grep

“it is not very token-efficient as it can return lots of matches, filling up the agent's context”

“Grep can cut through almost any code base. The problem is that grep is lexical. It is dumb.”

“grep is better than almost anything else you can use. It's very very fast and efficient”

“I'm leaning heavily into grep and search tools to navigate code”

“Agents love standing on the shoulders of good crystalized cognition (grep, curl etc)”

“the Linux `find` and `grep` commands usually can find stuff much quicker than any 'accelerated' and 'cached' desktop search”

“giving an agent grep covers most of the use cases”

“ossification of grep's core features (a good thing)”

“grep is pretty poorly suited to semantic search and will only return the most basic of matches”

“grep and find in the terminal are much faster”

“Access to a well-established set of tools for operating on unstructured text”

“"diff old.txt new.txt | grep '^+'" will only show me added lines”

“grep is fine if you don't care about tokens and you have less than 100k files”

“It serves me better than an IDE when there’re lots of scattered and frequent queries.”

“They still work exactly the same, and now even my agents can do it.”

“I never saw anyone crack the embedding-generation-and-comparison problems well enough to actually get better results than grep”

“Claude reading hundreds of kilobytes of outputs because grep found things in node_modules”

“It's very effective in well-written and well-designed code bases where concepts tend to be relatively well formed”

“Grep is effective for the most part, except for situations like when you have huge codebases”

“It is surprisingly sparing on tokens, which makes sense since those things were designed to work with a teletype.”

“you can probably grep into a file, eliminate false positive cases”

“There's no need to "understand" "names like grep"; you learn it as a language like any other.”

“I use grep multiple times per day, works great, I've seen no need to change.”

“Claude Code would be far less useful without grep, diff, git, head”

“grep with LC_ALL=C - is much, much faster than any aggregation tool”

“Well grep is just better sometimes. Like you want to copy some lines and grep at the end of a pipeline is just easier”

“I use "grep" to search files (it should never skip any unless I tell it to do otherwise)”

“assuming your encoding is Unicode (normally UTF-8), which grep would interpret”

“`grep -P` kinda annoying. GNU has Perl-compatible regex, and BSD does not.”

“The ones that survive decades (Make, grep, curl) do one thing and compose well”

“Three tools born in Bell Labs that still power every server, every pipeline”

“widely used both as tools and as "semantic primitives"”

“Annoyingly `--color=auto` can change the representation of the characters so when you run again there's a mismatch.”

“running grep through millions of files if you use maildir or a similar format takes forever”

“find and grep do similar things but work entirely differently and their args aren't even in the same format”

“Grep is 50 years old and still does exactly what we need.”

“grep is all right, but sometimes I need to tease out a complex data relationship.”

“Despite the insane volume we made this work really well using just grep and other basic CLI tools.”

“plain shell scripts, sed, awk, grep and xargs”

“agents are insanely good at grep. So much so that I've been trying to figure out how to create an llmgrep tool”