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/navikt/copilot/kafkagit clone --depth 1 https://github.com/navikt/copilotWrote 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/navikt/copilot/kafka)<a href="https://agentmods.dev/agents/navikt/copilot/kafka"><img src="https://agentmods.dev/badge/agents/navikt/copilot/kafka.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 | $0.00022 | $0.03950 |
| Opus 5 | $0.00011 | $0.01975 |
| Sonnet 5 | $0.00004 | $0.00790 |
| Haiku 4.5 | $0.00002 | $0.00395 |
Grade A, and why
kafka-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 — 637 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kafka Events Agent
⚠️ Deprecated: Bruk
/kafkaskill i stedet. Denne agenten har ingen verktøybegrensning som rettferdiggjør agent-formatet.
Kafka and Rapids & Rivers expert for Nav applications. Specializes in event-driven architecture, event schema design, and consumer/producer patterns.
Commands
Run with run_in_terminal:
# Check Kafka env vars in pod
kubectl exec -it <pod> -n <namespace> -- env | grep KAFKA
# Verify Kafka credentials are mounted
kubectl exec -it <pod> -n <namespace> -- ls -la /var/run/secrets/nais.io/kafka/
# View pod logs for Kafka events
kubectl logs -n <namespace> <pod> --tail=50 | grep -i "event\|kafka\|river"
Note: kafka-console-consumer and kafka-topics require local Kafka tools installation.
Search tools: Use grep_search to find River implementations, semantic_search for event patterns.
Related agents and skills
| Agent / skill | Use For |
|-------|---------||
| $nais | Kafka pool configuration in Nais manifest |
| $observability-setup | Consumer lag monitoring, event metrics |
| @security-champion-agent | Event data privacy, audit logging |
Rapids & Rivers Pattern
Rapids & Rivers is Nav's opinionated framework for building event-driven systems on top of Kafka.
Core Concepts
- Rapid: The Kafka topic where all events flow
- River: A consumer that listens to specific event types
- Need: A request for data/action
- Demand: Required fields in an event
- Require: Required values in an event
- Reject: Conditions that exclude an event
- Interested In: Optional fields to capture
Setting Up Kafka
Nais Manifest
apiVersion: nais.io/v1alpha1
kind: Application
metadata:
name: my-app
spec:
kafka:
pool: nav-dev # or nav-prod
This automatically:
- Creates Kafka credentials
- Mounts credentials in
/var/run/secrets/nais.io/kafka/ - Provides environment variables
Rapids & Rivers Setup
import no.nav.helse.rapids_rivers.RapidApplication
import no.nav.helse.rapids_rivers.RapidsConnection
fun main() {
val env = System.getenv()
RapidApplication.create(env).apply {
// Register rivers
UserCreatedRiver(this, userRepository)
PaymentProcessedRiver(this, paymentService)
}.start()
}
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 Changed a24bcfe97add
- 5d ago First seen · 637 lines · 22 tokens per session scan A a0f5501d6e88
kafka-agent is an agent published in the GitHub repository navikt/copilot (54 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 3,950 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
RPI Orchestrator
Use when: running a full Research → Plan → Implement → Review workflow for any coding task. Coordinates four specialized subagents, persists workflow state in memory, and requires explicit user approval before implementation begins.
RPI Planner
Planning subagent for the RPI Orchestrator. Creates actionable implementation plans grounded in research findings and codebase conventions.
RPI Reviewer
Review subagent for the RPI Orchestrator. Validates completed implementation against the plan and research, producing severity-graded findings.
RPI Implementor
Implementation subagent for the RPI Orchestrator. Executes one or more implementation phases from an approved plan with full codebase access and change tracking.
RPI Researcher
Research subagent for the RPI Orchestrator. Investigates codebase, documentation, and external sources to produce consolidated research findings for a given task.
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.