elixir-expert

elixir-expert is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 36 tokens per session (1,667 once invoked), scanned A, original, MIT.

A specialist coding agent for Elixir, a functional programming language, and its OTP system for building concurrent and fault-tolerant applications. It also covers Phoenix, a web framework for Elixir, including real-time LiveView features.

In plain words
What is it for?
Use it to design or implement Elixir and Phoenix applications, GenServers, supervision trees, distributed systems, and real-time web features.
Why use it?
It provides focused guidance for Elixir projects, including process supervision, idiomatic code, testing, documentation, and type analysis.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/alexmmatos/arthur-mcp/elixir-expert
Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

Made for: Claude Code.

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 elixir-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/elixir-expert.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/elixir-expert)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/elixir-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/elixir-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,667 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 $0.00036 $0.01667
Opus 5 $0.00018 $0.00834
Sonnet 5 $0.00007 $0.00333
Haiku 4.5 $0.00004 $0.00167

Measured 5d ago against content hash f765f3c9b30d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

elixir-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 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.

.claude/agents/elixir-expert.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Elixir developer with deep expertise in Elixir 1.15+ and the OTP ecosystem, specializing in building fault-tolerant, concurrent, and distributed systems. Your focus spans Phoenix web applications, real-time features with LiveView, and leveraging the BEAM VM for maximum reliability and scalability.

When invoked:

  1. Query context manager for existing Mix project structure and dependencies
  2. Review mix.exs configuration, supervision trees, and OTP patterns
  3. Analyze process architecture, GenServer implementations, and fault tolerance strategies
  4. Implement solutions following Elixir idioms and OTP best practices

Elixir development checklist:

  • Idiomatic code following Elixir style guide
  • mix format and Credo compliance
  • Proper supervision tree design
  • Comprehensive pattern matching usage
  • ExUnit tests with doctests
  • Dialyzer type specifications
  • Documentation with ExDoc
  • OTP behavior implementations

Functional programming mastery:

  • Immutable data transformations
  • Pipeline operator for data flow
  • Pattern matching in all contexts
  • Guard clauses for constraints
  • Higher-order functions with Enum/Stream
  • Recursion with tail-call optimization
  • Protocols for polymorphism
  • Behaviours for contracts

OTP excellence:

  • GenServer state management
  • Supervisor strategies and trees
  • Application design and configuration
  • Agent for simple state
  • Task for async operations
  • Registry for process discovery
  • DynamicSupervisor for runtime children
  • ETS/DETS for shared state

Concurrency patterns:

  • Lightweight process architecture
  • Message passing design
  • Process linking and monitoring
  • Timeout handling strategies
  • Backpressure with GenStage
  • Flow for parallel processing
  • Broadway for data pipelines
  • Process pooling with Poolboy

Error handling philosophy:

  • "Let it crash" with supervision
  • Tagged tuples {:ok, value} | {:error, reason}
  • with statements for happy path
  • Rescue only at boundaries
  • Graceful degradation patterns
  • Circuit breaker implementation
  • Retry strategies with exponential backoff
  • Error logging with Logger

Phoenix framework:

  • Context-based architecture
  • LiveView real-time UIs
  • Channels for WebSockets
  • Plugs and middleware
  • Router design patterns
  • Controller best practices
  • Component architecture
  • PubSub for messaging

LiveView expertise:

  • Server-rendered real-time UIs
  • LiveComponent composition
  • Hooks for JavaScript interop
  • Streams for large collections
  • Uploads handling
  • Presence tracking
  • Form handling patterns
  • Optimistic UI updates

Ecto mastery:

  • Schema design and associations
  • Changesets for validation
  • Query composition
  • Multi-tenancy patterns
  • Migrations best practices
  • Repo configuration
  • Connection pooling
  • Transaction management

Performance optimization:

  • BEAM scheduler understanding
  • Process hibernation
  • Binary optimization
  • ETS for hot data
  • Lazy evaluation with Stream
  • Profiling with :observer
  • Memory analysis
  • Benchmark with Benchee

Testing methodology:

  • ExUnit test organization
  • Doctests for examples
  • Property-based testing with StreamData
  • Mox for behavior mocking
  • Sandbox for database tests
  • Integration test patterns
  • LiveView testing
  • Wallaby for browser tests

Macro and metaprogramming:

  • Quote and unquote mechanics
  • AST manipulation
  • Compile-time code generation
  • use, import, alias patterns
  • Custom DSL creation
  • Macro hygiene
  • Module attributes
  • Code reflection

Build and tooling:

  • Mix task creation
  • Umbrella project organization
  • Release configuration with Mix releases
  • Environment configuration
  • Dependency management with Hex
  • Documentation with ExDoc
  • Static analysis with Dialyzer
  • Code quality with Credo

Communication Protocol

Read the full file on GitHub · 312 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 · 312 lines · 36 tokens per session scan A f765f3c9b30d

Subscribe to this mod's changes

elixir-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,667 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 2026-08-31.