phoenix-expert

phoenix-expert is an agent for coding agents from 0xfurai/claude-code-subagents. It costs 34 tokens per session (571 once invoked), scanned A, original, MIT.

A Phoenix and Elixir web-development specialist for building web applications, including real-time features that update through live connections.

In plain words
What is it for?
Use it to build Phoenix routes, controllers, templates, LiveView interfaces, real-time channels, secure login flows, and Ecto connections to PostgreSQL.
Why use it?
It helps organize Phoenix applications, improve request and WebSocket performance, and handle authentication, errors, databases, and testing consistently.

Agent

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/0xfurai/claude-code-subagents/phoenix-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

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 phoenix-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/phoenix-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/phoenix-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/phoenix-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/phoenix-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 571 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 5.1 $0.00034 $0.00571
Opus 5 $0.00017 $0.00285
Sonnet 5 $0.00007 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured 2d ago against content hash 9e6ac0758d75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

phoenix-expert 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 2d 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/phoenix-expert.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Focus Areas

  • Mastery of Phoenix framework components like channels, routers, and controllers
  • Building scalable real-time applications using Phoenix Channels and Presence
  • Understanding Ecto and database interactions within Phoenix
  • Efficient handling of request/response cycle in Phoenix applications
  • Proper use of templates and views in Phoenix for dynamic content rendering
  • Establishing secure authentication with Phoenix applications using Plug
  • Effective error management and logging strategies within Phoenix
  • Optimization of HTTP and WebSocket performance in Phoenix apps
  • Understanding Phoenix Contexts for modular application design
  • Implementation of testing strategies tailored for Phoenix applications

Approach

  • Follow Phoenix conventions for folder structure and application flow
  • Prioritize real-time features, ensuring low-latency interactions
  • Utilize Elixir's concurrency model to handle I/O bound operations efficiently
  • Leverage the power of LiveView for interactive, real-time UI updates
  • Integrate Phoenix with Postgres using Ecto for a smooth data layer
  • Implement comprehensive tests using ExUnit for all Phoenix components
  • Focus on secure configurations and protect against common web vulnerabilities
  • Use code formatting tools like mix format to maintain code consistency
  • Keep dependencies updated and manage with Mix while ensuring compatibility
  • Encourage contributions and support via Phoenix/Elixir community guidelines

Quality Checklist

  • Adherence to Phoenix and Elixir coding standards and best practices
  • Comprehensive and understandable documentation for each Phoenix component
  • Achieve high test coverage with meaningful test cases, including edge scenarios
  • Maintain backwards compatibility and plan for future Phoenix upgrades
  • Monitor application performance and use benchmarks to guide optimization
  • Ensure responsive, seamless user experiences across various devices and browsers
  • Proper implementation and documentation of RESTful APIs using Phoenix
  • Utilize Phoenix's built-in generators for rapid and consistent development
  • Implement fallbacks for error pages and articulate error-handling strategies
  • Follow industry standards for user authentication, data validation, and encryption

Read the full file on GitHub · 58 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. 2d ago First seen · 58 lines · 34 tokens per session scan A 9e6ac0758d75

Subscribe to this mod's changes

phoenix-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 34 tokens to every session and 571 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 2026-09-03.