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/stieges/bpmn-generator/agents-mdgit clone --depth 1 https://github.com/Stieges/bpmn-generatorWrote 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/stieges/bpmn-generator/agents-md)<a href="https://agentmods.dev/instructions/stieges/bpmn-generator/agents-md"><img src="https://agentmods.dev/badge/instructions/stieges/bpmn-generator/agents-md.svg" alt="Measured on agentmods" 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 | $0.00283 | $0.00283 |
| Opus 5 | $0.00142 | $0.00142 |
| Sonnet 5 | $0.00057 | $0.00057 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
bpmn-generator 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.
What it actually says
BPMN Generator for Agents & opencode
This repository provides tools for autonomous agents to generate, validate, and manipulate BPMN 2.0 XML files.
Demo
Run the BPMN Copilot demo:
cd scripts
npm install # one-time, ~30s
npm run demo
This starts the HTTP server on http://localhost:3000 and serves the frontend.
Open your browser to that URL.
API key
For the LLM chat to work, you need an OpenAI-compatible API key. The frontend will
prompt you for it when you first click "Custom Text". The key is stored in
localStorage (browser only — never sent to disk on the server side).
If you prefer to pre-configure the key, set OPENAI_API_KEY in your shell before
running npm run demo. The server then uses it as a fallback for all LLM calls,
so requests work even without a key entered in the browser. (The backend also
exposes GET /api/v1/config, reporting envKeyConfigured, so a frontend can
detect this and skip the modal — wiring that into the UI is a separate step.)
Pre-loaded examples
Click any of the four example cards on the start screen — no key needed. The BPMN is pre-generated and rendered instantly.
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 · 34 lines · 283 tokens per session scan A 97c9433a5126
bpmn-generator AGENTS.md is an instructions file published in the GitHub repository Stieges/bpmn-generator (37 stars, last pushed 3d ago), licensed MIT. It adds 283 tokens to every session, about $0.0014 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 2026-09-04.
Other instructions, from other repositories
claude-bpmn-skill CLAUDE.md
Instructions for architawr/claude-bpmn-skill, covering claude.md, what this repo is, commands, architecture and working in this codebase.
tldraw AGENTS.md
AGENTS.md instructions for tldraw/tldraw, covering agents.md, core rules, repo overview, setup and common commands.
plantuml CLAUDE.md
Claude Code instructions for plantuml/plantuml, covering claude.md, project overview, build and test commands, build the project and run tests.
plantuml copilot-instructions.md
Copilot instructions for plantuml/plantuml: Please refer to the CLAUDE.md file for project guidelines, coding standards, and architecture notes.
tldraw CLAUDE.md
Claude Code instructions for tldraw/tldraw, a project described as: Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.
drawio-ai-kit AGENTS.md
Instructions for sparklabx/drawio-ai-kit, covering repository guidelines, tech stack & runtime and code conventions & common patterns.