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 Dynatrace/dynatrace-for-ai --skill dt-obs-network-flowsgit clone --depth 1 https://github.com/Dynatrace/dynatrace-for-aiWrote 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/dynatrace/dynatrace-for-ai/dt-obs-network-flows)<a href="https://agentmods.dev/skills/dynatrace/dynatrace-for-ai/dt-obs-network-flows"><img src="https://agentmods.dev/badge/skills/dynatrace/dynatrace-for-ai/dt-obs-network-flows/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/dynatrace/dynatrace-for-ai/dt-obs-network-flows"><img src="https://agentmods.dev/badge/skills/dynatrace/dynatrace-for-ai/dt-obs-network-flows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
- Socket pass
- Snyk pass
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 | $0.00235 | $0.01876 |
| Opus 5 | $0.00118 | $0.00938 |
| Sonnet 5 | $0.00047 | $0.00375 |
| Haiku 4.5 | $0.00023 | $0.00188 |
Grade A, and why
dt-obs-network-flows 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 12d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Network Flows Skill
Analyze network traffic in Dynatrace across three flow data sources. This skill covers the use cases network flows enable and routes each question to the right source and reference file. The detailed, source-specific DQL lives in the reference files.
What Network Flows Tell You
Network flow data answers questions that metrics and traces cannot:
- Who talks to whom — communication dependencies between hosts, processes, pods, services, and external endpoints
- Top talkers — which entities generate the most traffic, by bytes or connection count
- Connection health — resets, timeouts, retransmissions, and round-trip time (RTT) per conversation
- Traffic composition — protocol (TCP/UDP), destination ports, direction (client vs server)
- Peer resolution — mapping raw IP:port peers back to monitored entities (host, process, pod, service) or flagging them as external
The Three Flow Sources
Choose the source based on where the traffic is and what is capturing it. When more than one applies, prefer the source with the richest entity context (usually OneAgent).
| Source | Captured by | Data location | Entity context | Use when |
|---|---|---|---|---|
| OneAgent flows | OneAgent network agent on the host | events in the default_network_flows Grail bucket |
Rich — the capturing entity (client or server) resolved to host / process / pod smartscape IDs; the remote peer as IP:port | Traffic to/from OneAgent-monitored hosts, processes, or Kubernetes pods. The default and most detailed source. |
| NetFlow / IPFIX / sFlow | Network devices (switches, routers), ingested via an OpenTelemetry Collector | logs (otel.scope.name == "otelcol/netflowreceiver"; recommend routing to a dedicated bucket) |
Device/interface level — raw IPs, exporter, interfaces; no smartscape entities | Traffic seen by network hardware. Covers east-west and north-south flows at the network layer. |
| Cloud flow logs | Cloud provider (AWS VPC / TGW; Azure, GCP not yet documented) | logs (log.type == "aws.vpc" / "aws.tgw"; recommend routing to a dedicated bucket) |
Cloud resource level — VPC / subnet / AZ / ENI, TGW attachment; raw IPs, no smartscape entities | Traffic within/across cloud networks, including managed services and resources without an agent. |
What ships with it
7 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.
- references/cloud-flows/aws/aws.md 22 KB
- references/cloud-flows/aws/configuration.md 4.3 KB
- references/netflow/configuration.md 3.7 KB
- references/netflow/netflow.md 11 KB
- references/oneagent-flows/configuration.md 3.2 KB
- references/oneagent-flows/oneagent-flows.md 15 KB
- references/peer-resolution/peer-resolution.md 3.9 KB
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.
- 12d ago First seen · 85 lines · 235 tokens per session scan A 2dca4f14f5e9
dt-obs-network-flows is a skill published in the GitHub repository Dynatrace/dynatrace-for-ai (137 stars, last pushed yesterday), licensed Apache-2.0. It adds 235 tokens to every session and 1,876 once invoked, about $0.0012 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 skills, from other repositories
dtctl
Investigate incidents, debug performance issues, analyze logs, and manage observability resources in Dynatrace using the dtctl CLI. Use this skill whenever the user asks about error rates, latency spikes, service health, crash-looping pods, web vitals, SLO status, open problems, root cause analysis, log patterns…
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…