What is sandbox-execution?

A way to run exploratory code in an isolated workspace using tools designed for medical-science analysis. The standard process creates a sandbox, runs a command, retrieves selected results, and can remove the workspace afterward.

Use it when existing research tools cannot perform a needed analysis, when you need custom scripts, or when exploratory jobs need their own workspace.

It keeps custom or longer-running code separate from the main environment and uses a network-disabled default for isolation.

How omar-A-hassan/medsci-agent configures OpenCode

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/skills/sandbox-execution/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/omar-A-hassan/medsci-agent

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/omar-a-hassan/medsci-agent/sandbox-execution/github.svg)](https://agentmods.dev/skills/omar-a-hassan/medsci-agent/sandbox-execution)

Your own site

<a href="https://agentmods.dev/skills/omar-a-hassan/medsci-agent/sandbox-execution"><img src="https://agentmods.dev/badge/skills/omar-a-hassan/medsci-agent/sandbox-execution/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/omar-a-hassan/medsci-agent/sandbox-execution"><img src="https://agentmods.dev/badge/skills/omar-a-hassan/medsci-agent/sandbox-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 377 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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.00377
Opus 5	$0.00014	$0.00188
Sonnet 5	$0.00006	$0.00075
Haiku 4.5	$0.00003	$0.00038

Measured 10d ago against content hash ef485c20242d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sandbox-execution 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 10d 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/skills/sandbox-execution/SKILL.md · 42 lines

What it actually says

Sandbox Execution

When to Use

Domain MCP tools cannot directly perform the requested analysis
Task requires generated/custom code execution
Long-running exploratory workflows need isolation

Standard Workflow (Sequential)

1. Prepare sandbox  → sandbox_prepare(workspace_path, network_policy="deny")
2. Run command      → sandbox_run_job(sandbox_name, command, timeout_sec)
3. Check status     → sandbox_status(sandbox_name) [optional/advisory]
4. Fetch outputs    → sandbox_fetch_artifact(sandbox_name, artifact_path)
5. Teardown         → sandbox_teardown(sandbox_name, remove=true|false)

Defaults and Guardrails

Default network policy: deny
Use explicit timeout_sec on every run job
Treat sandbox_run_job success/failure as source-of-truth for execution outcome
If sandbox_status is used, apply 1-2s retry/backoff before final state conclusion
Retrieve only required artifacts/logs
Prefer removing sandbox after one-off jobs (remove=true)
Prefer python3 for inline script execution commands

Failure Handling

SANDBOX_TIMEOUT: reduce scope or increase timeout
CLI_UNAVAILABLE: verify Docker + Docker Sandbox CLI installed
SANDBOX_CREATE_FAILED: check Docker Desktop status and template availability
ARTIFACT_PATH_FORBIDDEN: use safe paths under workspace/artifact roots only
ARTIFACT_NOT_FOUND: verify command produced expected files before fetch

Notes

Keep tool calls sequential to avoid local contention.
Return raw execution outputs even if interpretation models are unavailable.

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.

10d ago First seen · 42 lines · 28 tokens per session scan A ef485c20242d

Subscribe to this mod's changes

sandbox-execution is a skill published in the GitHub repository omar-A-hassan/medsci-agent (18 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 377 once invoked, about $0.0001 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.

Scientific agents mcp medgemma ollama opencode txgemma

build-expression-tree

For symbolic computation: ASTs, mathematical expressions, code that manipulates code structure, expression transformations.

jimmc414/claude-code-plugin-marketplace · 24 tokens

find-convex-hull

For computational geometry: convex hull, point enclosure, polygon operations. Uses monotone chain algorithm with stack-based turn detection.

jimmc414/claude-code-plugin-marketplace · 31 tokens

dfam-check

Measure mesh files against Design for Additive Manufacturing (DfAM) rules and report printability findings per process (FDM, SLS, SLA/DLP, metal PBF, MJF). Use when the user asks whether a part is printable, wants overhang/wall-thickness/support analysis of an .stl, .obj, .ply, or .3mf mesh, wants a build-orientation…

earthtojake/text-to-cad · 111 tokens

peer-review

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating…

xintaofei/codeg · 71 tokens

tooluniverse-gene-enrichment

Gene-set enrichment analysis — GO (Biological Process, Molecular Function, Cellular Component), KEGG, Reactome pathway enrichment via clusterProfiler, gseapy, ORA, GSEA. Use for interpreting DEG lists, screen hit lists, or any gene-list-to-pathways query. Includes simplify-cutoff handling and union-vs-total…

mims-harvard/ToolUniverse · 82 tokens

tooluniverse-phylogenetics

Phylogenetic analysis — de novo multiple sequence alignment (Clustal Omega/MUSCLE/MAFFT via EBImsaalign) and neighbour-joining/UPGMA tree building (EBIbuildphylogenetictree) from your own sequences, plus tree analysis, treeness, saturation (PhyKIT), parsimony-informative sites, alignment gap analysis, DVMC…

mims-harvard/ToolUniverse · 155 tokens

medsci-agent: Skill for OpenCode