Mara Averick batpigandme

One-liner

If you're authoring shared instructions across both Claude Code and Cowork from the same repo, bridge AGENTS.md → CLAUDE.md with a symlink, not an @import — Code expands @AGENTS.md, Cowork treats it as literal text. Discovered the hard way; fix is ln -s AGENTS.md CLAUDE.md.

Context. Spent yesterday refactoring a combo repo to work cleanly across Code + Cowork — extracting procedures into skills, trimming AGENTS.md, putting an audit on quarterly cadence. Found 5 Code/Cowork asymmetries that matter for anyone using both surfaces on the same repo.

1. CLAUDE.md @import doesn't work in Cowork. The Anthropic memory docs recommend a CLAUDE.md containing @AGENTS.md to bridge naming conventions. Code expands this directive on load. Cowork treats it as literal text. Result: instructions silently disappear in Cowork while your Code session looks fine.

Fix: replace the import with a symlink.

WARP.md

This file provides guidance to WARP (warp.dev) when working with code in this repository.

Project Overview

stdlib is a standard library for JavaScript and Node.js, with an emphasis on numerical and scientific computation. It provides a comprehensive collection of robust, high performance libraries for mathematics, statistics, data processing, streams, and more. The library is fully decomposable, allowing individual packages to be consumed independently.

Architecture

	animal	date
	cow	05-05-2021
	chicken	06-05-2021
	horse	07-05-2021
	dog	08-05-2021

	# {crssuggest} by Kyle E Walker
	# Get appropriate CRS suggestions for your spatial data in R
	# src: https://github.com/walkerke/crsuggest
	# remotes::install_github("walkerke/crsuggest")

	## Use case 1: Analyzing unprojected data
	library(tigris)
	library(sf)
	options(tigris_class = "sf")

	library(tidyverse)
	set.seed(406)
	df <- tibble(x = runif(3), y = runif(3), z = runif(3))
	df %>% rowwise() %>% mutate(m = min(c(x, y, z)))
	df %>% mutate(m = pmin(x, y, z))
	df %>% mutate(m = pmap_dbl(list(x, y, z), min))

	library(tidyverse)

	family <- list(
	list(
	"name" = "Bob",
	"age" = 46,
	"mother" = NA,
	"father" = "Big Bob",
	"siblings" = list(NA),
	"children" = list("Tina", "Gene", "Louise"),

	<?xml version="1.0" encoding="UTF-8"?>
	<!DOCTYPE plist PUBLIC "-//Apple Computer//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
	<!-- Generated by: TmTheme-Editor -->
	<!-- ============================================ -->
	<!-- app: http://tmtheme-editor.herokuapp.com -->
	<!-- code: https://github.com/aziz/tmTheme-Editor -->
	<plist version="1.0">
	<dict>
	<key>name</key>
	<string>LisaFrankentheme</string>

	## Decoding lyrics — @pprevos
	## https://github.com/pprevos/r.prevos.net/blob/master/Miscellaneous/lyrics.R

	library(tidyverse)
	library(tidytext)
	library(reshape2)
	library(rvest)

	get_lyrics <- function(artist, song) {
	artist <- gsub("[^A-Za-z0-9]+", "", tolower(artist))

	snippet aa
	${1:dataset} <- ${1:dataset} %>% ${0}