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>

.claude/skills/contract/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: contract
+description: 특정 sprint의 contract 파일만 새로 작성하거나 갱신. plan-architect 에이전트에 위임. /sprint와 달리 PROGRESS.md 의 sprint 상태는 변경하지 않음(planning-only).
+argument-hint: <sprint-id e.g. S4>
+allowed-tools: Read, Write, Glob, Agent
+---
+
+대상 sprint: `$ARGUMENTS`
+
+1. `PLAN.md` 의 sprint 분할표에 `$ARGUMENTS` 가 있는지 확인.
+2. 기존 `docs/contracts/$ARGUMENTS-contract.md` 가 있으면 사용자에게 덮어쓸지 묻는다.
+3. **`plan-architect`** Agent 도구로 호출:
+   ```
+   Sprint $ARGUMENTS 의 contract 만 docs/contracts/$ARGUMENTS-contract.md 에
+   작성/갱신하라. PROGRESS.md sprint 상태판은 건드리지 말고, contract 링크만
+   해당 행의 Contract 칸에 갱신하라.
+   ```
+4. 결과 (생성/갱신된 contract 경로) 보고.