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/ocaml-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/ocaml-expert)<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/ocaml-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/ocaml-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 5.1 | $0.00021 | $0.00427 |
| Opus 5 | $0.00010 | $0.00214 |
| Sonnet 5 | $0.00004 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
ocaml-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.
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 OCaml's type system
- Functional programming paradigms
- Pattern matching and recursive data types
- Module system and functors
- Polymorphic variants and GADTs
- Efficiency in managing side-effects
- Type inference and type safety
- Error handling and exception safety
- Memory management with OCaml's garbage collector
- OCaml's toolchain and build systems
Approach
- Write idiomatic OCaml code using function composition
- Leverage pattern matching for clarity and safety
- Use immutability and pure functions to minimize side effects
- Implement algorithms with recursive functions and tail recursion
- Optimize performance through detailed profiling
- Harness the module system for scalable design
- Utilize type inference for concise and type-safe code
- Employ unit tests to ensure correctness and prevent regressions
- Debug using OCaml's interactive toplevel
- Follow OCaml's conventions and best practices
Quality Checklist
- Ensures code follows OCaml's formatting conventions
- All functions are tested, documented, and optimized
- Utilize type definitions to enhance code readability
- Pattern matching covers all possible cases
- Handle all exceptions consistently
- Perform static analysis to catch potential errors
- Ensure tail-call optimization in recursive functions
- Validate memory usage and performance constraints
- Use descriptive function and variable names for clarity
- Maintain concise and expressive code structure
Output
- Well-structured OCaml code with modular design
- Thoroughly documented functions and types
- Comprehensive test suites with edge case coverage
- Efficient implementations using OCaml's standard library
- Performance-optimized code with profiling analysis
- Robust error handling throughout the program
- Type-safe abstractions with minimal runtime errors
- Concise code examples demonstrating complex concepts
- Detailed code reviews focusing on functional correctness
- Cleaned up and refactored codebase following best practices
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 · 21 tokens per session scan A 35ce52fb095c
ocaml-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (996 stars, last pushed 10mo ago), licensed MIT. It adds 21 tokens to every session and 427 once invoked, about $0.0001 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.
Other agents, from other repositories
test-engineer
Testing expert for .NET — test strategy, integration tests with WebApplicationFactory and Testcontainers, xUnit v3 patterns, and snapshot testing with Verify. Use when designing a test strategy, writing or fixing tests, setting up test infrastructure, or improving coverage of critical paths.
unittest-generator
Use this agent when you need to create unit tests for your code in unittest.TestCase format, organized in a tests folder with concept-based subfolders. Examples: Context: User has just written a new authentication module and needs comprehensive unit tests. user: 'I just finished writing my user authentication…
test-writer
Use when writing, fixing, or expanding tests. Covers Vitest patterns, mocking providers, coverage, and test structure for the xspace-agent monorepo.
vitest-component-tester
Use this agent when you need to test components and logic using Vitest following the project's testing strategy. Examples: Context: User has just implemented a new React component and wants to ensure it's properly tested. user: 'I just created a UserProfile component that displays user information and handles edit…
labview-lunit-unit-test
Writes and runs LUnit (Astemes) unit tests for LabVIEW code — creates the test case class off LUnit's own Test Case.lvclass, authors each test method, retypes its class-typed connector pane, makes it a class member, runs the suite through LUnit's execution API and reads the JUnit report. Use ONLY when the user…
scala-dev-architect
Use this agent when you need deep Scala expertise for implementation, functionality development, and unit testing. This agent should be deployed when: (1) writing new Scala features or refactoring existing code in the Knowledge Platform, (2) designing actor-based implementations using Apache Pekko, (3) creating…