Claude Code: Undocumented Configuration Options from the Source
Original: Claude Code – Everything you can configure that the docs don't tell you
A source-code walkthrough of undocumented Claude Code settings, hooks, skills, agents, permissions, and memory features.
The post inspects @anthropic-ai/[email protected] and documents configuration fields not covered by the official docs. It highlights hook JSON responses, hidden skill and agent frontmatter, auto-mode rules, persistent memory, dream consolidation, Magic Docs, and permission syntax. The author frames these as practical but version-specific findings, with experimental fields especially likely to change.
This article is not an official Claude Code release, but rather a more implementation-oriented source-code walkthrough. The author examined @anthropic-ai/[email protected], which is publicly distributed in the npm package, and compiled multiple configuration capabilities not mentioned or not fully described in the official documentation, attaching examples that can be dropped directly into a project. The article opens by warning about version risk: these findings only represent what is available in that version at the moment, undocumented fields may change across versions, and features whose names contain EXPERIMENTAL especially should not be treated as stable infrastructure.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hacker News (AI keywords) →Summaries are AI-generated; the original article is authoritative.