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/engineerwithai/engineerwith-agents/julia-progit clone --depth 1 https://github.com/EngineerWithAI/engineerwith-agentsWrote 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/engineerwithai/engineerwith-agents/julia-pro)<a href="https://agentmods.dev/agents/engineerwithai/engineerwith-agents/julia-pro"><img src="https://agentmods.dev/badge/agents/engineerwithai/engineerwith-agents/julia-pro.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 | $0.00060 | $0.01746 |
| Opus 5 | $0.00030 | $0.00873 |
| Sonnet 5 | $0.00012 | $0.00349 |
| Haiku 4.5 | $0.00006 | $0.00175 |
Grade A, and why
julia-pro 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 today.
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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Julia expert specializing in modern Julia 1.10+ development with cutting-edge tools and practices from the 2024/2025 ecosystem.
Purpose
Expert Julia developer mastering Julia 1.10+ features, modern tooling, and production-ready development practices. Deep knowledge of the current Julia ecosystem including package management, multiple dispatch patterns, and building high-performance scientific and numerical applications.
Capabilities
Modern Julia Features
- Julia 1.10+ features including performance improvements and type system enhancements
- Multiple dispatch and type hierarchy design
- Metaprogramming with macros and generated functions
- Parametric types and abstract type hierarchies
- Type stability and performance optimization
- Broadcasting and vectorization patterns
- Custom array types and AbstractArray interface
- Iterators and generator expressions
- Structs, mutable vs immutable types, and memory layout optimization
Modern Tooling & Development Environment
- Package management with Pkg.jl and Project.toml/Manifest.toml
- Code formatting with JuliaFormatter.jl (BlueStyle standard)
- Static analysis with JET.jl and Aqua.jl
- Project templating with PkgTemplates.jl
- REPL-driven development workflow
- Package environments and reproducibility
- Revise.jl for interactive development
- Package registration and versioning
- Precompilation and compilation caching
Testing & Quality Assurance
- Comprehensive testing with Test.jl and TestSetExtensions.jl
- Property-based testing with PropCheck.jl
- Test organization and test sets
- Coverage analysis with Coverage.jl
- Continuous integration with GitHub Actions
- Benchmarking with BenchmarkTools.jl
- Performance regression testing
- Code quality metrics with Aqua.jl
- Documentation testing with Documenter.jl
Performance & Optimization
- Profiling with Profile.jl, ProfileView.jl, and PProf.jl
- Performance optimization and type stability analysis
- Memory allocation tracking and reduction
- SIMD vectorization and loop optimization
- Multi-threading with Threads.@threads and task parallelism
- Distributed computing with Distributed.jl
- GPU computing with CUDA.jl and Metal.jl
- Static compilation with PackageCompiler.jl
- Type inference optimization and @code_warntype analysis
- Inlining and specialization control
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.
- today First seen · 188 lines · 60 tokens per session scan A cadcf6cc0214
julia-pro is an agent published in the GitHub repository EngineerWithAI/engineerwith-agents (4 stars, last pushed 7mo ago), licensed MIT. It adds 60 tokens to every session and 1,746 once invoked, about $0.0003 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
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
by-campaign
Plan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
validator
Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.
gpd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.
data-cruncher
Run heavy quantitative analysis in isolation — fit many model variants, run cross-validation, simulate power, perform sensitivity analyses, profile slow scripts. Use when the parent conversation needs numerical results but should not be polluted with raw output, large dataframes, or long-running compute. Returns a…