medsci-agent: Command for Claude Code

.opencode/commands/sandbox-job.md

sandbox-job is a command for Claude Code, OpenCode from omar-A-hassan/medsci-agent. It costs 9 tokens per session (155 once invoked), scanned A, original, MIT.

A command that runs one isolated job in a biomedical sandbox, collects its output, and removes the temporary environment afterward. A sandbox is a restricted place for running code separately from the main project.

In plain words
What is it for?
Use it to execute a command or small script with controlled network access, a timeout, saved logs, and temporary artifacts.
Why use it?
It provides a defined sequence for preparing, running, checking, collecting, and cleaning up an isolated task.

Command for Claude CodeOpenCode

Written for Claude Code and OpenCode: $ARGUMENTS substitution, but also installed under .opencode/. Also seen: agent in frontmatter.

This is omar-A-hassan/medsci-agent's own configuration. It tells Claude Code and OpenCode how to work on medsci-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything medsci-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to omar-A-hassan/medsci-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/omar-A-hassan/medsci-agent/main/.opencode/commands/sandbox-job.md
Clone the repo
git clone --depth 1 https://github.com/omar-A-hassan/medsci-agent

Made for: Claude Code, OpenCode.

Wrote 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.

agentmods badge for sandbox-job

README.md
[![agentmods](https://agentmods.dev/badge/commands/omar-a-hassan/medsci-agent/sandbox-job/github.svg)](https://agentmods.dev/commands/omar-a-hassan/medsci-agent/sandbox-job)
Your own site
<a href="https://agentmods.dev/commands/omar-a-hassan/medsci-agent/sandbox-job"><img src="https://agentmods.dev/badge/commands/omar-a-hassan/medsci-agent/sandbox-job/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.

agentmods 80×15 button for sandbox-job

Your own site · 80×15
<a href="https://agentmods.dev/commands/omar-a-hassan/medsci-agent/sandbox-job"><img src="https://agentmods.dev/badge/commands/omar-a-hassan/medsci-agent/sandbox-job.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 155 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00009 $0.00155
Opus 5 $0.00005 $0.00077
Sonnet 5 $0.00002 $0.00031
Haiku 4.5 $0.00001 $0.00015

Measured 11d ago against content hash 220c09950e2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sandbox-job 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 11d 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.

.opencode/commands/sandbox-job.md · 27 lines

What it actually says

Run this through medsci-sandbox with sequential steps:

Command: $ARGUMENTS

Command defaults:

  • For inline scripts, prefer python3 -c "..." over python -c "...".

Workflow:

  1. sandbox_prepare with default network_policy=deny
  2. sandbox_run_job with explicit timeout
  3. sandbox_status only as advisory check (retry/backoff 1-2s before final conclusion)
  4. sandbox_fetch_artifact for logs/output
  5. sandbox_teardown remove=true unless user requested persistence

Return:

  • command executed
  • exit status
  • key stdout/stderr summary
  • artifact paths
  • any safety/timeout issues
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. 11d ago First seen · 27 lines · 9 tokens per session scan A 220c09950e2d

Subscribe to this mod's changes

sandbox-job is a command published in the GitHub repository omar-A-hassan/medsci-agent (18 stars, last pushed 4d ago), licensed MIT. It adds 9 tokens to every session and 155 once invoked, about $0.0000 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.