OpenSandbox is a sandbox platform that gives AI applications APIs, SDKs, and runtimes for creating isolated environments, running commands, and managing files. It is used for coding and GUI agents, browser automation, code execution, agent evaluation, and reinforcement-learning training across Docker and Kubernetes environments. The catalogue entries provide instructions and a skill for working with these sandboxes.
Borrowing it
Nothing to install: this file belongs to opensandbox-group/OpenSandbox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/opensandbox-group/OpenSandbox/main/AGENTS.mdgit clone --depth 1 https://github.com/opensandbox-group/OpenSandboxWrote 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/instructions/opensandbox-group/opensandbox/agents-md)<a href="https://agentmods.dev/instructions/opensandbox-group/opensandbox/agents-md"><img src="https://agentmods.dev/badge/instructions/opensandbox-group/opensandbox/agents-md/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/instructions/opensandbox-group/opensandbox/agents-md"><img src="https://agentmods.dev/badge/instructions/opensandbox-group/opensandbox/agents-md.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 | $0.01945 | $0.01945 |
| Opus 5.5 | $0.00778 | $0.00778 |
| Sonnet 5.5 | $0.00389 | $0.00389 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
OpenSandbox AGENTS.md 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 9d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSandbox AGENTS
Use this file as the root router for the monorepo. Prefer the nearest AGENTS.md in the directory tree for task-specific instructions.
Repository Map
server/: FastAPI lifecycle control plane, Docker/Kubernetes runtime integration, snapshot metadata, and server testscomponents/execd/: in-sandbox execution daemoncomponents/egress/: per-sandbox network egress policy sidecarcomponents/ingress/: ingress gateway and endpoint routingcomponents/internal/: shared Go helpers used by runtime componentssdks/: sandbox, code-interpreter, and MCP SDKs plus generated clientsspecs/: public OpenAPI contracts and exampleskubernetes/: Kubernetes operator, CRDs, task-executor, and Kind e2e testsmanifests/charts/: Helm charts (base, controller, server, ingress-gateway, node-agent, fast-sandbox, opensandbox umbrella)cli/:osbcommand-line client and bundled CLI skillsconsole/: developer console (React SPA + FastAPI BFF), optional K8s examples; no server/spec changestests/: cross-language end-to-end SDK testsdocs/,examples/,oseps/: documentation, samples, and proposals
Routing
- For
server/**, or lifecycle server behavior, sandbox creation flow, or user-visible server config, readserver/AGENTS.md. - For
sdks/**, or SDK generation, handwritten adapters, or cross-language SDK alignment, readsdks/AGENTS.md. - For
specs/**, or API contract, schema, or example changes, readspecs/AGENTS.md. - For
kubernetes/**, or CRDs, controller behavior, task execution, Helm/Kustomize deployment, pool scheduling, pause/resume snapshots, or Kind e2e tests, readkubernetes/AGENTS.md. - For cross-cutting changes spanning spec, server, and SDKs, start with
specs/AGENTS.mdand then read affected consumer guides. - For runtime component changes under
components/**, read the nearestREADME.mdorDEVELOPMENT.md; keep component APIs aligned withspecs/and SDK consumers. - For CLI changes under
cli/**, readcli/README.mdand verify command help/output behavior alongside unit tests. - For console changes under
console/**, readconsole/README.mdandconsole/docs/; runconsole/webbuild and keep BFF env docs aligned withconsole/k8s/*.example.yaml. - For cross-language e2e tests under
tests/**, read the language-local README and keep test assumptions aligned with current server and SDK behavior. - For areas without a local
AGENTS.md, use the nearestREADME.md,DEVELOPMENT.md, and CI workflow as the next source of truth.
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.
- 9d ago Changed · +2 lines · +72 tokens per session dec90f8d5ad2
- 19d ago Changed · +3 lines · +178 tokens per session 4b7761a47a95
- 24d ago Changed · -8 lines · -18 tokens per session 5380d7fb6b44
- 1mo ago Changed · -1 lines · -1 tokens per session bfcf49b90cb7
- 1mo ago Changed · +4 tokens per session 3d971c059c88
- 1mo ago Changed · +1 lines · +26 tokens per session daea4edea0f1
- 1mo ago Changed · -9 tokens per session ba41b8e8bccc
- 2mo ago First seen · 123 lines · 1,693 tokens per session scan A ef18bc5d12dc
OpenSandbox AGENTS.md is an instructions file published in the GitHub repository opensandbox-group/OpenSandbox (16,463 stars, last pushed today), licensed Apache-2.0. It adds 1,945 tokens to every session, about $0.0078 per session on Opus 5.5. 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.
OpenSandbox AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| OpenSandbox AGENTS.mdopensandbox-group/OpenSandbox | Instructions file | 16k | today | Apache-2.0 | A | 1,945 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |