morninglisted

# /morning — Morning Routine **Conduct ALL conversation with the user in the language defined by `.claude/rules/personal-language.md`** (or the user's input language if absent). The English instructions below are for skill clarity, not for output style. Exceptions (only): tokens inside backticks or code blocks, proper nouns, ASCII acronyms. > **Tool references in this skill** ("skill invocation") describe **intent**, not Claude-specific tool calls. Each harness should map them to its native equivalent — Claude Code uses its built-in Skill tool; Codex CLI uses its own skill invocation mechanism (mention / implicit / `/skills`). Runs the two user-facing daily reports in sequence: Daily Note (/briefing) and research newsletter (/newsletter). Both run inline within the current session via the harness's skill mechanism. Background processing (external source sync, knowledge distillation) is **not** part of /morning (ADR-075). When you want to catch up, ask inside your vault — *"pull in new entries and extract anything useful"* — and the assistant will route to `/sync` then `/distill`. For unattended automation, see [docs/guides/scheduling.md](../../docs/guides/scheduling.md). ## Why sequential (not parallel) Earlier revisions of /morning spawned `/briefing` and `/newsletter` as parallel sub-processes. When the parent session runs in `auto` mode (the recommended default), the harness's classifier reliably refuses to spawn in-session sub-agents with elevated permissions — this