Setup RailPose3D harness (Planner/Generator/Evaluator)

Name the project RailPose3D and stand up a multi-agent harness
following the Anthropic harness-design blog principles
(decomposition, separation of concerns, file-based handoff,
sprint contracts, context-reset over compaction).

- CLAUDE.md / PLAN.md / PROGRESS.md as the file-based handoff
  surface; every agent must read PLAN+PROGRESS before acting.
- 7 sub-agents under .claude/agents/: plan-architect (Planner),
  pole-detector-builder, rail-detector-builder, triangulation-
  builder, data-pipeline-builder (Generators), module-evaluator
  (Evaluator), dataset-explorer (read-only helper).
- 6 skills under .claude/skills/: /start /sprint /eval /progress
  /handoff /contract.
- SessionStart and Stop hooks to inject the PLAN/PROGRESS
  briefing and remind about PROGRESS.md updates.
- docs/plan.md captures the user-approved detailed plan;
  docs/research.md is the prior tech survey.
- .gitignore excludes data/, .usage/, model checkpoints, and
  local Claude overrides.

Tracking: closes #1

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.gitignore

@@ -0,0 +1,30 @@
+# Data and outputs (large, gitignored per CLAUDE.md §5)
+data/
+*.pth
+*.ckpt
+*.onnx
+
+# Local usage tracking
+.usage/
+
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+.venv/
+.uv/
+build/
+dist/
+
+# Editor / OS
+.idea/
+.vscode/
+.DS_Store
+Thumbs.db
+
+# Claude Code local
+.claude/CLAUDE.local.md
+.claude/settings.local.json
+
+# Large prebuilt binary in this repo (if accidentally added)
+claude_token_usage(1).exe