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.
npx agentmods add skills/togethercomputer/skills/together-sandboxesnpx skills add togethercomputer/skills --skill together-sandboxesgit clone --depth 1 https://github.com/togethercomputer/skillsWhat 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.
| Model | Per session | Once 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 |
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.
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.
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-clustersfor full infrastructure control or larger distributed jobs - Use
together-dedicated-containersfor custom containerized runtime logic - Use
together-chat-completionsif the user only wants generated code, not executed code
Quick Routing
- Remote execution with session reuse
- Response schema and session listing
- MCP-style access for agent workflows
Workflow
- Decide whether the task needs code execution or only code generation.
- Start a session with
client.code_interpreter.execute(). - Reuse
session_idwhen the workflow depends on prior state. - Inspect
stdout,stderr, structured outputs, and display outputs separately. - 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_idas part of the workflow state. - Inspect
response.errorsbefore assuming a run succeeded. plt.show()with the Agg backend does not reliably producedisplay_dataoutputs. To retrieve charts, save the figure to aBytesIObuffer withfig.savefig(), base64-encode it, and print the encoded string to stdout. Parse it from thestdoutoutput 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.
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.
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.
- 3d ago First seen · 69 lines · 64 tokens per session scan A 9c91677fbed9
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.
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.
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…
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…
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…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
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.