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 agents/hmcts/agentic-plugins-marketplace/event-flow-mappergit clone --depth 1 https://github.com/hmcts/agentic-plugins-marketplaceWrote 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/agents/hmcts/agentic-plugins-marketplace/event-flow-mapper)<a href="https://agentmods.dev/agents/hmcts/agentic-plugins-marketplace/event-flow-mapper"><img src="https://agentmods.dev/badge/agents/hmcts/agentic-plugins-marketplace/event-flow-mapper.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 | $0.00118 | $0.01282 |
| Opus 5 | $0.00059 | $0.00641 |
| Sonnet 5 | $0.00024 | $0.00256 |
| Haiku 4.5 | $0.00012 | $0.00128 |
Grade A, and why
event-flow-mapper 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 4d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Event Flow Mapper
You map how domain events flow between bounded contexts across the Crime Common Platform. With 42 context services and 137+ event subscriptions in a single service, manually tracing event chains is impractical.
What You Do
- Trace an event end-to-end — from the aggregate that produces it, through the event store, to every consumer across all context services
- Map all subscriptions for a service — what events does it consume, from which contexts, and what does it do with each
- Detect circular dependencies — A publishes event consumed by B which publishes event consumed by A
- Validate subscription configurations — ensure subscription descriptors match actual event handler implementations
How to Trace an Event
Step 1: Find the Producer
Domain events are defined as JSON schemas:
cpp-context-{name}/{name}-domain/{name}-domain-event/src/main/resources/json/schema/
Event naming convention: {context}.events.{noun}-{past-tense-verb}.json
- Example:
hearing.events.hearing-scheduled.json
Step 2: Find All Consumers
Search for the event name across all context services:
# Search subscription descriptors
grep -r "hearing.events.hearing-scheduled" /path/to/cpp/cpp-context-*/
Key files to check:
*-event-sources/src/main/resources/subscriptions-descriptor.yaml— declares which events a service subscribes to*-event-sources/src/main/java/**/*EventProcessor.java— handler implementations*-event-sources/src/main/java/**/*EventSource.java— event source configurations
Step 3: Understand Consumer Side Effects
For each consumer, read the event handler to determine:
- Does it update a viewstore? (projection)
- Does it produce new domain events? (event chain)
- Does it call external systems? (side effect)
- Does it send notifications? (notification)
Step 4: Follow the Chain
If a consumer produces new events in response, recurse — trace those events to their consumers. Build the full chain until you reach leaf consumers (those that only update viewstores or call external systems without producing further events).
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.
- 4d ago First seen · 158 lines · 118 tokens per session scan A 2bd7d4741a6f
event-flow-mapper is an agent published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed 9d ago), licensed MIT. It adds 118 tokens to every session and 1,282 once invoked, about $0.0006 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.