Content
@
https://warpcast.com/~/channel/aichannel
0 reply
0 recast
0 reaction
Matt Galligan
@mg
Watching my AI agents go crazy just to locate a single line of code felt like hunting for a **needle in a stack of needles**. 🔍 🔍 🔍🤬 So I whipped up a little experiment called grep-anchors or "grepa". Just drop ":ga:<text>" anchors in comments and your tools (or agents) *teleport* to the right spot. Like the TODO's and FIXME's before, but with some conventions for predictability (and composability). 🚢 Early days, but I’m already seeing way fewer fruitless tool calls!
8 replies
9 recasts
60 reactions
Matt Galligan
@mg
🍇 Grepa = “grep-anchors.” - ultra-terse tags (":ga:tldr start here", ":ga:perf,todo") - one anchor pattern per repo - dead-simple to insert, grep on, and agents are fast to understand how to search/write them Conventions & docs » https://github.com/galligan/grepa
1 reply
0 recast
5 reactions
ASM
@asm.eth
Is the theory here that it just scans for the anchors and once it finds the correct anchor text it parses that portion of the code? Pretty cool idea
1 reply
0 recast
0 reaction
Backseats
@backseats
Fire
0 reply
0 recast
1 reaction
0xdesigner
@0xdesigner
i’m turning on notis for your posts
0 reply
0 recast
1 reaction
shoni.eth
@alexpaden
Why do it on a todo?
0 reply
0 recast
0 reaction
Geo Ppls
@geoppls
Smart
0 reply
0 recast
0 reaction
Kyle
@kalelabs
Love this. Have been using something like this in terms of nested dependencies. A component calls a service which calls an endpoint and having that relationship commented in the code
0 reply
0 recast
0 reaction
JamesLamphere
@jameslamphere
AI agents hunting code feels like endless needle searching frustration
0 reply
0 recast
0 reaction
