sandy

A tool for running TypeScript scripts in disposable sandboxed microVMs or Docker containers, with access to AWS services through temporary credentials.

In plain words
What is it for?
Use it for read-only AWS queries and TypeScript automation that needs AWS SDK access.
Why use it?
It lets you investigate AWS resources or automate tasks in an isolated environment instead of running scripts directly on your machine.

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

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,703 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 $0.00045 $0.01703
Opus 5 $0.00023 $0.00851
Sonnet 5 $0.00009 $0.00341
Haiku 4.5 $0.00005 $0.00170

Measured 2d ago against content hash 496a783f889a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade 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.

The scan reads SKILL.md. This mod also ships 2 executable files (resources/examples/ec2_describe.ts, resources/examples/ecs_services.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

embedded/skills/cli/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sandy

Sandy executes TypeScript scripts in disposable sandboxed environments (Shuru microVMs or Docker containers) with AWS credentials from IMDS.

The CLI uses explicit sessions. Create one first, then run scripts from that session’s scripts/ directory.

Setup

Read the scripting guide before writing scripts:

sandy resource sandy://skills/cli/resources/scripting-guide.md

This guide defines runtime constraints, available AWS SDK packages, and the required async generator pattern.

IMDS port

Start an IMDS server separately and pass its port to sandy run and sandy check connect.

CLI commands

sandy image

Create or delete the Sandy sandbox image.

sandy image create
sandy image delete
sandy image delete --force

sandy session create

Create a session and print the session name plus scripts path.

sandy session create

sandy check

Verify sandbox health. Each check creates and deletes an ephemeral session; no session argument is accepted.

sandy check baseline
sandy check connect --imds-port 9001
sandy check connect --imds-port 9001 --region ap-southeast-2

sandy run

Run a TypeScript script from <session>/scripts/.

sandy run --session happy-fox-trail --script inventory.ts --imds-port 9001
sandy run --session happy-fox-trail --script inventory.ts --imds-port 9001 --region ap-southeast-2
sandy run --session happy-fox-trail --script inventory.ts --imds-port 9001 -- arg1 arg2

Options:

Flag Required Description
--session yes Session name
--script yes Script path relative to <session>/scripts/
--imds-port yes Port of the running IMDS server
--region no AWS region (default us-west-2)
-- no Arguments passed as process.argv inside the script

Session layout on the host:

  • .sandy/<session>/scripts/ mounted read-only at /workspace/scripts
  • .sandy/<session>/output/ mounted read-write at /workspace/output

Read the full file on GitHub · 189 lines

Files

What ships with it

4 files beside SKILL.md 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.

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 · 189 lines · 45 tokens per session scan A 496a783f889a

Subscribe to this mod's changes

sandy is a skill published in the GitHub repository jamestelfer/sandy (7 stars, last pushed 28d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,703 once invoked, about $0.0002 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.