bpmn-package-explorer

bpmn-package-explorer is a skill for Claude Code, Codex from BlackBeltTechnology/pi-agent-dashboard. It costs 229 tokens per session (1,747 once invoked), scanned A, original, MIT.

A tool for creating, checking, and viewing BPMN 2.0 process diagrams from plain-language descriptions. BPMN is a standard format for mapping business processes, including decisions and user forms.

In plain words
What is it for?
Use it to model workflows, render BPMN or DMN files, create decision tables and forms, and package related process files together.
Why use it?
It turns described processes into structured diagrams while checking that the generated layout does not corrupt the process meaning.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to model workflows, render BPMN or DMN files, create decision tables and forms, and package related process files together.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blackbelttechnology/pi-agent-dashboard/bpmn-package-explorer
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.

Any agent
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill bpmn-package-explorer
Clone the repo
git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard

Made for: Claude Code, Codex.

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-package-explorer

README.md
[![agentmods](https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/bpmn-package-explorer/github.svg)](https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/bpmn-package-explorer)
Your own site
<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/bpmn-package-explorer"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/bpmn-package-explorer/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-package-explorer

Your own site · 80×15
<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/bpmn-package-explorer"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/bpmn-package-explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 229 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,747 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00229 $0.01747
Opus 5 $0.00114 $0.00873
Sonnet 5 $0.00046 $0.00349
Haiku 4.5 $0.00023 $0.00175

Measured 8d ago against content hash e0ca9d51a3fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

bpmn-package-explorer 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 8d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (assets/bpmn-js/bpmn-navigated-viewer.production.min.js, assets/dmn-js/dmn-viewer.production.min.js, assets/lib/bpmn-pipeline.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/pi-forms-bpmn/.pi/skills/bpmn-package-explorer/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BPMN Package Explorer

Generate and view BPMN 2.0 process packages: a process plus the decisions its rule tasks evaluate, the forms its user tasks present, and a manifest binding them — kept as plain, vendor-neutral BPMN 2.0. Buildless and offline: it vendors pre-built viewers and a self-contained Node layout bundle; generating or rendering a package needs no npm install, no bundler and no network. Requires Node ≥ 20.12 and a browser.

When to use

Model a business process from a prose description; make/view a BPMN diagram or a DMN decision table; build a cross-linked process package. Hungarian triggers: „csinálj egy folyamatábrát”, „rajzold meg a folyamatot”, „döntési tábla”, „nézd meg ezt a .bpmn fájlt”.

The two guarantees

  • Never a corrupt diagram. A language model can author correct BPMN semantics but not a readable coordinate set. bpmn-auto-layout fills that gap but fails silently on sub-processes, pools and lanes (all outputs stay schema-valid). A layout guard verifies every laid-out diagram against its own semantics and aborts on any corruption, in strict mode.
  • Vendor-neutral. The .bpmn/.dmn/.form files carry no engine extension. A sidecar package.yaml holds the link graph (bindings, roles), so a package opens in Camunda Modeler, Signavio or any conformant tool.

Generation workflow

The agent authors the artifacts (guided by the references); the pipeline runs the mechanical steps, each failing loudly:

  1. Author semantics — one or more semantics-only .bpmn (no geometry), applying the authoring envelope and identifier rules. Emit <bpmn:incoming>/<bpmn:outgoing> on every connected flow node.
  2. Author artifacts — the .dmn decisions and .form schemas.
  3. Write package.yaml — the bindings and roles.
  4. Validate the manifestnode scripts/generate-cli.mjs <packageDir> runs the envelope check, manifest validation, layout + guard, and assembles a render root; it stops before serving on any error.
  5. Serve + canvas — serve the printed render-root path with node scripts/serve.mjs <renderRoot> [port] (CORS-enabled) and open the printed URL on the canvas (never file://). Do not use serve_mockup for canvas display: it omits Access-Control-Allow-Origin, so the viewer's fetch('package-data.json') fails in the opaque-origin sandbox (“Failed to fetch” → blank diagram).

Read the full file on GitHub · 127 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 127 lines · 229 tokens per session scan A e0ca9d51a3fe

Subscribe to this mod's changes

bpmn-package-explorer is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (279 stars, last pushed yesterday), licensed MIT. It adds 229 tokens to every session and 1,747 once invoked, about $0.0011 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 2026-09-03.