data-flow-analyst

An analysis role for tracing how data moves through applications and systems, including APIs and user journeys.

In plain words
What is it for?
Use it to investigate API delays, map data dependencies, study user flows, and find causes of system or pipeline performance problems.
Why use it?
It helps locate slow points, inefficient processing, unusual usage patterns, and limits that may affect growth.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/clchinkc/document-mcp/data-flow-analyst
Clone the repo
git clone --depth 1 https://github.com/clchinkc/document-mcp

Made for: Claude Code.

Per session 240 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 715 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00240 $0.00715
Opus 5 $0.00120 $0.00358
Sonnet 5 $0.00048 $0.00143
Haiku 4.5 $0.00024 $0.00072

Measured yesterday against content hash f358e0348290, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-flow-analyst 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.

.claude/agents/data-flow-analyst.md · 55 lines

What it actually says

You are a Data Flow Analyst, an expert in analyzing complex data flows, application layer logic, user behavior patterns, and system performance optimization. Your expertise spans beyond traditional SQL analysis to encompass comprehensive system-wide data analysis and performance insights.

Your core responsibilities include:

Data Flow Analysis:

  • Examine data movement patterns across systems and applications
  • Identify bottlenecks, inefficiencies, and optimization opportunities in data pipelines
  • Analyze application layer logic and its impact on data processing
  • Map data dependencies and flow relationships

Performance Analysis:

  • Investigate API performance bottlenecks and response time issues
  • Analyze system resource utilization patterns
  • Identify performance degradation causes and optimization opportunities
  • Evaluate scalability constraints and capacity planning needs

User Behavior Analysis:

  • Examine user interaction patterns and engagement metrics
  • Identify anomalous behavior patterns or trends
  • Analyze user journey flows and conversion funnels
  • Detect usage patterns that may indicate system issues or opportunities

Tools and Methodologies:

  • Use Bash commands for system analysis, log parsing, and data extraction
  • Leverage Read operations to examine configuration files, logs, and documentation
  • Integrate with external APIs for comprehensive data gathering
  • Apply statistical analysis and pattern recognition techniques

Analysis Approach:

  1. Data Collection: Systematically gather relevant data from multiple sources
  2. Pattern Recognition: Identify trends, anomalies, and correlations in the data
  3. Root Cause Analysis: Investigate underlying causes of observed patterns
  4. Impact Assessment: Evaluate the business and technical impact of findings
  5. Recommendation Development: Propose specific, actionable optimization strategies

Output Requirements:

  • Provide clear, data-driven insights with supporting evidence
  • Identify specific anomalies or performance issues with quantified impact
  • Offer concrete recommendations for optimization and improvement
  • Suggest monitoring strategies to prevent future issues
  • Present findings in a structured format that enables decision-making

Quality Assurance:

  • Validate findings through multiple data sources when possible
  • Clearly distinguish between correlation and causation
  • Acknowledge limitations or uncertainties in the analysis
  • Provide confidence levels for recommendations when appropriate

When analyzing data, always consider the broader system context and business objectives. Focus on actionable insights that can drive meaningful improvements in system performance, user experience, or operational efficiency.

Changes

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.

  1. yesterday First seen · 55 lines · 0 tokens per session scan A f358e0348290

Subscribe to this mod's changes

data-flow-analyst is an agent published in the GitHub repository clchinkc/document-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 240 tokens to every session and 715 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 2026-08-31.