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/gogpu/gg/agents-mdgit clone --depth 1 https://github.com/gogpu/ggWhat 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 | $0.00806 | $0.00806 |
| Opus 5 | $0.00403 | $0.00403 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
gg 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 yesterday.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — gg
Pure Go 2D graphics library. Smart rasterizer, GPU acceleration, text rendering, SVG paths.
What is gg
gg is a 2D graphics library for Go — draw shapes, text, images, paths with anti-aliasing. Features a smart 6-algorithm rasterizer that auto-selects the best algorithm per path (NoAA, Analytic, SparseStrips, TileCompute, SDF, Vello PTCL). GPU acceleration via blank import.
Part of the GoGPU ecosystem — think Flutter or Qt, but Pure Go with zero CGO.
When to use gg
- Draw 2D shapes (circles, rectangles, paths) →
gg.Context - Render text with font shaping →
cc.DrawString() - Generate images programmatically →
gg.NewContext(w, h) - GPU-accelerated 2D in a gogpu window →
ggcanvas.New()+import _ "github.com/gogpu/gg/gpu"
Quick Start
Standalone (CPU, no window)
import "github.com/gogpu/gg"
dc := gg.NewContext(800, 600)
dc.SetRGB(1, 0, 0)
dc.DrawCircle(400, 300, 100)
dc.Fill()
dc.SavePNG("circle.png")
With gogpu window (GPU-accelerated)
import (
"github.com/gogpu/gg"
"github.com/gogpu/gg/integration/ggcanvas"
_ "github.com/gogpu/gg/gpu" // GPU SDF acceleration
)
var canvas *ggcanvas.Canvas
app.OnDraw(func(dc *gogpu.Context) {
if canvas == nil {
canvas, _ = ggcanvas.New(dc.GPUContextProvider(), 800, 600)
}
canvas.Draw(func(cc *gg.Context) {
cc.SetRGB(1, 0, 0)
cc.DrawCircle(400, 300, 100)
cc.Fill()
})
canvas.Render(dc.RenderTarget())
})
Important: Always add _ "github.com/gogpu/gg/gpu" blank import for GPU acceleration. Without it, gg uses CPU-only rasterization.
Key Packages
| Package | Purpose |
|---|---|
gg (root) |
Drawing context, shapes, text, images |
gg/gpu |
GPU acceleration registration (blank import) |
gg/integration/ggcanvas |
GPU canvas for gogpu integration |
gg/scene |
Scene graph for retained-mode rendering |
Build & Test
go build ./...
go test ./...
golangci-lint run --timeout=5m
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.
- yesterday First seen · 93 lines · 806 tokens per session scan A f6b0d2c59cea
gg AGENTS.md is an instructions file published in the GitHub repository gogpu/gg (159 stars, last pushed 2d ago), licensed MIT. It adds 806 tokens to every session, about $0.0040 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 2026-09-01.
Other instructions, from other repositories
DeepSpeed AGENTS.md
AGENTS.md instructions for deepspeedai/DeepSpeed, covering deepspeed project rules, commit & ci requirements, code change discipline, tool caveats and edit tool auto-formatter.
awesome-go AGENTS.md
AGENTS.md instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
neva AGENTS.md
AGENTS.md instructions for nevalang/neva, covering neva engineering guide, project model, repository map, documentation and ai engineering harness.
tldraw AGENTS.md
AGENTS.md instructions for tldraw/tldraw, covering agents.md, core rules, repo overview, setup and common commands.