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.
curl -O https://raw.githubusercontent.com/dcelisgarza/PortfolioOptimisers.jl/main/CLAUDE.mdgit 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/claude-md)<a href="https://agentmods.dev/instructions/dcelisgarza/portfoliooptimisers.jl/claude-md"><img src="https://agentmods.dev/badge/instructions/dcelisgarza/portfoliooptimisers.jl/claude-md.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 | $0.01713 | $0.01713 |
| Opus 5 | $0.00856 | $0.00856 |
| Sonnet 5 | $0.00343 | $0.00343 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
PortfolioOptimisers.jl CLAUDE.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 3d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PortfolioOptimisers.jl — working agreements
A Julia portfolio-optimisation library. Estimators are configuration, Results are data, and the
domain vocabulary is normative — read CONTEXT.md before touching anything you cannot already name.
Orientation
STANDARDS.mdis the map. It routes a subject — a docstring, anexport, a constructor, a test — to the file that owns the rule and to the check that fails when the rule breaks. Start there when you do not know which file governs what you are about to change. It carries no rules of its own, so it never overrides the file it points at./improve-standardsaudits it.CONTEXT.mdis the glossary. It defines the domain language (Prior, Constraint Space, Universe Sets, Feature Matrix, Objective Penalty, …) and is hand-written. When you introduce or rename a concept, update it in the same change.docs/adr/records decisions. An ADR whose decision reachedmainis amended, never rewritten: append a## Amendment (YYYY-MM-DD)section. Such an ADR describes released behaviour, so an ADR describing superseded behaviour is correct history, not a bug. An ADR whose decision has not reachedmainis still a draft — rewrite it in place, because no reader outside the branch ever saw the text you would be amending.- To find code, prefer kaimon's
search_code(semantic) when you can only describe what you want, andgrep_codewhen you already hold an exact token./graphifybuilds a queryable graph for larger architectural questions.
Running Julia
- Go through the kaimon MCP tools, not
juliaon Bash.ex(e="…")evaluates in a REPL the user shares live. - Single-threaded:
julia -t 1,BLAS.set_num_threads(1). Never kick off the full test suite or a docs build — those are the maintainer's to run. - Run targeted
test_*.jlfiles for the area you changed.test/runtests.jlsupplies a sharedinit_codepreamble (Test,Logging,CSV,TimeSeries,DataFrames,StableRNGs,StatsBase,LinearAlgebra,find_tol); reproduce it if you include a test file directly. - On a Revise world-age warning, restart the session and cold-load. If a session wedges, shut it down and start a new one rather than fighting it.
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.
- 3d ago First seen · 108 lines · 1,713 tokens per session scan A 3ed143934310
PortfolioOptimisers.jl CLAUDE.md is an instructions file published in the GitHub repository dcelisgarza/PortfolioOptimisers.jl (21 stars, last pushed today), licensed MIT. It adds 1,713 tokens to every session, about $0.0086 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.