Borrowing it
Nothing to install: this file belongs to ara3d/ara3d-sdk. 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/ara3d/ara3d-sdk/main/AGENTS.mdgit clone --depth 1 https://github.com/ara3d/ara3d-sdkWrote 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/ara3d/ara3d-sdk/agents-md)<a href="https://agentmods.dev/instructions/ara3d/ara3d-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/ara3d/ara3d-sdk/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/ara3d/ara3d-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/ara3d/ara3d-sdk/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 | $0.03825 | $0.03825 |
| Opus 5.5 | $0.01530 | $0.01530 |
| Sonnet 5.5 | $0.00765 | $0.00765 |
| Haiku 4.5 | $0.00382 | $0.00382 |
Grade A, and why
ara3d-sdk 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 1mo 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Working in the Ara3D SDK
This is the operating guide for AI agents (and humans) writing code in this repository. Read it before making changes. It encodes how this codebase is built and maintained.
This project is maintained by one person with virtually no outside contributions. Optimize for that reality: code that is simple, correct, easy to refactor, and cheap to understand six months later beats code that is clever, abstract, or "enterprise-grade".
1. The two rules that override everything
- The code must work. Correctness first. A working simple version beats a broken elegant one.
- The code must be easy to improve and refactor. Everything below serves this.
If a guideline here ever conflicts with these two rules, the two rules win.
2. The standard workflow (do things in steps)
Work in small, verifiable increments. Never combine "make it work" with "make it pretty" in the same step.
- Add code + tests for the smallest useful slice of behavior.
- Verify it works — build and run the tests (see §8). Do not proceed on a red build.
- Plan the refactor — note what should improve. Add
// TODO:markers in code and a matching entry indocs/TECHNICAL_DEBT.md. - Save the state — this is a natural stopping/commit point. The working version is preserved.
- Apply the refactor — change structure, not behavior. Tests from step 1 prove you didn't break anything.
Never refactor on a red build. If tests are failing, get them green first, then refactor.
When given a multi-step task, use a todo list and keep it current.
3. Core principles
First, the monorepo-wide API-first design principles (canonical list in the root
AGENTS.md) apply to everything here:
- Write code as if writing a public API — these SDK libraries literally are one.
- Eat your own dogfood: consume existing SDK APIs before adding new ones; awkwardness in an existing API is a reason to improve it, not bypass it.
- Design for relocation: code should move cleanly between projects/layers — few, explicit dependencies.
- Write for the next learner: someone else must be able to learn and use it quickly.
- Obvious usage: correct use discoverable from signatures and names alone.
- Types and affordances guide correct use: illegal states unrepresentable; misuse a compile error where possible.
- Path of least resistance = best practice: the easiest way must be the right way.
- Composition and reuse by default: every new piece is a candidate building block.
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.
- 1mo ago Changed · -15 lines · -304 tokens per session 8d32f3cdd3b3
- 1mo ago First seen · 332 lines · 4,129 tokens per session scan A 93bf2e81c331
ara3d-sdk AGENTS.md is an instructions file published in the GitHub repository ara3d/ara3d-sdk (43 stars, last pushed 5d ago), licensed MIT. It adds 3,825 tokens to every session, about $0.0153 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.