PortfolioOptimisers.jl: Skill for Claude Code

.claude/skills/run-doctests/SKILL.md

run-doctests is a skill for Claude Code from dcelisgarza/PortfolioOptimisers.jl. It costs 44 tokens per session (307 once invoked), scanned A, original, MIT.

A project guide for running and updating PortfolioOptimisers.jl documentation tests, called doctests. It gives the exact Julia command used by continuous integration and explains how to regenerate expected output.

In plain words
What is it for?
Use it before running doctests or updating their expected output in a Julia project.
Why use it?
It prevents false failures caused by running tests in a changed interactive session or editing printed results by hand.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is dcelisgarza/PortfolioOptimisers.jl's own configuration. It tells Claude Code how to work on PortfolioOptimisers.jl itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything PortfolioOptimisers.jl configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dcelisgarza/PortfolioOptimisers.jl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dcelisgarza/PortfolioOptimisers.jl/main/.claude/skills/run-doctests/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dcelisgarza/PortfolioOptimisers.jl

Made for: Claude Code.

Wrote 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.

agentmods badge for run-doctests

README.md
[![agentmods](https://agentmods.dev/badge/skills/dcelisgarza/portfoliooptimisers.jl/run-doctests/github.svg)](https://agentmods.dev/skills/dcelisgarza/portfoliooptimisers.jl/run-doctests)
Your own site
<a href="https://agentmods.dev/skills/dcelisgarza/portfoliooptimisers.jl/run-doctests"><img src="https://agentmods.dev/badge/skills/dcelisgarza/portfoliooptimisers.jl/run-doctests/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.

agentmods 80×15 button for run-doctests

Your own site · 80×15
<a href="https://agentmods.dev/skills/dcelisgarza/portfoliooptimisers.jl/run-doctests"><img src="https://agentmods.dev/badge/skills/dcelisgarza/portfoliooptimisers.jl/run-doctests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 307 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.00307
Opus 5 $0.00022 $0.00153
Sonnet 5 $0.00009 $0.00061
Haiku 4.5 $0.00004 $0.00031

Measured 5d ago against content hash e000bbabb114, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

run-doctests 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 5d 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.

.claude/skills/run-doctests/SKILL.md · 27 lines

What it actually says

Running doctests

  • Run them in a fresh process, never in a working REPL. show omits a module prefix for types reachable unqualified from the active module, so a session that has done using StatsBase makes StatsBase.SimpleCovariance print bare and produces dozens of phantom failures.
  • The CI invocation is in .github/workflows/Docs.yml — mirror it exactly:
julia --project=docs -e '
  using Documenter: DocMeta, doctest
  using PortfolioOptimisers
  PortfolioOptimisers.set_compact_show!(false)
  DocMeta.setdocmeta!(PortfolioOptimisers, :DocTestSetup, :(using PortfolioOptimisers, StatsBase,
    Statistics, LinearAlgebra, Dates, Distributions, StableRNGs, TimeSeries;
    PortfolioOptimisers.set_compact_show!(false)); recursive=true)
  doctest(PortfolioOptimisers)'
  • The pretty-printer right-aligns field names to the widest field in each block, so renaming a field re-indents every printed block that contains it, including nested ones. Regenerate the expected output from a real run rather than hand-editing it.
Changes

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.

  1. 5d ago First seen · 27 lines · 44 tokens per session scan A e000bbabb114

Subscribe to this mod's changes

run-doctests is a skill published in the GitHub repository dcelisgarza/PortfolioOptimisers.jl (21 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 307 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 2026-09-04.