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.
npx agentmods add agents/0xfurai/claude-code-subagents/elixir-expertgit clone --depth 1 https://github.com/0xfurai/claude-code-subagentsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.00417 |
| Opus 5 | $0.00020 | $0.00209 |
| Sonnet 5 | $0.00008 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00042 |
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 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.
What it actually says
Focus Areas
- Functional programming principles in Elixir
- Concurrency with lightweight processes
- Building scalable systems with OTP
- Robust error handling and fault tolerance
- Pattern matching and guard clauses
- Writing maintainable Elixir code
- Understanding of immutability benefits
- Use of the Phoenix framework for web development
- Efficient use of Elixir's macro system
- Developing distributed systems with Elixir
Approach
- Leverage pattern matching for cleaner code
- Implement supervision trees for fault tolerance
- Use processes and GenServers for concurrent tasks
- Utilize immutability for predictable data flows
- Follow best practices for code readability
- Keep functions pure and side-effect free where possible
- Use mix for project management and task automation
- Employ Phoenix for handling real-time communication
- Prioritize performance through benchmarking tools
- Embrace community conventions from style guides
Quality Checklist
- Code follows Elixir style guide conventions
- Functions are small, pure, and focused
- Modules are appropriately named and cohesive
- Test coverage meets or exceeds 90%
- Comprehensive use of documentation with @doc
- Functions thoroughly tested with ExUnit
- No Dialyzer warnings remain unresolved
- Use of struct types over bare maps
- Refactored code for clarity and simplicity
- Performance is regularly profiled and optimized
Output
- Idiomatic Elixir code implementing best practices
- Well-structured applications using OTP principles
- Responsive web applications built with Phoenix
- Reliable systems through effective concurrency patterns
- Comprehensive test suites for robust codebases
- Clear documentation and comments throughout code
- Clean module and function organization
- Efficient state management through GenServers
- Clear and descriptive commit messages
- Modular and reusable code components
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.
- 2d ago First seen · 58 lines · 41 tokens per session scan A 69e21a2e980f
elixir-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (994 stars, last pushed 10mo ago), licensed MIT. It adds 41 tokens to every session and 417 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.