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/.claude/skills/vgpu-agent-flow/SKILL.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/skills/vercel-labs/vgpu/vgpu-agent-flow)<a href="https://agentmods.dev/skills/vercel-labs/vgpu/vgpu-agent-flow"><img src="https://agentmods.dev/badge/skills/vercel-labs/vgpu/vgpu-agent-flow/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/skills/vercel-labs/vgpu/vgpu-agent-flow"><img src="https://agentmods.dev/badge/skills/vercel-labs/vgpu/vgpu-agent-flow.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 | $0.00063 | $0.04789 |
| Opus 5.5 | $0.00025 | $0.01916 |
| Sonnet 5.5 | $0.00013 | $0.00958 |
| Haiku 4.5 | $0.00006 | $0.00479 |
Grade A, and why
vgpu-agent-flow 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vgpu agent flow
You are the lead. Specialists live in .subharness/agents/ and run through the subharness CLI
(root devDependency; call it as pnpm exec subharness or npx subharness). You own every
conversation with the human, every decision, every worktree, and every merge. Specialists never
talk to the human and never see this conversation — each prompt must carry the full context.
Team
For Blender assets and image-guided visual refinement, use the asset iteration lane. It pairs an Astra author with declared Opus 5.5 shader/runtime and critique children, with measured screenshots and evidence-based lessons. For web delivery and high-to-low conversion, use asset production. For CPU/GPU measurements, use performance measurement. These workflows also work with one agent when delegation is disabled. The normal API phases below still apply if the asset work changes a public API.
| Target | Harness / model | Role |
|---|---|---|
repo:api-researcher |
fx google/gemini-3.8-flash → Codex gpt-5.6-luna |
How other frameworks/libraries solve it. Raw findings only |
repo:graphics-researcher |
fx google/gemini-3.8-flash → Codex gpt-5.6-luna |
Papers, talks, shipped game techniques. Raw findings only |
repo:eval-designer |
Claude claude-opus-5.5 high → Codex gpt-6-astra high |
Eval methodology, independent gates, negative controls, and evidence-based analysis |
repo:api-designer |
Codex gpt-6-astra xhigh → Claude claude-opus-5.5 xhigh |
API alternatives + illustrative snippets, agent-ergonomics evaluation |
repo:planner |
Claude claude-sonnet-5.5 high → Codex gpt-6-astra high |
Plan folder: index, task specs, agent assignment, lanes, progress log |
repo:implementer |
Claude claude-opus-5.5 high → Codex gpt-5.6-sol high |
Complex implementation, test-first; runs writer and reviewer as children; commits |
repo:implementer-simple |
Claude claude-sonnet-5.5 high → Codex gpt-5.6-sol high |
Scaffolding and straightforward tasks; same writer, reviewer, verification, and commit workflow |
repo:writer |
Claude claude-sonnet-5.5 high → Codex gpt-5.6-sol high |
Docs in house style (called by either implementer, or by you for docs-only work) |
repo:pr-writer |
Claude claude-sonnet-5.5 high (no fallback) |
Markdown-first problem/solution walkthrough and native code blocks; images only for complex diagrams that need drawing; then the technical PR record; lead reviews and publishes |
repo:reviewer |
Codex gpt-6-astra high → Claude claude-opus-5.5 high |
Read-only review (called by either implementer per task, and by you after integration) |
repo:fixer |
Claude claude-sonnet-5.5 high → Codex gpt-5.6-sol high |
Applies a bounded list of integration-review findings |
repo:asset-author |
Codex gpt-6-astra high (no fallback) |
Blender modeling, renders and authored lighting; declares producer, runtime and critic children |
repo:asset-producer |
Claude claude-opus-5.5 high (no fallback) |
LOW meshes, UVs, cages, bakes, compressed exports and decoded validation |
repo:performance-engineer |
Claude claude-sonnet-5.5 high (no fallback) |
Bounded measurement plans/runs, offline comparison and device-telemetry interpretation |
repo:asset-runtime |
Claude claude-opus-5.5 high (no fallback) |
Shaders, browser rendering and parity with Blender; called by asset-author |
repo:asset-critic |
Claude claude-opus-5.5 high (no fallback) |
Actual capture and cost review, called by asset-author |
repo:example-builder |
Claude claude-opus-5.5 xhigh |
One docs gallery example end to end from a brief; sees it running through capture_preview; runs example-reviewer; commits |
repo:example-reviewer |
Claude claude-opus-5.5 high |
Example review: code plus hands-on interaction checks through capture_preview (called by example-builder) |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 015fbe1a5be3
- 1mo ago Changed · +2 lines 330d53442cd7
- 1mo ago Changed · +26 lines 9f97af5b5713
- 1mo ago Changed · +19 lines 0ba538fbabcd
- 1mo ago Changed · +12 lines · -21 tokens per session 563a5a902515
- 1mo ago Changed · +33 lines 530a9a8cca65
- 1mo ago First seen · 196 lines · 84 tokens per session scan A d301b82b4f74
vgpu-agent-flow is a skill published in the GitHub repository vercel-labs/vgpu (2,620 stars, last pushed 21d ago), licensed MIT. It adds 63 tokens to every session and 4,789 once invoked, about $0.0003 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 2026-09-25.
vgpu-agent-flow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vgpu-agent-flowvercel-labs/vgpu | Skill | 2.6k | 21d ago | MIT | A | 63 | Claude Code |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 36k | 18d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 9d ago | Apache-2.0 | A | 95 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 121 | Claude Code |
| motionOpenDCAI/GameFactory-3A | Skill | 1.0k | 8d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| unity-addressablesBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 25 | Claude Code, Codex |
| unity-manual-componentBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 36 | Claude Code, Codex |