agentmods.dev

bpmn-generator: Instructions file for Claude Code

CLAUDE.md

bpmn-generator CLAUDE.md is an instructions file for Claude Code from Stieges/bpmn-generator. It costs 25,223 tokens per session, scanned A, original, MIT.

Project instructions for generating BPMN 2.0 process diagrams from structured JSON. BPMN is a standard notation for describing business processes, and the output can be opened by tools such as Camunda Modeler.

In plain words
What is it for?
It guides conversion from natural-language process descriptions to validated JSON, automatic layout, and BPMN XML and SVG output.
Why use it?
It separates process meaning from diagram layout, reducing the risk that generated coordinates or XML break the diagram.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Stieges/bpmn-generator's own configuration. It tells Claude Code how to work on bpmn-generator 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 bpmn-generator configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is │ ../cross/decision-doc.js, for the opt-in `decisions` option — text, no rule,.

not rated 56repo +2 changed 11d ago A scan 25,223 tokens original MIT
View source ↗ Stieges/bpmn-generator
Reuse

Borrowing it

Nothing to install: this file belongs to Stieges/bpmn-generator. 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/Stieges/bpmn-generator/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Stieges/bpmn-generator

Made for: Claude Code.

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 bpmn-generator CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stieges/bpmn-generator/claude-md/github.svg)](https://agentmods.dev/instructions/stieges/bpmn-generator/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/stieges/bpmn-generator/claude-md"><img src="https://agentmods.dev/badge/instructions/stieges/bpmn-generator/claude-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 bpmn-generator CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/stieges/bpmn-generator/claude-md"><img src="https://agentmods.dev/badge/instructions/stieges/bpmn-generator/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25,223 This file is loaded in full into every session.
When invoked 25,223 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.25223 $0.25223
Opus 5.5 $0.10089 $0.10089
Sonnet 5.5 $0.05045 $0.05045
Haiku 4.5 $0.02522 $0.02522

Measured 11d ago against content hash 9533ddb68365, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bpmn-generator CLAUDE.md scanned grade A with 1 finding 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 11d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Subprocess (expanded) → `tests/fixtures/expanded-subprocess.json`
CLAUDE.md · 896 lines

How it starts

The opening of the file, as written. The whole thing — 896 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — BPMN Generator

Project Context

Enterprise BPMN 2.0 Generator: JSON Logic-Core → Validation → ElkJS Layout → BPMN 2.0 XML + SVG. OMG BPMN 2.0.2 compliant (ISO/IEC 19510:2013). Compatible with bpmn.io / Camunda Modeler.

Used as a Claude Code Skill (SKILL.md) — the LLM extracts Logic-Core JSON from natural language, the pipeline handles layout and serialization. The LLM NEVER touches coordinates.

Glossary

  • Logic-Core: the JSON intermediate format between LLM and pipeline. Schema in references/input-schema.json, prose in references/logic-core-schema.md. Example: tests/fixtures/simple-approval.json.
  • BPMN 2.0.2: OMG standard (ISO/IEC 19510:2013) for business process notation. We emit XML compatible with bpmn.io and Camunda Modeler.
  • BPMNDI: BPMN Diagram Interchange — the <bpmndi:*> namespace that carries graphical layout (coordinates, waypoints) alongside the semantic XML.
  • Pool / Lane: a Pool is a participant in a collaboration (its own process boundary); Lanes partition a Pool into roles/actors. Pools communicate via Message Flows.
  • WF-Net: Workflow-Net — a restricted Petri-Net with one source and one sink. Used for soundness analysis (WF01–WF03 rules).
  • Soundness: a process is sound if every case can reach the end state, no dead activities, no proper deadlocks. Petri-Net property.
  • Sugiyama: layered graph drawing algorithm (Sugiyama et al., 1981). ElkJS implements a variant; we use it via the org.eclipse.elk.layered algorithm.
  • ElkJS Layered: JavaScript port of the Eclipse Layout Kernel's layered algorithm. Our auto-layout engine — see scripts/bpmn/layout.js.
  • Bruce Silver Method & Style: industry-recognized style conventions for BPMN diagrams. Most M-layer rules derive from this work — M11 is our own (the decisionRef bridge), not Silver.
  • MCP: Model Context Protocol — the protocol Claude Code uses to talk to external tools. We expose the generator via scripts/mcp-bpmn-server.js.
  • MaD: Model-and-Data sanity check used by the robustness subsystem to validate synthetic fixtures.
  • Golden file: an .expected.bpmn (or .expected.svg) committed alongside a fixture; tests fail if output diverges.

Read the full file on GitHub · 896 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. 11d ago Changed · +2 lines · +50 tokens per session 9533ddb68365
  2. 13d ago Changed · +218 lines · +7,364 tokens per session 7bf6da6ff4b1
  3. 14d ago Changed · +99 lines · +4,545 tokens per session 392b691b631d
  4. 1mo ago First seen · 577 lines · 13,264 tokens per session scan A 744521de3b7f

Subscribe to this mod's changes

bpmn-generator CLAUDE.md is an instructions file published in the GitHub repository Stieges/bpmn-generator (56 stars, last pushed 13d ago), licensed MIT. It adds 25,223 tokens to every session, about $0.1009 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Design and UXbpmnbpmn2diagramelkjsmcpprocess-modeling
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,581 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens