Borrowing it
Nothing to install: this file belongs to oframe/ogpu. 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/oframe/ogpu/main/AGENTS.mdgit clone --depth 1 https://github.com/oframe/ogpuWrote 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/oframe/ogpu/agents-md)<a href="https://agentmods.dev/instructions/oframe/ogpu/agents-md"><img src="https://agentmods.dev/badge/instructions/oframe/ogpu/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/oframe/ogpu/agents-md"><img src="https://agentmods.dev/badge/instructions/oframe/ogpu/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 | $0.03232 | $0.03232 |
| Opus 5.5 | $0.01293 | $0.01293 |
| Sonnet 5.5 | $0.00646 | $0.00646 |
| Haiku 4.5 | $0.00323 | $0.00323 |
Grade A, and why
ogpu 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 12d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Shared agent guidance for this repo. CLAUDE.md / GEMINI.md / .cursor/rules/main.mdc are one-line imports of this file — edit here only.
Hand-rolled WebGPU engine. Vanilla JS, Vite, no framework, no TypeScript (ambient decls in types/ogpu.d.ts for TS consumers). No tests, no typechecker. ESLint + Prettier, format-on-save.
Where things are
api-digest.md— generated public-surface index (every exported class, its method signatures, barrel re-exports). Read it for any signature or constructor option instead of opening the file.module-graph.json— generated import graph;hubslists the highest-in-degree modules. Traceedgesinstead of grepping for importers.- Both regenerate with
npm run repomap. A pre-commit hook runsrepomap:checkand blocks stale copies — if a commit is blocked,git add api-digest.md module-graph.jsonand recommit.
This file is the why; api-digest is the what. Keep method lists out of here.
Each source directory has its own CLAUDE.md with that area's footguns, auto-loaded when you read files there:
src/core/ (Renderer, Transform, Camera, Mesh, RenderBundleGroup, Shader, UniformBuffer, PipelineRegistry, PerDrawBuffer, RenderPipeline, Geometry, ComputeShader, Texture, RenderTarget, reflect/, primitives/, skin/, ShaderReload) · src/math/ (the @math/functions layer — vec2/vec3/vec4/quat/mat3/mat4, out param last; wgpu-matrix plus local overrides, imported from here, never wgpu-matrix directly, lint-enforced — under chainable Float32Array-subclass classes) · src/modules/ (Orbit, Raycast, GUI, Animation, GLTFLoader, CubeMap, VideoTexture, pbr/, gsplat/, text/ (MSDF text + SplitText-style reveals)) · src/utils/IBLUtils/.
src/utils/ is standalone helpers; examples/ is runnable demos at the repo root.
examples/ covers shadows, skinning, PBR/IBL, render targets, compute particles, glTF. Anything overlapping those extends the existing path rather than starting a new one.
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.
- 12d ago Changed · +8 lines · +1,525 tokens per session af7ad7289b7f
- 20d ago Changed · +5 tokens per session 036d8975e71f
- 1mo ago Changed · +52 tokens per session d8dda0cf8d76
- 1mo ago Changed · -66 lines · -2,195 tokens per session d0adc5892f1a
- 1mo ago First seen · 140 lines · 3,845 tokens per session scan A df56d5f5874e
ogpu AGENTS.md is an instructions file published in the GitHub repository oframe/ogpu (163 stars, last pushed 3d ago), licensed Unlicense. It adds 3,232 tokens to every session, about $0.0129 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.