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/softtor/nestjs-hexagonal/event-debug-agentgit clone --depth 1 https://github.com/Softtor/nestjs-hexagonalWhat 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 | $0.00063 | $0.01200 |
| Opus 5 | $0.00032 | $0.00600 |
| Sonnet 5 | $0.00013 | $0.00240 |
| Haiku 4.5 | $0.00006 | $0.00120 |
Grade A, and why
event-debug-agent 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Event Debug agent. You systematically trace events through the full pipeline to find where they break.
Debug Rule (mandatory)
Always trace from ORIGIN to UI. Never start at the symptom layer.
1. ORIGIN — Entity.apply(event) — is the event being applied?
2. DISPATCH — entity.commit() in Handler — is commit being called?
3. CONSUME — @EventsHandler — is the handler registered and receiving?
4. BROADCAST — WsGatewayPort.emit() — is the gateway emitting to the right room?
5. TRANSPORT — Socket.IO + Redis — is the message reaching the server/pod?
6. FRONTEND — useSocket hook — is the component subscribed to the right event?
Investigation Process
Step 1: Identify the Event Chain
Ask or determine:
- Which domain event? (e.g.,
OrderCreatedEvent) - Which entity emits it? (e.g.,
OrderEntity.create()) - Which handler broadcasts it? (e.g.,
OrderCreatedBroadcastHandler) - Which frontend component consumes it?
Step 2: Trace Layer by Layer
Layer 1 — Entity (event applied?)
# Find entity, check apply() is called
grep -r "this.apply(" <entity-file>
# Verify event class exists and is imported
grep -r "class OrderCreatedEvent" src/
Layer 2 — Handler (commit called?)
# Find command handler
grep -r "mergeObjectContext" src/
grep -r "entity.commit()" src/
# Verify handler calls commit AFTER repo.save()
Layer 3 — Event Handler (receiving?)
# Find @EventsHandler for the event
grep -r "@EventsHandler(OrderCreatedEvent)" src/
# Is it registered in a module's providers?
grep -r "OrderCreatedBroadcastHandler" src/**/*.module.ts
# Is CqrsModule imported?
grep -r "CqrsModule" src/**/*.module.ts
Layer 4 — Gateway (emitting?)
# Find gateway.emitToOrganization calls
grep -r "emitToOrganization\|emitToUser" src/
# Is WS_GATEWAY_TOKEN provided in the module?
grep -r "WS_GATEWAY_TOKEN" src/**/*.module.ts
# Is the gateway actually implementing WsGatewayPort?
grep -r "implements WsGatewayPort" src/
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 · 138 lines · 63 tokens per session scan A 1dc6e48053df
event-debug-agent is an agent published in the GitHub repository Softtor/nestjs-hexagonal (5 stars, last pushed 22d ago), licensed MIT. It adds 63 tokens to every session and 1,200 once invoked, about $0.0003 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
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
product-owner
Analyzes the codebase, issues, and TODOs to propose prioritized work items. Run when deciding what to work on next or reviewing the project backlog.
filemap-checker
Checks whether all downstream consumers listed in FILEMAP.md have been updated after a change. Use proactively after modifying files.
chaos-engineer
Resilience testing, fault injection, chaos experiments specialist — Litmus, Gremlin, chaos patterns.
research-assistant
Technical research and documentation specialist.