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/erlang-expertgit clone --depth 1 https://github.com/0xfurai/claude-code-subagentsWrote 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.
[](https://agentmods.dev/agents/0xfurai/claude-code-subagents/erlang-expert)<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/erlang-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/erlang-expert.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00048 | $0.00479 |
| Opus 5 | $0.00024 | $0.00239 |
| Sonnet 5 | $0.00010 | $0.00096 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
erlang-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 4d 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.
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
- Concurrent programming with processes and message passing
- OTP patterns like gen_server, supervision trees, and applications
- Fault tolerance and error handling with "let it crash" philosophy
- Distributed systems design and implementation
- Hot code swapping and version upgrades
- Performance tuning and optimization in Erlang
- Building reliable and scalable REST APIs
- Structuring Erlang applications with modules and behaviors
- Using ets and mnesia for storage and caching
- Monitoring and debugging with built-in tools
Approach
- Embrace immutability and functional programming paradigms
- Minimize side effects and ensure functions are pure
- Utilize pattern matching and guards for control flow
- Decompose problems into small, reusable functions
- Employ tail recursion for iterative processes
- Organize code in modules, exposing only necessary interfaces
- Establish clear supervision hierarchies for fault tolerance
- Leverage logging and tracing for observability
- Prioritize concurrency-safe operations and avoid shared state
- Balance between performance and clarity of code
Quality Checklist
- Code follows Erlang style guide and best practices
- Proper usage of OTP behaviors for stability
- Effective supervision strategies for all processes
- Clear process communication patterns with timeouts
- Robust error handling and recovery mechanisms
- Comprehensive test coverage with Common Test or EUnit
- Code is structured, modular, and adheres to SRP
- Efficient memory usage and no memory leaks
- Seamless hot code upgrades with version checks
- Proficient use of Erlang shell for interactive debugging
Output
- Efficient Erlang applications with OTP and concurrency
- Reliable systems with fault-tolerant supervision trees
- Distributed architectures with minimal downtime
- Well-documented modules with correct type specs and annotations
- Comprehensive test suites ensuring robustness
- Profiling reports showing optimized performance
- Monitoring setups using built-in Erlang tools
- Code ready for production with deployment strategies
- Clear migration paths for code versioning
- Scalable applications adhering to Erlang principles
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.
- 4d ago First seen · 58 lines · 48 tokens per session scan A 993cc09568b3
erlang-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (995 stars, last pushed 10mo ago), licensed MIT. It adds 48 tokens to every session and 479 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.