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.
git clone --depth 1 https://github.com/gotempsh/tempsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/gotempsh/temps/sandbox)<a href="https://agentmods.dev/commands/gotempsh/temps/sandbox"><img src="https://agentmods.dev/badge/commands/gotempsh/temps/sandbox/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/gotempsh/temps/sandbox"><img src="https://agentmods.dev/badge/commands/gotempsh/temps/sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03984 |
| Opus 5.5 | $0.00000 | $0.01594 |
| Sonnet 5.5 | $0.00000 | $0.00797 |
| Haiku 4.5 | $0.00000 | $0.00398 |
Grade A, and why
sandbox 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 7d 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sandbox command reference
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
Contents
sandbox createsandbox listsandbox nodessandbox showsandbox rmsandbox pausesandbox resumesandbox restartsandbox clonesandbox shellsandbox extendsandbox execsandbox logssandbox domainsandbox passwordsandbox fssandbox snapshotssandbox snapshot
sandbox
Manage standalone sandboxes (/v1/sandbox API)
Subcommands:
create- Create a new sandboxlist(ls) - List your sandboxesnodes- List nodes that can run sandboxes and control which ones take new sandboxesshow- Show details for a sandboxrm(stop,destroy) - Remove a sandbox permanently (aliases: stop, destroy)pause- Pause a running sandbox (non-destructive — resume later withsandbox resume)resume- Resume a paused sandboxrestart- Restart a running sandbox (preserves filesystem)clone- Clone a git repo or extract a tarball into a running sandboxshell(attach) - Open an interactive terminal in a sandbox. Detach with Ctrl-P Ctrl-Q to leave the program running;exitends it. Reattach with the same --tabextend- Extend a sandbox's idle timeoutexec- Run a command inside a sandbox. Use--to pass flags:exec ID -- ls -lalogs- Stream logs from a detached job (SSE)domain- Resolve the preview URL for a port inside a sandboxpassword- Generate, rotate, or clear the preview-URL password for a sandboxfs- Filesystem operations inside a sandboxsnapshots- Manage sandbox snapshots (ADR-037)snapshot- Take a snapshot of a sandbox
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.
- 7d ago Changed · +1 lines 4eac64204199
- 12d ago Changed · +1 lines 996e47f3eaaf
- 19d ago Changed · +101 lines 79c86cfaaf86
- 1mo ago First seen · 326 lines · 0 tokens per session scan A d47d15be27ec
sandbox is a command published in the GitHub repository gotempsh/temps (861 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,984 tokens. 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 2026-09-03.
Other commands, from other repositories
secrets-audit
You are a senior DevOps & Cloud Infrastructure specialist. The user needs help with secrets audit in the context of ci/cd pipelines, container orchestration, iac, monitoring and incident response.
cost-optimize
You are a senior DevOps & Cloud Infrastructure specialist. The user needs help with cost optimize in the context of ci/cd pipelines, container orchestration, iac, monitoring and incident response.
incident-runbook
You are a senior DevOps & Cloud Infrastructure specialist. The user needs help with incident runbook in the context of ci/cd pipelines, container orchestration, iac, monitoring and incident response.
cost-optimize
You are a senior DevOps & Cloud Infrastructure specialist. The user needs help with cost optimize in the context of ci/cd pipelines, container orchestration, iac, monitoring and incident response.
sparc-devops
🚀 DevOps - You are the DevOps automation and infrastructure specialist responsible for deploying, managing, ...
sdlc-deploy
Phase 5 — Infrastructure & Deployment. Spawns devops-engineer and cloud-engineer to design CI/CD, containerization, and cloud infrastructure.