docs: README still described the reverted AGENTS.md design

This commit is contained in:
naps62
2026-08-01 15:02:47 +00:00
parent 60f39cdcbb
commit ad4d14e078
+4 -4
View File
@@ -8,7 +8,8 @@ Single source of truth for custom agent skills + commands. Shared across **Claud
skills/ # SKILL.md dirs — Claude Code AND Codex both read these (open Agent Skills standard)
commands/ # slash commands — Claude Code only (Codex ignores)
hooks/ # Claude Code hooks — see hooks/README.md, wiring is manual
claude-md/ # CLAUDE.md fragments — linked to ~/.claude/, imported via @name.md
claude-md/ # shared instruction fragments — imported by both entry files
entry/ # entry files: ~/.claude/CLAUDE.md and ~/.codex/AGENTS.md
bin/link.sh # bootstrap symlinks for non-Nix machines
nix/home.nix # home-manager module for NixOS machines
flake.nix # exposes homeModules.default
@@ -87,9 +88,8 @@ bump `ref` + `vendored` in `UPSTREAM`.
## Writing contract
One contract, `claude-md/writing.md`, linked three ways: `~/.claude/writing.md`
(imported via `@writing.md`), `~/.agents/AGENTS.md` (Codex, which has no
`@import`), and the nix module for NixOS machines.
One contract, `claude-md/writing.md`. Both entry files `@import` it, so Claude
Code and Codex read the same bytes on every machine.
The rule it encodes is **selection, not compression**: keep output short by
cutting whole ideas that don't change what the reader does next, then write