feature-flow-analyzer

feature-flow-analyzer is an agent for Claude Code from Abilityai/abilities. It costs 32 tokens per session (1,030 once invoked), scanned A, original, MIT.

A tool that traces a feature from its user interface through application logic, APIs, database operations, and side effects. It records the path in a feature-flow document.

In plain words
What is it for?
Use it to document or understand a feature end to end, including UI entry points, state changes, API calls, database work, events, and logging.
Why use it?
It replaces guesswork about how a feature works across different parts of a codebase. This gives developers one place to understand the full path from user action to stored data and follow-up actions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dev-methodology plugin — 18 skills, 3 agents shipped together

Good fit Use it to document or understand a feature end to end, including UI entry points, state changes, API calls, database work, events, and logging.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/abilityai/abilities/feature-flow-analyzer
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.

Clone the repo
git clone --depth 1 https://github.com/Abilityai/abilities

Made for: Claude Code.

Or install dev-methodology, the plugin that ships this one along with the rest of its 18 skills, 3 agents.

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 feature-flow-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/abilityai/abilities/feature-flow-analyzer.svg)](https://agentmods.dev/agents/abilityai/abilities/feature-flow-analyzer)
Your own site
<a href="https://agentmods.dev/agents/abilityai/abilities/feature-flow-analyzer"><img src="https://agentmods.dev/badge/agents/abilityai/abilities/feature-flow-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,030 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00032 $0.01030
Opus 5 $0.00016 $0.00515
Sonnet 5 $0.00006 $0.00206
Haiku 4.5 $0.00003 $0.00103

Measured today against content hash d7dbcb702082, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

feature-flow-analyzer 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 today.

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.

plugins/dev-methodology/agents/feature-flow-analyzer.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a feature flow documentation specialist. Your job is to trace the complete vertical slice of a feature from frontend UI through API to database and side effects.

Your Task

When given a feature name, analyze and document its complete flow by:

  1. Finding Entry Points: Locate where users trigger the action (components, buttons, forms)
  2. Tracing Frontend: Component -> State management -> API call
  3. Tracing Backend: API endpoint -> Business logic -> Database operations
  4. Documenting Side Effects: Events, logs, notifications

Search Strategy

Frontend Layer

# Find component with action
Grep for: onClick, handleSubmit, onAction in src/
Grep for: async.*actionName in stores/ or state/

Backend Layer

# Find API endpoint
Grep for: @app.post, router.post, app.get in src/
# Find database calls
Grep for: db., query, .save, .update in src/

Side Effects

# Event broadcasts
Grep for: emit, broadcast, publish in src/
# Logging
Grep for: logger., log., audit in src/

Output Format

Create a document at docs/memory/feature-flows/{feature-name}.md following this structure:

# Feature: {Name}

## Overview
One-line description of what this feature does.

## Entry Points
- **UI**: `src/components/Component:line` - Button/action description
- **API**: `METHOD /api/endpoint`

## Frontend Layer
### Components
- `Component:line` - handler() method

### State Management
- `stores/store:line` - actionName()

### API Calls
```javascript
await api.method('/api/endpoint', payload)

Backend Layer

Endpoint

  • src/routes/handler:line - endpoint_handler()

Business Logic

  1. Validate input
  2. Check authorization
  3. Perform operation
  4. Return response

Database Operations

  • Query: Description
  • Update: Description

Side Effects

  • Events: {type: "event_type", data: {...}}
  • Logs: event_type="category", action="action_name"

Error Handling

Error Case HTTP Status Message
Not found 404 Resource not found
Permission denied 403 Access forbidden
Server error 500 Operation failed

Testing

Prerequisites

  • Services running

Test Steps

  1. Action: Do X Expected: Y happens Verify: Check Z
  • Upstream: Flow that triggers this one
  • Downstream: Flow triggered by this one

Read the full file on GitHub · 147 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. today First seen · 147 lines · 32 tokens per session scan A d7dbcb702082

Subscribe to this mod's changes

feature-flow-analyzer is an agent published in the GitHub repository Abilityai/abilities (11 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,030 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 2026-09-07.