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 Sangkwun/sandynpx agentmods add plugins/sangkwun/sandy/sandy-skillgit clone --depth 1 https://github.com/Sangkwun/sandyGrade A, and why
sandy 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.
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",
"description": "MCP action building blocks - Replay tool sequences to save tokens. Use for: (1) Full automation when all steps are deterministic, (2) Micro patterns like click-and-wait or scroll-and-wait where Sandy executes actions, then LLM calls screenshot for visual analysis.",
"version": "1.5.0",
"author": {
"name": "sangkwun"
},
"repository": "https://github.com/Sangkwun/sandy",
"license": "Apache-2.0",
"keywords": ["mcp", "automation", "scenario", "replay", "deterministic"],
"skills": "./skills/"
}
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.
- 2d ago First seen · 13 lines scan A 25dbd6cd8197
sandy is a plugin published in the GitHub repository Sangkwun/sandy (14 stars, last pushed 6mo 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 2026-08-30.
Other plugins, from other repositories
lattice
Lattice — the grid underneath. Type one sentence about a game and get an isometric, deterministic, zero-asset game you can play in a browser.
lattice
Build an isometric game from one sentence. /lattice picks the shape, installs the kit, wires it, gets to a running screen, then opens it in a browser and looks at it.
agent-pragma
Plugin marketplace listing 1 plugin: pragma.
pragma
Deterministic linting hooks, semantic code validators, and a multi-LLM advisory council. Enforces coding rules mechanically — not by suggestion.
seldonframe
Plugin marketplace listing 1 plugin: reelier.
reelier
Ships two Agent Skills and nothing else: reelier-replay freezes a repeatable tool-call job into a deterministic replay with a receipt per run, and reelier-write-safety covers bounding an agent's writes before you grant them. Skill-only package — it includes no MCP servers.