drawio-ai-kit AGENTS.md

drawio-ai-kit AGENTS.md is an instructions file for Codex, OpenCode from sparklabx/drawio-ai-kit. It costs 427 tokens per session, scanned A, original, MIT.

Project instructions for drawio-ai-kit, a toolkit that helps an AI create draw.io diagrams. They describe its runtime, code style, layout patterns, and rules for where generated diagram files may be written.

In plain words
What is it for?
Use them when developing the kit, running its checks, or generating diagrams with its layout and icon conventions.
Why use it?
They keep changes compatible with the repository and prevent generated diagrams from being written into the toolkit’s own source folder.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/sparklabx/drawio-ai-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/sparklabx/drawio-ai-kit

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 drawio-ai-kit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sparklabx/drawio-ai-kit/agents-md.svg)](https://agentmods.dev/instructions/sparklabx/drawio-ai-kit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sparklabx/drawio-ai-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/sparklabx/drawio-ai-kit/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 427 This file is loaded in full into every session.
When invoked 427 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00427 $0.00427
Opus 5 $0.00214 $0.00214
Sonnet 5 $0.00085 $0.00085
Haiku 4.5 $0.00043 $0.00043

Measured 3d ago against content hash 693157423e42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

drawio-ai-kit 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 3d 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 · 20 lines

What it actually says

Repository Guidelines

drawio-ai-kit helps an AI draw correct, beautiful draw.io diagrams.

[!IMPORTANT] Hard rule (see SKILL.md): The kit is read-only infrastructure. Write generated .drawio/.xml output into the user's cwd, never into the repo folder.

Tech Stack & Runtime

  • Node.js ≥18 (ESM, .nvmrc = 22) - "type": "module"; zero default exports (named exports only).
  • npm (respect package-lock.json). Node built-in node:test (no test deps).
  • For complete details on the architecture, directories, and files, see docs/developer-guide.md.

Code Conventions & Common Patterns

  • No bundler, no transpiler, no TypeScript. Plain .mjs only.
  • Catalog injection: loadCatalog() returns the merged catalog; every core.mjs function takes catalog as first arg; builder.mjs stores it as this.c.
  • Declarative layout > coordinates: Build node trees with layout-engine.mjs factories (group/frame/grid + icon/box) → renderTree(d, root)Diagram. Hardcoding x/y coordinates violates the design pattern.
  • Color = Identity: Never recolor AWS icons away from their category color (colorFor: entry.color → categoryColors[category]#232F3E).
  • Nesting Hierarchy: Group nesting order is enforced by GROUP_LEVEL: Cloud/Account/Region=0 → VPC=2 → AZ=3 → Subnet=4 → SG=5.
  • Edge Rounding Policy: Tree/fanout roles → sharp (rounded=0); flow → type's edgeCorner.
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. 3d ago First seen · 20 lines · 427 tokens per session scan A 693157423e42

Subscribe to this mod's changes

drawio-ai-kit AGENTS.md is an instructions file published in the GitHub repository sparklabx/drawio-ai-kit (638 stars, last pushed 23d ago), licensed MIT. It adds 427 tokens to every session, about $0.0021 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 2026-08-30.

Related

Other instructions, from other repositories

awesome-kubernetes CLAUDE.md

Instructions for nubenetes/awesome-kubernetes, covering claude.md — nubenetes project instructions for claude code, git workflow: gitflow, branches, release process (mandatory for all releases) and versioning.

nubenetes/awesome-kubernetes · 1,242 tokens

aurora AGENTS.md

Instructions for Arvo-AI/aurora, covering aurora - agent guidelines, commands, docker deployments, architecture and secrets management (vault).

Arvo-AI/aurora · 2,731 tokens

agent-kernel AGENTS.md

Instructions for yaalalabs/agent-kernel, covering agents.md, two skill sets — don't confuse them, repo map, adapter architecture — stay unopinionated and setup, build, lint, test.

yaalalabs/agent-kernel · 2,326 tokens

nudgebee CLAUDE.md

Claude Code instructions for nudgebee/nudgebee, covering nudgebee monorepo - development guide, module structure, ai coding principles, 2. definition of done and 3. fix the class, not the instance (rule of three).

nudgebee/nudgebee · 4,019 tokens

nudgebee GEMINI.md

Gemini CLI instructions for nudgebee/nudgebee: This file used to mirror CLAUDE.md. Maintaining two long copies of the same document caused drift — they were updated independently and disagreed on conventions, decisions, and the architecture-decisions log.

nudgebee/nudgebee · 213 tokens

strata CLAUDE.md

Claude Code instructions for makedirectory/strata, covering claude.md, commands, the core architectural invariant, layout & data flow and persistence.

makedirectory/strata · 1,291 tokens