Author gritty, disposition-gated Margreave content (lore bible + hand-authored
quest/item/location/origin JSON) that reconciles against existing canon before
writing, holds the world's hard-by-default / warm-when-earned NPC tone, and keeps
the content_build --check gate green.
- SKILL.md: read-before-write workflow, read-only on existing canon (propose
diffs, require approval), build+check+pytest as the done bar.
- references/schema.md: full bible + JSON contract, secrecy scale, gate model.
- references/tone.md: tone contract + NPC disposition-warmth model.
- scripts/canon_index.py: dumps existing ids for reconciliation.
- evals/: 3 test cases (all green in isolated-worktree runs).
Un-ignore /.claude/skills/ so project skills are versioned like code; all other
.claude/ dirs (root + nested api/client) stay ignored.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HuHRPE7VfppUJEaoGBEUqZ
These are Claude Code session/state files, not project code. They were
swept into the first commit; remove from the index (kept on disk) and
ignore going forward so they stop dirtying status.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
