together-sandboxes

A managed remote environment for running Python code in persistent sessions. It supports file uploads, data analysis, chart creation, and notebook-like execution.

In plain words
What is it for?
Use it for stateful Python sessions, uploaded-file analysis, generated charts, and agent-written code that needs to be executed.
Why use it?
It lets an agent or application run code remotely without setting up local execution infrastructure.

Skill for Claude CodeCodex

Part of the togetherai-skills plugin — 14 skills shipped together

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/togethercomputer/skills/together-sandboxes
Any agent
npx skills add togethercomputer/skills --skill together-sandboxes
Clone the repo
git clone --depth 1 https://github.com/togethercomputer/skills

Made for: Claude Code, Codex.

Or install togetherai-skills, the plugin that ships this one along with the rest of its 14 skills.

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 746 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 $0.00064 $0.00746
Opus 5 $0.00032 $0.00373
Sonnet 5 $0.00013 $0.00149
Haiku 4.5 $0.00006 $0.00075

Measured 3d ago against content hash 9c91677fbed9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

together-sandboxes 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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/execute_with_session.py, scripts/execute_with_session.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.

skills/together-sandboxes/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Together Sandboxes

Overview

Use Together Sandboxes when the user wants to execute Python remotely in a managed sandbox.

Typical fits:

  • stateful Python sessions
  • data analysis and chart generation
  • agent-generated code execution
  • file uploads into a remote runtime

When This Skill Wins

  • The user wants remote execution rather than local shell execution
  • Session state needs to persist across multiple calls
  • The result may include display outputs such as charts
  • A lightweight managed runtime is enough; no custom infra is required

Hand Off To Another Skill

  • Use together-gpu-clusters for full infrastructure control or larger distributed jobs
  • Use together-dedicated-containers for custom containerized runtime logic
  • Use together-chat-completions if the user only wants generated code, not executed code

Quick Routing

Workflow

  1. Decide whether the task needs code execution or only code generation.
  2. Start a session with client.code_interpreter.execute().
  3. Reuse session_id when the workflow depends on prior state.
  4. Inspect stdout, stderr, structured outputs, and display outputs separately.
  5. List sessions only when the user needs operational visibility or cleanup.

High-Signal Rules

  • Python scripts require the Together v2 SDK (together>=2.0.0). If the user is on an older version, they must upgrade first: uv pip install --upgrade "together>=2.0.0".
  • Treat session_id as part of the workflow state.
  • Inspect response.errors before assuming a run succeeded.
  • plt.show() with the Agg backend does not reliably produce display_data outputs. To retrieve charts, save the figure to a BytesIO buffer with fig.savefig(), base64-encode it, and print the encoded string to stdout. Parse it from the stdout output on the client side. See the chart example in scripts/execute_with_session.py.
  • Use this skill when the user benefits from remote stateful execution, not just because Python is involved.
  • If the task outgrows the sandbox model, hand off to GPU clusters or dedicated containers.

Read the full file on GitHub · 69 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. 3d ago First seen · 69 lines · 64 tokens per session scan A 9c91677fbed9

Subscribe to this mod's changes

together-sandboxes is a skill published in the GitHub repository togethercomputer/skills (34 stars, last pushed 15d ago), licensed MIT. It adds 64 tokens to every session and 746 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 2026-08-30.

Related

Other skills, from other repositories

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

bigquery-ai-ml

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…

google/skills · 104 tokens

ondb

A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…

x-cmd/x-cmd · 71 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

mixed-precision

Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.

aiming-lab/AutoResearchClaw · 25 tokens

sparse-autoencoder-training

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Orchestra-Research/AI-Research-SKILLs · 58 tokens