What is SolvingMicroDSOPs CLAUDE.md?

Repository instructions for SolvingMicroDSOPs, a project containing LaTeX lecture notes and Python code for studying saving and consumption decisions under uncertainty. They describe how to build the PDF, run tests, check code, and reproduce results.

Use them when editing the lecture notes or Python code, building the PDF, running tests and lint checks, executing the notebook, or reproducing the project’s results.

They give a coding agent the project-specific commands and rules needed to make changes safely and verify them.

SolvingMicroDSOPs CLAUDE.md — Instructions file by llorracc

Install

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.

agentmods

npx agentmods add instructions/llorracc/solvingmicrodsops/claude-md

Clone the repo

git clone --depth 1 https://github.com/llorracc/SolvingMicroDSOPs

Per session 1,011 This file is loaded in full into every session.

When invoked 1,011 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.01011	$0.01011
Opus 5	$0.00505	$0.00505
Sonnet 5	$0.00202	$0.00202
Haiku 4.5	$0.00101	$0.00101

Measured 3d ago against content hash 41dca00346e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SolvingMicroDSOPs 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.

CLAUDE.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

SolvingMicroDSOPs is LaTeX lecture notes + Python replication code for numerical methods in consumption/saving problems under uncertainty. The main artifact is the PDF built from root-level .tex files, with a companion Jupyter notebook (SolvingMicroDSOPs.ipynb).

Build Commands

LaTeX → PDF

latexmk                    # Compiles SolvingMicroDSOPs.pdf (LuaLaTeX via .latexmkrc)

Python dependencies

uv sync --all-groups       # Install all Python dependencies

Run tests

pytest Code/Python/tests/ -m "not slow" -v   # Fast tests only
pytest Code/Python/tests/ -v                  # All tests

Lint

ruff check Code/Python/

Execute notebook

uv run jupyter nbconvert --execute --to notebook --inplace SolvingMicroDSOPs.ipynb

Structural estimation

uv run python Code/Python/StructEstimation.py

Full reproduction

./reproduce.sh             # Runs: notebook → PDF → estimation

Critical Rules

docs/ is a frozen reference copy — never edit it. All edits go to root-level .tex files.
verbatimwrite pattern: Equation files in Equations/ are generated at compile time by \begin{verbatimwrite} blocks inside _sectn-*.tex files. Edit the equation in the section file, not the generated fragment.
Code mirrors math: Python identifiers parallel LaTeX macros (e.g., DiscFac ↔ \DiscFac, vEndPrd ↔ \vEndPrd, cNrm ↔ \cNrm).
@resources/ and @local/ are literal directory names (the @ is part of the path). They contain LaTeX classes, styles, and macros required for the build. Search paths are configured in .latexmkrc.
Preserve %% CodeInfo: annotations when editing equations — they document code-math correspondence.

Architecture

LaTeX Structure

SolvingMicroDSOPs.tex — main entry point, includes all sections
SolvingMicroDSOPs-options.tex — boolean flags (shortVersion, draftmode, realcode, pseudocode, hidetime, etc.) that control what appears in the PDF
_sectn-*.tex — section subfiles (independently compilable via subfiles package)
_apndx-*.tex — appendix subfiles
Equations/ — reusable equation fragments (many auto-generated by verbatimwrite)

Read the full file on GitHub · 90 lines

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.

3d ago First seen · 90 lines · 1,011 tokens per session scan A 41dca00346e7

Subscribe to this mod's changes

SolvingMicroDSOPs CLAUDE.md is an instructions file published in the GitHub repository llorracc/SolvingMicroDSOPs (22 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,011 tokens to every session, about $0.0051 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.

Documents PDF Scientific

SolvingMicroDSOPs CLAUDE.md