shallot: Instructions file for Codex

AGENTS.md

shallot AGENTS.md is an instructions file for Codex, OpenCode from dylanebert/shallot. It costs 70 tokens per session, scanned A, original, MIT.

Repository guidance for Shallot, a WebGPU game engine. WebGPU is a browser and system graphics API for rendering with the GPU; the instructions describe the engine, project generator, examples, editor extension and documentation sources.

In plain words
What is it for?
Developing the engine, ECS, plugins, rendering, physics, project generator, VS Code extension, examples and related tests or documentation.
Why use it?
They show where engine behavior and consumer-facing rules are defined, so changes fit the existing package structure. This helps contributors work across the engine, scaffolding tool, extension and examples without losing the intended contracts.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is dylanebert/shallot's own configuration. It tells Codex and OpenCode how to work on shallot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything shallot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dylanebert/shallot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dylanebert/shallot/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/dylanebert/shallot

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for shallot AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dylanebert/shallot/agents-md/github.svg)](https://agentmods.dev/instructions/dylanebert/shallot/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dylanebert/shallot/agents-md"><img src="https://agentmods.dev/badge/instructions/dylanebert/shallot/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.

agentmods 80×15 button for shallot AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dylanebert/shallot/agents-md"><img src="https://agentmods.dev/badge/instructions/dylanebert/shallot/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 This file is loaded in full into every session.
When invoked 70 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.00070
Opus 5.5 $0.00028 $0.00028
Sonnet 5.5 $0.00014 $0.00014
Haiku 4.5 $0.00007 $0.00007

Measured 6d ago against content hash 57f5cb39bcca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shallot 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 6d 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.

AGENTS.md · 4 lines

What it actually says

Read CONTRIBUTING.md.

Pre-land check: bun check && bun run lint && bun run test --path-ignore-patterns '**/*.gpu.test.ts' && bun test --todo ./scripts/check-*.node.ts && { git diff --quiet origin/main -- crates || cargo fmt --check; } && sh scripts/clippy.sh.

Changes

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.

  1. 6d ago Changed · -35 tokens per session 57f5cb39bcca
  2. 11d ago Changed · -32 tokens per session 479b69e99669
  3. 15d ago Changed · -36 tokens per session 39448840c621
  4. 16d ago Changed · -41 tokens per session a41f8773a23c
  5. 17d ago Changed · +44 tokens per session c3489e5f9de5
  6. 18d ago Changed · -1 lines · +52 tokens per session ec08f11bcc5d
  7. 19d ago Changed · +43 tokens per session d9b020f8b936
  8. 20d ago Changed · +15 tokens per session 303371d534ec
  9. 21d ago Changed · +29 tokens per session 2dd128995fa7
  10. 24d ago First seen · 5 lines · 31 tokens per session scan A 38a508e3418e

Subscribe to this mod's changes

shallot AGENTS.md is an instructions file published in the GitHub repository dylanebert/shallot (469 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session, 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 2026-08-30.

Related

shallot AGENTS.md compared with instructions from other repositories

shallot AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
shallot AGENTS.mddylanebert/shallotInstructions file469yesterdayMITA70Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode