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 jamestelfer/sandynpx agentmods add plugins/jamestelfer/sandy/mcpgit clone --depth 1 https://github.com/jamestelfer/sandyGrade A, and why
sandy-mcp 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": "sandy-mcp",
"version": "0.8.0",
"description": "Sandy: sandboxed TypeScript execution for AWS queries via MCP",
"author": {
"name": "James Telfer"
}
}
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 · 9 lines scan A c0e8f234d9b8
sandy-mcp is a plugin published in the GitHub repository jamestelfer/sandy (7 stars, last pushed 27d 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 2026-08-31.
Other plugins, from other repositories
prowler-plugins
Prowler Cloud Security for Claude Code.
ccmux
Drive the ccmux cross-harness CLI to dispatch work to other AI coding agents (Claude Code, Codex, Cursor, OpenCode, Pi, Gemini) through programmatic ccmux invoke calls. Requires the ccmux CLI on PATH.
defang
Deploy Docker Compose apps to your own cloud account using Defang. Includes a /defang:deploy skill and Defang MCP server integration.
jenkins-cli
GitHub CLI-style interface for Jenkins controllers - create multibranch jobs, inspect config.xml, and manage runs, logs, artifacts, credentials, nodes, and queues.
techneering
Techneering — open-source Claude Code plugin marketplace: spec-driven development workflows, execution discipline, and frontend design.
graph-engineering
Runs coding work as an explicit execution graph (DAG) instead of a natural-language conversation. Deterministic work is executed by the server with zero LLM calls, the points where a human steps in are declared in the graph, and run state is owned by the server rather than the conversation.