Agent skill

Sandbox AWS

Sign AWS requests (S3 and every other SigV4 service) in a Code node or CodeAct action, with NodeTool's signer running on the host

AGPL-3.0Auto-check passedBackend & APIs

Install Sandbox AWS

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-aws -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-aws --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/sandbox-packs/sandbox-aws .claude/skills/sandbox-aws && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "sandbox-aws" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-aws into .claude/skills/sandbox-aws/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-aws", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-aws

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-aws -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-aws --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/sandbox-packs/sandbox-aws .agents/skills/sandbox-aws && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "sandbox-aws" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-aws into .agents/skills/sandbox-aws/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-aws", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-aws -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-aws --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/sandbox-packs/sandbox-aws .cursor/skills/sandbox-aws && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "sandbox-aws" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-aws into .cursor/skills/sandbox-aws/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-aws", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/nodetool-ai/nodetool.git --path packages/sandbox-packs/sandbox-aws

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-aws -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-aws --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/sandbox-packs/sandbox-aws .gemini/skills/sandbox-aws && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "sandbox-aws" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-aws into .gemini/skills/sandbox-aws/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-aws", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-aws

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-aws -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/sandbox-packs/sandbox-aws .github/skills/sandbox-aws && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "sandbox-aws" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-aws into .github/skills/sandbox-aws/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-aws", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add nodetool-ai/nodetool --skill sandbox-aws -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install nodetool-ai/nodetool sandbox-aws --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nodetool-ai/nodetool.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/sandbox-packs/sandbox-aws .opencode/skills/sandbox-aws && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "sandbox-aws" agent skill from https://github.com/nodetool-ai/nodetool/tree/main/packages/sandbox-packs/sandbox-aws into .opencode/skills/sandbox-aws/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sandbox-aws", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: sandbox-aws
GitHub stars: 560
Token cost: ~849 tokens
SKILL.md length: 317 words
Files: 2
Skills in repo: 127
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Sign AWS requests (S3 and every other SigV4 service) in a Code node or CodeAct action, with NodeTool's signer running on the host

Tasks that involve File uploads and storage
SKILL.md covers sigv4 — sign a request, presign — a URL that… and Gotchas
Needs AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY

What it does

Sandbox AWS is an agent skill from nodetool-ai/nodetool. Sign AWS requests (S3 and every other SigV4 service) in a Code node or CodeAct action, with NodeTool's signer running on the host

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `package.json`).

It sits in Backend & APIs, covering File uploads and storage. It works with Amazon Web Services. The repository describes itself as: Agent-first Creative Workspace. The licence is AGPL-3.0.

When your agent uses it

Tasks that involve File uploads and storage

Example prompts

“/sandbox-aws”

Requirements

A credential in AWS_SECRET_ACCESS_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 339f069. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- AWS_ACCESS_KEY_ID
- AWS_SECRET_ACCESS_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sandbox AWS loads about 849 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 317 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~35
When it runs · the whole SKILL.md, loaded when a task matches: ~849

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nodetool-ai/nodetool at commit 339f069, republished under its AGPL-3.0 licence (© nodetool-ai). 317 words, ~849 tokens.

Download SKILL.mdSave it as .claude/skills/sandbox-aws/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: sandbox-aws
description: Sign AWS requests (S3 and every other SigV4 service) in a Code node or CodeAct action, with NodeTool's signer running on the host

AWS SigV4 in the sandbox

Specifier: @nodetool-ai/sandbox-aws. Import it at the top of the body.

S3 is an HTTP API, so fetch already reaches it. What the guest cannot do is sign the request: SigV4 is an HMAC-SHA256 chain over a canonical form of the request, and one wrong byte gives a signature mismatch that names nothing. This pack is a host module: the chain runs on the host and hands back headers.

Nothing here sends a request. Both exports are pure — they take a request and return a signed one. The call goes out through the guest's own fetch, so the run's fetch cap and its SSRF guard still apply.

sigv4 — sign a request

import { sigv4 } from "@nodetool-ai/sandbox-aws";

const accessKeyId = await nodetool.secrets.get("AWS_ACCESS_KEY_ID");
const secretAccessKey = await nodetool.secrets.get("AWS_SECRET_ACCESS_KEY");

const signed = await sigv4({
  method: "GET",
  url: "https://my-bucket.s3.us-east-1.amazonaws.com/?list-type=2&max-keys=100",
  region: "us-east-1",
  service: "s3",
  accessKeyId,
  secretAccessKey
});

const res = await fetch(signed.url, { method: signed.method, headers: signed.headers });
return { xml: await res.text() };

Options: method (default GET), url (required, absolute), region (default us-east-1), service (default s3), accessKeyId and secretAccessKey (required), sessionToken (for temporary STS credentials), headers, body, payloadHash.

