core-sdk: Instructions file for Codex

AGENTS.md

core-sdk AGENTS.md is an instructions file for Codex, OpenCode from Flowscape-UI/core-sdk. It costs 4,115 tokens per session, scanned A, original, MIT.

Repository instructions for agents working on the Flowscape core SDK, a framework-independent engine for graphical editors and infinite canvases. They describe the project layout, architecture, and rules for its public programming interface.

In plain words
What is it for?
Use them when changing the engine, playground, documentation site, or shared tooling in this Bun and Turborepo monorepo—a repository containing several related projects managed together.
Why use it?
They give coding agents project-specific context and constraints, helping them make changes that fit the repository instead of treating it like a generic application.

Instructions file for CodexOpenCode

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

This is Flowscape-UI/core-sdk's own configuration. It tells Codex and OpenCode how to work on core-sdk 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 core-sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Flowscape-UI/core-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.

Copy the file
curl -O https://raw.githubusercontent.com/Flowscape-UI/core-sdk/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Flowscape-UI/core-sdk

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 core-sdk AGENTS.md

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

agentmods 80×15 button for core-sdk AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/flowscape-ui/core-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/flowscape-ui/core-sdk/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,115 This file is loaded in full into every session.
When invoked 4,115 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 $0.04115 $0.04115
Opus 5.5 $0.01646 $0.01646
Sonnet 5.5 $0.00823 $0.00823
Haiku 4.5 $0.00411 $0.00411

Measured 1mo ago against content hash a3abf1d84fac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

core-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.

AGENTS.md · 620 lines

How it starts

The opening of the file, as written. The whole thing — 620 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Purpose

This file defines the default working rules for AI coding agents operating in the Flowscape repository.

Flowscape is a developer-first, framework-agnostic 2D engine for building infinite-canvas editors, design tools, visual builders, whiteboards, diagram editors, and similar graphical applications.

Treat Flowscape as an engine, not as an application framework or a collection of UI components. Preserve the separation between scene state, node state, rendering, input, hosts, and application-level code.

These rules apply to the entire repository unless a more specific AGENTS.md exists deeper in the directory tree.


Repository Layout

Flowscape is a Bun + Turborepo monorepo.

flowscape/
├── apps/
│   ├── docs/
│   └── playground/
├── packages/
│   └── engine/
├── package.json
├── turbo.json
└── bun.lock

Primary ownership:

  • packages/engine - the Flowscape engine, published as @flowscape-ui/core-sdk.
  • apps/playground - the development and manual-testing application.
  • apps/docs - the Docusaurus documentation site.
  • root - monorepo orchestration and shared tooling only.

Add dependencies to the workspace that actually uses them. Do not place package-specific runtime dependencies in the root package.


Project Identity and Architectural Direction

Flowscape is a low-level scene engine. It should provide reusable foundations for editor-like products without becoming coupled to a specific UI framework or product implementation.

Core principles:

  1. Keep engine state independent from rendering-backend objects whenever practical.
  2. Keep rendering logic out of node/model classes.
  3. Keep input/controller logic separate from renderers.
  4. Keep application-specific behavior out of the engine unless it is a reusable editor primitive.
  5. Prefer stable, extensible public APIs over shortcuts that expose implementation details.
  6. Preserve the ability to evolve rendering backends without rewriting product logic.
  7. Do not introduce abstractions only because they look cleaner; introduce them when they solve a real ownership, reuse, performance, or extensibility problem.

Read the full file on GitHub · 620 lines

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. 1mo ago First seen · 620 lines · 4,115 tokens per session scan A a3abf1d84fac

Subscribe to this mod's changes

core-sdk AGENTS.md is an instructions file published in the GitHub repository Flowscape-UI/core-sdk (49 stars, last pushed 2mo ago), licensed MIT. It adds 4,115 tokens to every session, about $0.0165 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 2026-10-02.

Related

core-sdk AGENTS.md compared with instructions from other repositories

core-sdk AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
core-sdk AGENTS.mdFlowscape-UI/core-sdkInstructions file492mo agoMITA4,115Codex, 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