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 skills add DarrenLyons/agentic-ddd --skill event-stormgit clone --depth 1 https://github.com/DarrenLyons/agentic-dddWrote 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/skills/darrenlyons/agentic-ddd/event-storm)<a href="https://agentmods.dev/skills/darrenlyons/agentic-ddd/event-storm"><img src="https://agentmods.dev/badge/skills/darrenlyons/agentic-ddd/event-storm/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.
<a href="https://agentmods.dev/skills/darrenlyons/agentic-ddd/event-storm"><img src="https://agentmods.dev/badge/skills/darrenlyons/agentic-ddd/event-storm.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00074 | $0.12733 |
| Opus 5.5 | $0.00030 | $0.05093 |
| Sonnet 5.5 | $0.00015 | $0.02547 |
| Haiku 4.5 | $0.00007 | $0.01273 |
Grade A, and why
event-storm 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.
How it starts
The opening of the file, as written. The whole thing — 948 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Event Storming Facilitator
Facilitates a DDD event storming exercise to produce a shared domain model. Use when the team needs to agree on aggregate boundaries, bounded contexts, or ubiquitous language for a new or contentious area of the system.
When to use
- Aggregate / bounded-context disagreement (the model is being argued at the wrong altitude — naming aggregates without enumerating events)
- New product area being added with no existing model
- Major refactor before code lands
- Ubiquitous language drift (terms being used inconsistently)
When NOT to use:
- Bug fixes (use a focused bug-fix workflow)
- Single-feature work where the model is already clear
- Vocabulary-only fixes (just update your project glossary)
Modes
/event-storm <slug> — kick off a new storm. Defaults: focused scope, in-harness architecture.
/event-storm continue — resume an in-flight exercise from its last completed phase or stage.
/event-storm wrap — finalise deliverables.
A <slug> is a short kebab-case identifier (e.g. subscription-lifecycle, whole-product). Used for folder/file naming.
Flags
--mode=focused | big-picture— scope. Focused (default) targets a known bounded context and runs Phases 0–5. Big-picture targets the whole product to discover contexts and runs Phases 0–2 plus context discovery.--arch=in-harness | out-of-band | hybrid— architecture. In-harness (default) uses an agent team with full project context (reference shape: Claude Code agents; equivalent in any harness with multi-agent or multi-context support). Out-of-band uses one isolated dispatch per role from a clean cwd for genuine independence (reference command:claude -p; equivalent for other harnesses). Hybrid runs out-of-band positions first, then loads them into the in-harness team for stress-testing.
Scope and architecture are independent. Any combination is valid; some make more sense than others — see selection below.
Mode selection (scope)
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.
- 1mo ago First seen · 948 lines · 74 tokens per session scan A 0a11d91c9f54
event-storm is a skill published in the GitHub repository DarrenLyons/agentic-ddd (2 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 12,733 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
ddd-evans-2003
Domain-Driven Design methodology using bounded contexts, ubiquitous language, and strategic/tactical patterns.
domain-modeling
DDD practical guide: Event Storming, Bounded Contexts, Aggregates and domain-driven design patterns.
ddd
A guide to domain-driven design, a way of structuring software around the important concepts and rules of a business. It covers business boundaries, domain models, and common building blocks such as entities and value objects.
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
a-philosophy-of-software-design
Apply John Ousterhout-inspired software design rules when reducing complexity, designing module boundaries, or reviewing APIs and abstractions.
domain-driven-design
Apply Eric Evans-inspired DDD rules when modeling a complex domain, defining bounded contexts, protecting ubiquitous language, or designing aggregates.