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 sethdford/claude-skills --skill data-flow-diagramgit clone --depth 1 https://github.com/sethdford/claude-skillsWrote 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/sethdford/claude-skills/data-flow-diagram)<a href="https://agentmods.dev/skills/sethdford/claude-skills/data-flow-diagram"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/data-flow-diagram/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/sethdford/claude-skills/data-flow-diagram"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/data-flow-diagram.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 | $0.00037 | $0.00619 |
| Opus 5.5 | $0.00015 | $0.00248 |
| Sonnet 5.5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
data-flow-diagram 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Flow Diagram
Visualize data movement, transformations, and storage across systems to identify bottlenecks and design efficient pipelines.
Context
You are designing how data flows between systems. Document data sources, transformations, sinks, and timing. Read existing architecture documents and data pipelines.
Domain Context
Based on enterprise data architecture patterns and streaming frameworks:
- Batch Processing: High-latency, high-throughput; good for analytics and reports
- Stream Processing: Low-latency, event-driven; good for realtime features and monitoring
- Lambda Architecture: Batch + streaming for both completeness and speed
- Transformation Stages: Extract, transform (business logic), load; validate at each stage
- Data at Rest vs In Motion: Storage systems vs message queues and streams
Instructions
-
Identify Data Sources: List all sources (APIs, databases, event streams, user uploads). For each, note volume, frequency, data format, and reliability.
-
Map Transformations: What business logic applies? Normalize, enrich, aggregate, filter? Where does the transformation happen (source, pipeline, destination)? What's the latency requirement?
-
Define Sinks and Destinations: Where does processed data land? Data warehouse for analytics? Cache for serving? Message queue for downstream consumers? API for external systems?
-
Choose Processing Model: Batch (daily jobs) or streaming (realtime)? Hybrid (Lambda)? Consider latency, cost, operational complexity, and consistency needs.
-
Diagram the Flow: Show sources, transformation stages, queues, storage, consumers. Mark synchronous vs asynchronous flows. Identify potential failure points and bottlenecks.
Anti-Patterns
- Spaghetti Pipelines: Too many ad-hoc integrations between systems. Result: impossible to understand data lineage, hard to modify. Guard: Create canonical pipeline architecture; consolidate sources.
- No Staging Environment: Transform data directly to production analytics. Result: bugs corrupt historical data. Guard: Stage transformations; validate data quality before final load.
- Ignoring Failure Recovery: Assume pipelines always succeed. Result: gaps in data, silent failures. Guard: Implement idempotent transformations, track completion, replay on failure.
- Tight Coupling Between Stages: Output of one transformation directly feeds next without buffering. Result: failure cascades. Guard: Use message queues; decouple producers and consumers.
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 · 48 lines · 37 tokens per session scan A 82f228c47194
data-flow-diagram is a skill published in the GitHub repository sethdford/claude-skills (46 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 619 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
pydantic-ai-expert
Expert guide for type-safe Python AI agent development with Pydantic AI — dependency injection, structured outputs, model-agnostic routing, and graph workflows / Panduan ahli pengembangan agen AI Python type-safe dengan Pydantic AI.
voice-ai-realtime-agent
Expert guide for Ultra-Low Latency Conversational Voice AI (<300ms), WebRTC bidirectional streaming, OpenAI Realtime API, Gemini Multimodal Live Audio, LiveKit Agents, and Semantic VAD / Panduan ahli AI suara percakapan real-time berlatensi ultra-rendah.
LLM
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.
serving-llms-vllm
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
gemini-interactions-api
Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…