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/jamestelfer/sandyWrote 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/jamestelfer/sandy/cli)<a href="https://agentmods.dev/plugins/jamestelfer/sandy/cli"><img src="https://agentmods.dev/badge/plugins/jamestelfer/sandy/cli/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/jamestelfer/sandy/cli"><img src="https://agentmods.dev/badge/plugins/jamestelfer/sandy/cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sandy-cli 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 6d 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-cli",
"version": "0.11.0",
"description": "Sandy: sandboxed TypeScript execution for AWS queries via the sandy CLI",
"author": {
"name": "James Telfer"
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 54 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 6d ago Changed 57a20f442069
- 7d ago Changed 4745305d7239
- 8d ago Changed df8aa8b7a8eb
- 1mo ago First seen · 9 lines scan A 5b6799c7c059
sandy-cli is a plugin published in the GitHub repository jamestelfer/sandy (7 stars, last pushed yesterday), 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
aws-agent-skills
Collection of AWS engineering skills for IAM, Lambda, DynamoDB, S3, and 14 other core AWS services.
nable
Prices what your coding agent is about to do before it runs: asks before costly launches and destroys, tracks AI spend, and answers cost questions across AWS, Azure, GCP, Kubernetes and AI providers. Local, read-only. The guard is on once the plugin is installed; nable guard off pauses it. Credentials stay on your…
stack
Plan and configure supported project services from Claude Code with Stack's CLI and MCP bridge.
cloud-cost-agent
Native-first FinOps agent for AWS, GCP, and Azure. Finds cloud savings using each provider's own CLIs and recommendation engines (Cost Explorer/Compute Optimizer, GCP Recommender, Azure Advisor).
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.