sandy-cli

A command-line add-on for running TypeScript scripts in temporary isolated virtual machines or Docker containers. The scripts can use the AWS SDK to query Amazon Web Services resources and obtain credentials through the instance metadata service.

In plain words
What is it for?
It helps run read-only AWS queries and TypeScript automation that needs AWS credentials through shell commands.
Why use it?
It lets developers investigate AWS resources or run AWS-related automation in an isolated environment without placing credential-handling instructions directly in the script.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/jamestelfer/sandy/sandy-cli
Any agent
npx skills add jamestelfer/sandy --skill sandy-cli
Clone the repo
git clone --depth 1 https://github.com/jamestelfer/sandy

Made for: Claude Code, Codex.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 179 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00054 $0.00179
Opus 5 $0.00027 $0.00089
Sonnet 5 $0.00011 $0.00036
Haiku 4.5 $0.00005 $0.00018

Measured 2d ago against content hash ee82798a9eb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

plugins/cli/skills/sandy-cli/SKILL.md · 24 lines

What it actually says

Sandy (CLI)

This plugin bootstraps the sandy command-line tool. Sandy's real instructions live in its prime output, not here.

First action

Run in a shell:

sandy prime

Read its complete output before doing anything else. It documents the available sandy subcommands, the IMDS credential flow, and the sandy resource sandy://skills/cli/resources/... commands you need for script-authoring guidance.

Follow every resource link sandy prime gives you before writing or running a script.

Changes

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.

  1. 2d ago First seen · 24 lines · 54 tokens per session scan A ee82798a9eb3

Subscribe to this mod's changes

sandy-cli is a skill published in the GitHub repository jamestelfer/sandy (7 stars, last pushed 28d ago), licensed Apache-2.0. It adds 54 tokens to every session and 179 once invoked, about $0.0003 per session on Opus 5. 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.