Tensorlake is a serverless compute platform for building agent applications with isolated, stateful virtual machines called sandboxes and a runtime for coordinating background work. Developers use the sandboxes to run agents, tools, or code generated by language models, and use the orchestration runtime for long-running agent tasks. The catalogue instructions relate to using Tensorlake's sandbox and orchestration workflows.
Borrowing it
Nothing to install: this file belongs to tensorlakeai/tensorlake. 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/tensorlakeai/tensorlake/main/AGENTS.mdgit clone --depth 1 https://github.com/tensorlakeai/tensorlakeWrote 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/tensorlakeai/tensorlake/agents-md)<a href="https://agentmods.dev/instructions/tensorlakeai/tensorlake/agents-md"><img src="https://agentmods.dev/badge/instructions/tensorlakeai/tensorlake/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/tensorlakeai/tensorlake/agents-md"><img src="https://agentmods.dev/badge/instructions/tensorlakeai/tensorlake/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 | $0.00129 | $0.00129 |
| Opus 5.5 | $0.00052 | $0.00052 |
| Sonnet 5.5 | $0.00026 | $0.00026 |
| Haiku 4.5 | $0.00013 | $0.00013 |
Grade A, and why
tensorlake 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 18d 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- agent-comms CLAUDE.md — 100% identical, 7 lines differ
- document-mcp AGENTS.md — 100% identical, 7 lines differ
- clockify-mcp-server CLAUDE.md — 100% identical, 6 lines differ
- document-mcp CLAUDE.md — 100% identical, 7 lines differ
- ragflow-knowledge-mcp-server GEMINI.md — 100% identical, 7 lines differ
- agent-permissions AGENTS.md — 100% identical, 7 lines differ
- libsrc-mcp CLAUDE.md — 100% identical, 5 lines differ
- claude-code-plugins CLAUDE.md — 100% identical, 6 lines differ
What it actually says
Tensorlake SDK agent guide
Read README.md for the SDK overview and public API examples.
Use product terms in user documentation, comments, and user-facing messages because sandbox runtimes are internal platform details. Map Firecracker (FC) to non-CAS sandbox, Cloud Hypervisor (CH) to CPU-only CAS sandbox, and gVisor to GPU CAS sandbox. The SDK may expose runtime identifiers for inspection and diagnostics, but they are not the primary user-visible terms. Once migration to CAS is complete, the product terms will be CPU-only sandboxes and GPU sandboxes.
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.
- 18d ago Changed · +5 lines · +127 tokens per session 8d5e47659cc4
- 1mo ago First seen · 1 lines · 2 tokens per session scan A b33563055168
tensorlake AGENTS.md is an instructions file published in the GitHub repository tensorlakeai/tensorlake (1,028 stars, last pushed today), licensed Apache-2.0. It adds 129 tokens to every session, about $0.0005 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.