vgpu is a TypeScript library that provides one WebGPU programming interface for browser rendering, headless Node execution, and deterministic tests, including shader modules, 3D scenes, GPU tensors, neural networks, and mathematical visualizations. Developers use it to write explicit GPU drawing and computation code while sharing it across runtimes without hidden global state. The catalogue skill supports work with this library.
Borrowing it
Nothing to install: this file belongs to vercel-labs/vgpu. 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/vercel-labs/vgpu/canary/AGENTS.mdgit clone --depth 1 https://github.com/vercel-labs/vgpuWrote 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/vercel-labs/vgpu/agents-md)<a href="https://agentmods.dev/instructions/vercel-labs/vgpu/agents-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/vgpu/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/vercel-labs/vgpu/agents-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/vgpu/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 | $0.01008 | $0.01008 |
| Opus 5.5 | $0.00403 | $0.00403 |
| Sonnet 5.5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
vgpu 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 21d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on vgpu
This file is the workflow index. Before planning, editing files, or acting on an issue/PR, read workflow context, then select the matching path below. If the directing person's role is unknown, follow its mandatory GitHub permission lookup and routing rules. Read required guides in full before the relevant stage. Read additional guides only when their conditions apply; the linked steps are mandatory, not optional reference material.
Select the task workflow
| When | Read |
|---|---|
| Acting for an external contributor submitting or revising an issue, proposal, reproduction, or prototype PR. | External contributor |
| Acting for a maintainer on work originating from an external issue or PR, including review, triage, implementation, or a request to merge it. | Maintainer adoption |
| Acting for a maintainer on an internal task with no external contribution as its origin. | Maintainer original |
| Continuing an existing maintainer PR. | Read its recorded workflow above and resume the current stage; use workflow context if role/origin is unclear. |
Read the sub-workflow for the current stage
| When | Read before proceeding |
|---|---|
| Starting authorized maintainer implementation, including documentation or policy edits. | Implementation |
| Designing or changing scene utilities or their guides. | Scene library boundary |
| Changing published behavior, writing a changeset, or deciding whether consumers need migration. | Changesets and migrations |
| Preparing, editing, reviewing, or merging a maintainer integration PR. | Pull requests and CONTRIBUTING.md |
| Preparing/reviewing an RC or stable release, changing package versions for release, or publishing packages. | Releases |
Promoting a published stable release to main, or synchronizing it back to canary. |
Stable promotion and back-merge |
| Preparing a web-only production change. | Web-only production updates |
| Submitting an external PR or changing its type/checks/merge policy. | Contribution policy rollout |
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.
- 21d ago Changed · +5 lines · +108 tokens per session ed40c186038a
- 1mo ago Changed · +5 lines · +93 tokens per session 7109905fe7a3
- 1mo ago Changed · +1 lines · +28 tokens per session 1008d6378ba8
- 1mo ago Changed · +5 lines · +82 tokens per session b5691f8c43b2
- 1mo ago Changed · +8 lines · +98 tokens per session a72a91cb0952
- 1mo ago Changed · -39 lines · -436 tokens per session cc4e665e414f
- 1mo ago First seen · 71 lines · 1,035 tokens per session scan A 834d6b907c03
vgpu AGENTS.md is an instructions file published in the GitHub repository vercel-labs/vgpu (2,620 stars, last pushed 21d ago), licensed MIT. It adds 1,008 tokens to every session, about $0.0040 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 2026-09-10.
vgpu AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vgpu AGENTS.mdvercel-labs/vgpu | Instructions file | 2.6k | 21d ago | MIT | A | 1,008 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | 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 | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |