Update LLM instruction files for token efficiency and cross-repo navigation
- CLAUDE.md: reduced to single-line pointer to copilot-instructions.md (eliminates redundant auto-loaded content) - copilot-instructions.md: added @repo name field, relative paths in own-dep-repos, "do not re-read .md files" rule, and explicit permission to navigate external repos Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
parent
7b84ab8111
commit
4a33872b9d
File diff suppressed because one or more lines are too long
|
|
@ -1,8 +1 @@
|
||||||
# AyCode.Core — Claude Code Instructions
|
Always read `.github/copilot-instructions.md` first — it is the single source of truth for this repo.
|
||||||
|
|
||||||
Before writing any code, read these files:
|
|
||||||
1. `.github/copilot-instructions.md` — Domain rules and key pitfalls (single source of truth)
|
|
||||||
2. `docs/GLOSSARY.md` — Core abstractions and terminology
|
|
||||||
3. The relevant project's `README.md` for folder-specific context
|
|
||||||
|
|
||||||
When modifying code, update the corresponding README.md if it becomes out of sync with the code.
|
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue