Claude Code team should try macro so users can complete 3x as many tasks

A developer proposes that the Claude Code team implement a macro feature to batch multiple file changes and test commands into a single turn, claiming it could reduce LLM turns by 40-80% and save tokens. The idea was tested on other coding agents and is shared on Hacker News with a link to a GitHub repository containing the implementation and benchmarks.

So the idea is really simple. If CC need to change a file and run some test, CC needs to: Turn 1 — apply patch change package file Turn 2 — apply patch fix the bug Turn 3 — apply patch edit the testing script Turn 4 — build Turn 5 — run tests and lint Turn 6 — and if is playwright CC needs another round to read media The concept is that we can use macro command to put the entire process into a RAG in one single turn. For example like this: step1: inspect env step2: apply patch change package file step2: apply patch fix the bug step2: apply patch edit the testing script step3: build step4: run tests and lint step5: read medias I could not test this implementation due to Antropic terms of use. But I tested on other coding agent and providers this can reduce llm turns around by 40% - 80%, and saving nearly same amount of tokens. （I need to use to hide the provider's name in order to avoid the post being deleated by the bot . If you think this approch could help and my testing method is reasonable, you can give me an upvote Thx Here is the implementation and testing benchmark can be found in the md. I tested with DeepSWE and entire repo rewrite cases: https://github.com/Tura-AI/tura Comments URL: https://news.ycombinator.com/item?id=48957109 https://news.ycombinator.com/item?id=48957109 Points: 1 Comments: 0