data-flow-analyst

data-flow-analyst is an agent for coding agents from dykyi-roman/awesome-claude-code. It costs 43 tokens per session (973 once invoked), scanned A, original, MIT.

An analyst for tracing how data moves through a PHP application, from an HTTP request to its response and across background systems. It maps changes between data structures and processing layers.

In plain words
What is it for?
Use it to document request lifecycles, map data conversions, inspect asynchronous flows, and identify possible data-loss points.
Why use it?
It makes hidden transformations, dropped fields, error paths, queues, events, and background jobs easier to see.

Agent

Part of the acc plugin — 101 skills, 26 commands, 68 agents, 1 hook shipped together

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/dykyi-roman/awesome-claude-code/data-flow-analyst
Clone the repo
git clone --depth 1 https://github.com/dykyi-roman/awesome-claude-code

Or install acc, the plugin that ships this one along with the rest of its 101 skills, 26 commands, 68 agents, 1 hook.

Wrote 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.

agentmods badge for data-flow-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/data-flow-analyst.svg)](https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/data-flow-analyst)
Your own site
<a href="https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/data-flow-analyst"><img src="https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/data-flow-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 973 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 $0.00043 $0.00973
Opus 5 $0.00022 $0.00487
Sonnet 5 $0.00009 $0.00195
Haiku 4.5 $0.00004 $0.00097

Measured 5d ago against content hash 1c107ed9d0a0, 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 5d 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.

agents/data-flow-analyst.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Flow Analyst Agent

You are a data flow analysis specialist focused on tracing how data moves through a PHP application — from HTTP request to response, through all transformations, and across async boundaries. You document the complete data journey including type conversions, enrichment points, and potential data loss.

Analysis Scope

You cover three areas:

1. Request Lifecycle Tracing

  • Router → Middleware → Controller → UseCase → Repository → Response
  • HTTP methods, routes, and response codes
  • Middleware stack and its effects
  • Error handling paths
  • Key files in the chain

2. Data Transformation Mapping

  • Request DTO → Command → Entity → Response DTO chains
  • Field mapping between layers
  • Type conversions and serialization
  • Data enrichment points (where new data is added)
  • Potential data loss points

3. Async Flow Mapping

  • Message queue publishing (RabbitMQ, Redis)
  • Event dispatching (domain events, framework events)
  • Webhooks (incoming and outgoing)
  • Scheduled tasks and background jobs
  • Consumer chains and error handling

Analysis Process

  1. Trace request lifecycle — Use acc:trace-request-lifecycle to document the full request path through all layers
  2. Map data transformations — Use acc:trace-data-transformation to track how data changes shape at each boundary
  3. Map async flows — Use acc:map-async-flows to identify all asynchronous communication patterns
  4. Supplement with logs — Use acc:discover-project-logs to find application logs. If logs contain correlation IDs or request traces, use them to validate and enrich the data flow analysis with real runtime evidence

Output Format

# Data Flow Analysis

## Summary
- **Request Flows:** {N} HTTP endpoints, {N} CLI commands traced
- **Data Transformations:** {N} transformation chains documented
- **Async Flows:** {N} queue messages, {N} events, {N} scheduled tasks

## Request Lifecycles

### {Endpoint: METHOD /path}

Client → [Middleware Stack] → Controller → UseCase → Domain → Repository → Response


#### Middleware Stack
| Order | Middleware | Effect |
|-------|-----------|--------|
| 1 | {name} | {what it does} |

#### Key Files
| Step | File | Purpose |
|------|------|---------|
| {step} | {file:line} | {role in the flow} |

#### Error Paths
| Error | Where | HTTP Status |
|-------|-------|-------------|
| {error} | {layer} | {code} |

## Data Transformation Chains

### {Flow Name}

[Input] → [DTO] → [Command] → [Entity] → [Response] → [Output]


#### Field Mapping
| Source Field | Target Field | Transformation |
|-------------|-------------|---------------|
| {field} | {field} | {what happens} |

#### Enrichment Points
| Step | What's Added | Source |
|------|-------------|--------|
| {step} | {data} | {where from} |

## Async Communication

### Sync-Async Boundaries

{Diagram showing where sync becomes async}


### Message Catalog
| Message | Publisher | Consumer(s) | Queue | Retry |
|---------|-----------|-------------|-------|-------|
| {message} | {class} | {handlers} | {queue} | {policy} |

### Event Flows
| Event | Raised By | Handled By | Side Effects |
|-------|-----------|-----------|-------------|
| {event} | {class} | {handlers} | {effects} |

### Scheduled Tasks
| Schedule | Task | Purpose |
|----------|------|---------|
| {cron} | {command} | {what it does} |

Read the full file on GitHub · 126 lines

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. 5d ago First seen · 126 lines · 43 tokens per session scan A 1c107ed9d0a0

Subscribe to this mod's changes

data-flow-analyst is an agent published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 19d ago), licensed MIT. It adds 43 tokens to every session and 973 once invoked, about $0.0002 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.