Returns {url, method, headers} — never the body. Pass the same body value to fetch yourself, so bytes make one trip, not two.

Writing an object

const body = JSON.stringify(inputs.record);
const signed = await sigv4({
  method: "PUT",
  url: `https://my-bucket.s3.us-east-1.amazonaws.com/${inputs.key}`,
  region: "us-east-1", service: "s3",
  accessKeyId, secretAccessKey,
  headers: { "content-type": "application/json" },
  body
});
await fetch(signed.url, { method: "PUT", headers: signed.headers, body });

A Uint8Array body works the same way — from workspace.readBytes or a previous response.bytes().

presign — a URL that authorizes itself

import { presign } from "@nodetool-ai/sandbox-aws";

const url = await presign({
  method: "GET",
  url: "https://my-bucket.s3.us-east-1.amazonaws.com/report.pdf",
  region: "us-east-1", service: "s3",
  expiresIn: 3600,
  accessKeyId, secretAccessKey
});
return { url };

Returns the URL as a string. expiresIn is seconds, clamped to a week. The payload is unsigned, which is what makes a presigned PUT usable — whoever holds the URL supplies the body.

Gotchas

Every export is async. A host call is a round trip.
It signs; it does not send. Nothing reaches the network until you call fetch.
The signature is time-bound. It is stamped when you call sigv4, and AWS rejects one more than 15 minutes old. Sign immediately before fetching, not at the top of a long function.
Other services work too. Set service and region — dynamodb, sqs, lambda, bedrock. Only s3 skips path normalization, because an object key is a key.
10 MB of body per signature. Hash a bigger upload yourself and pass payloadHash, or use a presigned PUT.

Files

SKILL.md and 1 other file in packages/sandbox-packs/sandbox-aws of nodetool-ai/nodetool.

SKILL.md
package.json

Open the folder on GitHubat commit 339f069

Compare with similar skills

Sandbox AWS next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sandbox AWS compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Sandbox AWS this skillnodetool-ai/nodetool	560	—	~849	Automated safety check: Pass	AGPL-3.0	today
FoundatioFoundatioFx/Foundatio	2.1k	—	~3.9k	Automated safety check: Pass	Apache-2.0	yesterday
PhidownESA-PhiLab/phidown	105	—	~1k	Automated safety check: Pass	Apache-2.0	1 mo ago
Fftiers Opsborisachen/fftiers	202	—	~1.8k	Automated safety check: Warn	None	1 mo ago
Processing S3 Uploads With Step Functionsaws/agent-toolkit-for-aws	2.8k	—	~4k	Automated safety check: Pass	Apache-2.0	today
API Keysaws-samples/sample-host-openclaw-on-amazon-bedrock-agentcore	177	—	~825	Automated safety check: Pass	MIT-0	11 days ago

Similar skills

Foundatio
FoundatioFx/Foundatio
A skill your agent uses when working with Foundatio infrastructure abstractions for .NET -- caching, queuing, messaging, file storage, distributed locking, or background jobs.
2.1k GitHub stars~3.9k tokensUpdated yesterday
Backend & APIsAuto-check passed
Phidown
ESA-PhiLab/phidown
Search, filter, download, and analyze Copernicus Data Space products with the phidown project.
105 GitHub stars~1k tokensUpdated 1 mo ago
Backend & APIsAuto-check passed
Fftiers Ops
borisachen/fftiers
Operate the borischen.co fftiers pipeline — season rollover, run main.R, S3 deploy from Workbench or EC2.
202 GitHub stars~1.8k tokensUpdated 1 mo ago
Backend & APIsAuto-check: warnings
Processing S3 Uploads With Step Functions
aws/agent-toolkit-for-aws
Official
Deploy an event-driven workflow that routes S3 uploads to either Lambda or Fargate via Step Functions based on file size.
2.8k GitHub stars~4k tokensUpdated today
Backend & APIsAuto-check passed
API Keys
aws-samples/sample-host-openclaw-on-amazon-bedrock-agentcore
Official
Dual-mode API key storage — native file-based or AWS Secrets Manager.
177 GitHub stars~825 tokensUpdated 11 days ago
Backend & APIsAuto-check passed
Neon Functions
neondatabase/agent-skills
Official
Long-running, serverless Node.js HTTP functions deployed onto your Neon branch, with DATABASEURL injected automatically and compute that runs next to your data.
100 GitHub stars~12k tokensUpdated yesterday
Backend & APIsAuto-check: notes

