Anthropic to make Claude Code more hackable with Agents.MD and system prompt edits
trq212 · x · 2026-08-26
An Anthropic engineer shared that they are working to make Claude Code more hackable, including easy use of Agents.MD and other system prompt modifications. The reasoning: model families are not interchangeable and system prompts can significantly impact performance — Claude Code even ships different system prompts per model. He also documented how Claude models prefer their skills, system prompt, and Claude.MD to be formatted, while acknowledging this upkeep isn't worth it for everyone.
More from coding & agent
- Marc Lou praises PostShiba, a cute indie alternative to AWS SES for email infra — marclou · 2026-10-16
- RExBench: best coding agent completes only 33% of autonomous research extensions — najoungkim · 2026-10-16
- Wiring Pstack skills from a Grok bot into Hermes agent loops — alexcovo_eth · 2026-10-16
- past.dev launches long-term memory API for AI agents, tops BEAM public benchmark — thisiskp_ · 2026-10-16
- Google's CLASHarness benchmarks multi-agent conflicts in computer use, finds frontier VLMs struggle — google · 2026-10-16
- mitsuhiko's AI agent solved multiplayer with PeerJS before he could explain it — mitsuhiko · 2026-10-16