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 instructions/opensandbox-group/opensandbox/agents-mdgit clone --depth 1 https://github.com/opensandbox-group/OpenSandboxWhat 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 | $0.01693 | $0.01693 |
| Opus 5 | $0.00847 | $0.00847 |
| Sonnet 5 | $0.00339 | $0.00339 |
| Haiku 4.5 | $0.00169 | $0.00169 |
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 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 — 123 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, Helm charts, and Kind e2e testscli/:osbcommand-line client and bundled CLI skillstests/: cross-language end-to-end SDK testsdocs/,examples/,sandboxes/,oseps/: documentation, samples, images/environments, 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 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.
- 3d 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 (14,896 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,693 tokens to every session, about $0.0085 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 instructions, from other repositories
agent-sandbox AGENTS.md
Instructions for kubernetes-sigs/agent-sandbox, covering agents.md, project summary, repository layout, agent skills and build, test, lint.
agent-sandbox copilot-instructions.md
Instructions for kubernetes-sigs/agent-sandbox: Project Context & Architecture: Refer to AGENTS.md for full project background, module layout, toolchain versions, and core conventions.
openshell-k8s-operator CLAUDE.md
Instructions for lensapp/openshell-k8s-operator, covering claude.md, what this is, build / test / lint, conventions and layout.
agent-bundle AGENTS.md
Instructions for yujiachen-y/agent-bundle, covering agents.md, project overview, key commands, port allocation (prefix × 1000 + suffix) and port priority.
openshell-k8s-operator AGENTS.md
Instructions for lensapp/openshell-k8s-operator, a project described as: OpenShell Kubernetes Operator.
agent-bundle CLAUDE.md
Instructions for yujiachen-y/agent-bundle, a project described as: Bundle agent skills into a single deployable agent — sandboxed execution, token-scoped data access, type-safe build output.