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 instructions/dcelisgarza/portfoliooptimisers.jl/copilot-instructionsgit clone --depth 1 https://github.com/dcelisgarza/PortfolioOptimisers.jlWrote 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/instructions/dcelisgarza/portfoliooptimisers.jl/copilot-instructions)<a href="https://agentmods.dev/instructions/dcelisgarza/portfoliooptimisers.jl/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/dcelisgarza/portfoliooptimisers.jl/copilot-instructions.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 | $0.01697 | $0.01697 |
| Opus 5 | $0.00848 | $0.00848 |
| Sonnet 5 | $0.00339 | $0.00339 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
PortfolioOptimisers.jl copilot-instructions.md 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for PortfolioOptimisers.jl
Project Overview
PortfolioOptimisers.jl is a modular, extensible Julia package for advanced portfolio optimization, risk management, and financial analytics. The codebase is organized around composable estimators, algorithms, and result types, supporting a wide range of statistical, econometric, and optimization techniques.
Architecture & Key Patterns
- Modular Design: The main module (
src/PortfolioOptimisers.jl) includes a large set of submodules, each focused on a specific aspect (moments, risk, priors, constraints, optimisation, etc.). Each submodule is further split into fine-grained files (e.g., different covariance estimators, risk measures, etc.). - Abstract Types: All estimators, algorithms, and results are built on a hierarchy of abstract types (e.g.,
AbstractEstimator,AbstractAlgorithm,AbstractResult). New functionality should extend these types for consistency and dispatch. - Composability: Estimators and algorithms are designed to be composed. For example, a covariance estimator can be wrapped with a matrix post-processing estimator, or a mean estimator can be combined with a shrinkage algorithm.
- Validation: The codebase uses
@argcheck(from ArgCheck.jl) extensively for input validation and defensive programming. Always validate arguments in new methods. - Documentation: All public types and methods are documented with docstrings, including usage examples and references to related types.
Developer Workflows
-
Contributing and development:
- Follow the guidelines in
1-contributing.mdand2-developer.md.
- Follow the guidelines in
-
Examples:
- Example scripts and notebooks are in
examples/. Use these as references for end-to-end workflows.
- Example scripts and notebooks are in
Required Before Each Commit
-
Linting and Formatting:
- ALWAYS run
pre-commit run -abefore committing changes. - The repository uses pre-commit hooks for linting and formatting.
- Julia code is formatted using JuliaFormatter.jl.
- Commits will be rejected if pre-commit tests fail.
- Install pre-commit hooks once:
pre-commit install(requirespre-commitvia pipx).
- ALWAYS run
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 · 166 lines · 1,697 tokens per session scan A 6800b05b311a
PortfolioOptimisers.jl copilot-instructions.md is an instructions file published in the GitHub repository dcelisgarza/PortfolioOptimisers.jl (21 stars, last pushed today), licensed MIT. It adds 1,697 tokens to every session, about $0.0085 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.
Other instructions, from other repositories
NexusTrader CLAUDE.md
Instructions for Quantweb3-com/NexusTrader, covering claude.md, project overview, development commands, dependencies and setup and install with uv (package manager used in this project).
marimo AGENTS.md
AGENTS.md instructions for marimo-team/marimo, covering marimo development guidelines, your primary responsibility is to the project and its users, quick setup, development commands and python.
xalpha AGENTS.md
Instructions for refraction-ray/xalpha, covering xalpha agent platform guidelines, 1. the agentic workflow, 2. core compatibility contracts, 3. data scraping & api resilience and 4. local caching.
weightslab AGENTS.md
AGENTS.md instructions for GrayboxTech/weightslab, covering weightslab — agent context for users & debugging, 0. how to load this guide into claude code, 1. what it is and how the pieces connect, 2. install & run (the happy path) and ... your training loop ...
awesome-quant CLAUDE.md
Claude Code instructions for wilsonfreitas/awesome-quant, covering claude.md, project overview, architecture, commands and install dependencies (uses uv, requires python 3.11+).
tradememory-protocol AGENTS.md
Instructions for mnemox-ai/tradememory-protocol, covering tradememory protocol — agent context, project rules, recent changes and current status.