ledger lives in its own repo, one folder per project, so code repos stay clean.
comparative-landscape-brief
Market intelligence for product and GTM leaders. Five skills sharing one hardened research subagent that verifies quantitative claims against third-party sources and refuses instructions embedded in fetched pages. Compare 3 to 8 entities side by side, brief one company in depth, build a competitive landscape and…