- .gitattributes: *.glb / *.gltf now route to LFS. glb is the primary
Blender->Unity handoff and was committing as raw uncompressible blobs
(verified: git check-attr returned "unspecified"). Existing files stay
as plain blobs; new exports go to LFS.
- settings.json deny-list: add git restore / git checkout -- / git stash.
The list guarded the destructive commands that cannot lose work here
and omitted the ones that can, in a tree that is routinely dirty.
- settings.local.json: drop the blanket Bash(python *) allow (a full
escape hatch past the deny-list beside it), drop the serena MCP entry
(server removed 2026-07-07), and collapse 5 single-use literal command
allows into two prefix rules.
- workflow-patterns.md: stop telling subagents to prefer serena's
find_symbol — that template made every spawned agent burn a turn on a
tool-not-found error. Glob/Grep is now the primary instruction, matching
memory-protocol.md and CLAUDE.md.
Also done outside git: the leaked ghp_ PAT was stripped from the origin
remote URL, and lfs.allowincompletepush was unset so a failed LFS upload
fails the push loudly instead of reporting success.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Session log for the 07-24 character work. Adds cookbook 14-E: the per-instance _BaseColor override
gotcha (hit-flash sets URPMaterialPropertyBaseColor=(1,1,1) on player/enemy render children, replacing
the material _BaseColor -> flat null-map materials render cream; color via a solid _BaseColorMap texture).
Corrects the older 'clear the map -> uses _BaseColor' note.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Bank the Mark-V lessons: when scripted primitives can't nail an iconic organic shape, generate with
Hyper3D Rodin then CONFORM - watertight clean-decimate (weld+recalc first, gentle collapse, 0 boundary
edges = hole detector), drop the baked photoreal texture for the shared flat palette, flat-shade,
ontology-tie emissives, and don't skin a meter-scale generated mesh onto a cm-scale rig (~100x shrink).
Added the generate path to the Build phase + a keystone clause (strip a kitbash/gen mesh's own texture).
Also fixed a duplicate section number (12 -> 13).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
'Light is territory' pool lighting (reads top-down; vertical god-rays don't),
undulating seabed mesh, Play-mode ambiance script, and the apply-armature +
visual-transform static hero-bake recipe for style-proof placement.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds the in-engine verification recipe (URP SubmitRenderRequest render
harness, layer sign-bit gotcha, game-camera check) and the persistent
ArtStaging scene recipe.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
New /art-dev skill (SKILL.md + blender-cookbook + style-and-practices refs)
driving LANTERN Blender art work: Auto (headless) for simple changes, the
hybrid nudge-and-bake loop for precision/aesthetics, game-camera verification,
Blender-beginner coaching. Session log covers the A0 style-proof asset set +
the Bathynaut refinement.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Session log Part C (execution + validation evidence), roadmap stabilize #2
ticked, CLAUDE.md gains the MeshCollider-bakes-only-if-Read/Write gotcha
(38.4 KB, in budget), validation-harness.md gains the EditorApplication.update
guardian + EditorPrefs handoff pattern.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Serena dropped from .mcp.json + .serena/ untracked (unused in practice,
flaky on Unity per CLAUDE.md's own caveat); memory stack is now three
layers. Standing auths recorded in the skill: docs auto-commit + auto-push
main->gitea (origin stays ask-first).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Realigns the skill with how sessions actually run now — it predated the
Workflow tool and the ultracode two-review practice. Driven by an analysis
of the full session history + the 26-file memory corpus + skill-authoring
research, adversarially reviewed.
Key changes:
- Workflow-first orchestration: drop the dead manual "swarm (<=N agents)"
model and the impossible 3-5-agent impl swarm; implementation is serial
orchestrator MCP edits. New references/workflow-patterns.md (ground
fan-out + design-review lens/critic) replaces agent-briefs.md.
- Pre-code design-review + post-impl diff-review are now first-class gated
phases (the spine that catches what green tests + a clean Play miss).
- Size by blast-radius / netcode-heaviness, not time estimates.
- Lean SKILL.md (222 -> 131 lines, -25% KB): leans on CLAUDE.md instead of
duplicating its MCP cheat-sheet / anti-patterns / error-recovery.
- ctx7 CLI / find-docs mechanism (the MCP verbs are gone); live-verified
6.5-era library pins; kill the dead NetCodeTestWorld test path.
- Encode operator gates (no-time-estimates, present-forks, never-defer,
tuning-autonomy) + the highest-recurrence MCP-edit / Workflow gotchas.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Move the dots-dev skill from machine-local ~/.claude/skills/ into the
repo at .claude/skills/dots-dev/ so it travels with a clone. Update the
CLAUDE.md per-machine setup note to reflect that the skill no longer
needs manual placement; unity-mcp-skill and native memory/ stay local.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>