More from nodetool-ai/nodetool

All 127 skills in this repo

Beat Sync Editing
nodetool-ai/nodetool
Cut a NodeTool timeline to music and shape its pacing — detect the beat grid, place cuts on phrases, pick a cut type, build speed ramps with time remap, and give the piece an arc.
560 GitHub stars~2.6k tokensUpdated today
Auto-check passed
Caption Titles
nodetool-ai/nodetool
Add and animate a consistent text layer on an existing NodeTool timeline.
560 GitHub stars~1.9k tokensUpdated today
Auto-check passed
Color Motion
nodetool-ai/nodetool
Choose and animate colour on a NodeTool timeline, including shape and text gradients, colour grades, 3D LUTs, and dither.
560 GitHub stars~2.3k tokensUpdated today
Auto-check passed
Commercial Beat Sheet
nodetool-ai/nodetool
Write a shootable, precisely timed commercial beat sheet and store it as a NodeTool storyboard, with a consistent entity roster behind every shot.
560 GitHub stars~4.6k tokensUpdated today
Auto-check passed
Elevenlabs Audio Prompting
nodetool-ai/nodetool
Direct ElevenLabs speech, dialogue, sound effects and music — the bracketed audio tags v3 acts on and why the voice decides whether a tag lands, stability as the delivery dial, punctuation instead…
560 GitHub stars~1.9k tokensUpdated today
Auto-check passed
Frame Composition
nodetool-ai/nodetool
Stage the frame on a NodeTool timeline — grids, focal placement, safe areas per aspect ratio, depth layers and parallax, camera moves, and where elements enter and leave.
560 GitHub stars~3.5k tokensUpdated today
Auto-check passed

Works with

Amazon Web Services

Questions about Sandbox AWS

What does Sandbox AWS do?

Sign AWS requests (S3 and every other SigV4 service) in a Code node or CodeAct action, with NodeTool's signer running on the host. Sandbox AWS is an agent skill from nodetool-ai/nodetool.

When should I use Sandbox AWS?

Sandbox AWS fits situations like: tasks that involve File uploads and storage.

How do I install Sandbox AWS in Claude Code?

Run `npx skills add nodetool-ai/nodetool --skill sandbox-aws -a claude-code`. Or copy the skill folder (packages/sandbox-packs/sandbox-aws in nodetool-ai/nodetool) into .claude/skills/sandbox-aws in your project. Claude Code loads it when a task matches its description.

How do I install Sandbox AWS in Codex?

Run `npx skills add nodetool-ai/nodetool --skill sandbox-aws -a codex`. Or copy the skill folder (packages/sandbox-packs/sandbox-aws in nodetool-ai/nodetool) into .agents/skills/sandbox-aws in your project. Codex loads it when a task matches its description.

Can I use Sandbox AWS in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nodetool-ai/nodetool --skill sandbox-aws -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sandbox-aws, .gemini/skills/sandbox-aws, .github/skills/sandbox-aws and .opencode/skills/sandbox-aws in your project.

What does Sandbox AWS need to run?

Going by SKILL.md and its folder, Sandbox AWS needs credentials named AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY. Our summary lists: A credential in AWS_SECRET_ACCESS_KEY.

Does Sandbox AWS access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sandbox AWS safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sandbox AWS use?

Sandbox AWS is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sandbox AWS use?

About 849 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sandbox AWS?

Skills that share tags, products or a category with Sandbox AWS: Foundatio (FoundatioFx/Foundatio, 2.1k stars), Phidown (ESA-PhiLab/phidown, 105 stars), Fftiers Ops (borisachen/fftiers, 202 stars) and Processing S3 Uploads With Step Functions (aws/agent-toolkit-for-aws, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sandbox AWS?

nodetool-ai (a GitHub organization) maintains it in nodetool-ai/nodetool, which has 560 GitHub stars. The repository holds 127 skills in this directory. The repository was last updated on October 10, 2026.

Source: nodetool-ai/nodetool on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Sandbox AWS

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

AWS SigV4 in the sandbox

sigv4 — sign a request

Writing an object

presign — a URL that authorizes itself

Gotchas

Files

Compare with similar skills

Similar skills

More from nodetool-ai/nodetool

Related

Questions about Sandbox AWS