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 skills add Krastanov/JuliaLLMAgentSkills --skill develop-julia-packagesgit clone --depth 1 https://github.com/Krastanov/JuliaLLMAgentSkillsWrote 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/skills/krastanov/juliallmagentskills/develop-julia-packages)<a href="https://agentmods.dev/skills/krastanov/juliallmagentskills/develop-julia-packages"><img src="https://agentmods.dev/badge/skills/krastanov/juliallmagentskills/develop-julia-packages/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/krastanov/juliallmagentskills/develop-julia-packages"><img src="https://agentmods.dev/badge/skills/krastanov/juliallmagentskills/develop-julia-packages.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00110 | $0.00955 |
| Opus 5 | $0.00055 | $0.00477 |
| Sonnet 5 | $0.00022 | $0.00191 |
| Haiku 4.5 | $0.00011 | $0.00096 |
Grade A, and why
develop-julia-packages 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 10d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop Julia Packages
Make the smallest coherent package change, preserve the repository's supported Julia versions and established conventions, and validate through the package environment.
Start With Repository Evidence
- Read
Project.toml, the package entry module, tests, docs setup, CI, and contribution instructions. - Check
[compat]before choosing Julia, Pkg, stdlib, or package APIs. - Inspect the current test runner and environment layout before changing either.
- Check
git statusand preserve unrelated work. - Reproduce a failure with the same project and entry point used by CI.
Do not infer policy from a generated Manifest.toml alone. Treat a committed manifest, test project, docs project, and CI matrix as deliberate until repository evidence says otherwise.
Implement Conservatively
- Keep library code in the package module under
src/. Keep optional integrations inext/. - Declare dependencies and compat bounds; never install packages from package source or test code.
- Preserve the manifest policy. Do not delete or hand-edit a manifest to solve an ordinary resolution problem.
- Keep Pkg's conservative registry flavor unless a diagnosed publication-latency problem justifies
eager. - Gate workspaces and app entry points on the package's minimum Julia version.
- Prefer clear public seams and small fakes over method patching or a mocking framework.
- Keep runtime-generated or mutable data out of the package source tree.
Read environments and package layout before changing dependencies, projects, manifests, workspaces, apps, or directory structure.
Test Through the Package
Use Test assertions and make ParallelTestRunner.jl the default runner for a new file-split package suite. Preserve an established runner unless migration is requested or necessary. Preserve TestItemRunner.jl only when the repository already uses @testitem; do not introduce it into a conventional file suite just to standardize runners. A tiny or intentionally ordered suite may remain sequential.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 233 B
- references/ci-and-contributions.md 4.9 KB
- references/debugging.md 3.5 KB
- references/documentation.md 3.4 KB
- references/environments-and-layout.md 4.3 KB
- references/extensions.md 3.0 KB
- references/quality.md 3.9 KB
- references/scratch-runtime-data.md 3.0 KB
- references/testing.md 4.5 KB
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.
- 10d ago First seen · 64 lines · 110 tokens per session scan A 7d055d5b21ce
develop-julia-packages is a skill published in the GitHub repository Krastanov/JuliaLLMAgentSkills (30 stars, last pushed 1mo ago), licensed Unlicense. It adds 110 tokens to every session and 955 once invoked, about $0.0006 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 skills, from other repositories
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…
platform-detection
Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system. Use only for "which test platform/framework?", "VSTest or MTP?", or "what runner does this project use?", including bridge settings, UseVSTest opt-outs, and incompatible or conflicting VSTest/MTP configuration.…
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
omh-rust
This is a Hermes-native rust workflow skill.
axiom-concurrency
Use when writing ANY async code, actors, threads, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.