claude 'resolve the merge conflict'
@bcherny
-
Scroll in /usage for a detailed summary of consumed tokens
By
–
Scroll down a bit in the /usage view to see a detailed summary of which specific skills/MCPs/plugins are consuming your tokens, in order to optimize token usage.
-
Tip: Find plugins that consume your tokens in Claude Code
By
–
If you run Claude Code in the terminal, scroll down a bit after running /usage and you should see a complete detail of specific skills, MCP, and plugins that consume your tokens. Most of the time, it's a bad plugin that causes the
-
False positive of the cybernetic classifier, improvement in progress
By
–
Following our exchanges in DM, the problem was a false positive of the cybernetic classifier. The classifier generates many false positives, and we are actively working on improving it. More details here: https://
anthropic.com/news/claude-fa
ble-5-mythos-5
… Apart from that — for the exams of -
Fable 5: Leap Forward, 100% Coding in Terminal
By
–
Fable 5 represents the greatest leap forward I have felt in our models since Opus 4.5 last November. After the release of 4.5, I uninstalled my IDE when I realized that I had done 100% of my coding in a terminal for a few weeks. With Fable,
-
The importance of self-verification loops in the era of powerful models
By
–
We talk a lot about how important it is to set up self-verification loops. Especially in the age of powerful models that can run for long periods of time, self-verification is a key ingredient that enables the model to run for much longer, delivering a result that is closer to… https://t.co/NHiral0F9j
— Boris Cherny (@bcherny) 9 juin 2026We talk a lot about the importance of setting up self-verification loops. Especially in the era of powerful models that can operate for long periods, self-verification is a key ingredient that allows the model to function much more
-
Fable 5 available in Claude Code and Cowork, best coding model
By
–
Fable 5 is now available in Claude Code and Cowork
— Boris Cherny (@bcherny) 9 juin 2026
Fable is the best model I have used for coding, by a wide margin. It is a big step up, enabling less prompts and steers, more efficient token use, better code quality, better tool use, more intelligent self-verification, longer… https://t.co/RmVfZh39HtFable 5 is now available in Claude Code and Cowork. Fable is the best model I have used for coding, by far. It is a big step forward, allowing fewer instructions and guidance, more efficient token usage, better quality of
-
Experimentation with fork:true and agents to isolate context
By
–
An idea I'm experimenting with: adding 'fork:true' to the frontmatter of a skill so that it runs in its own context window, then within the skill telling it to use agents to keep the context isolated for each step as well. Add
-
Support for nested sub-agents in Claude Code, depth=5
By
–
Just landed: support for nested sub-agents in Claude Code. I'm starting to experiment more with agents that launch other agents as a way to better manage context. Limited to depth=5 for now, released in today's release.