feat: agent loop harness with Claude Code plugin support

Generator-evaluator architecture with iterative context-reset for
long-running coding tasks. Ships as a Claude Code plugin — install
with /plugin and use /agent-loop:init, /agent-loop:plan, /agent-loop:run.

templates/contract.md.template

@@ -0,0 +1,35 @@
+# Sprint Contract: {{STORY_ID}} — {{STORY_TITLE}}
+
+## What Will Be Built
+
+<!-- Concrete description of the deliverable -->
+
+## Done Conditions
+
+- [ ] <!-- Specific, testable condition -->
+- [ ] <!-- Another condition -->
+- [ ] All acceptance criteria from prd.json met
+- [ ] Quality gates pass (typecheck, lint, test)
+
+## Evaluation Criteria
+
+What the evaluator will specifically check:
+- [ ] <!-- Specific verification step -->
+- [ ] <!-- Another verification step -->
+- [ ] No regressions in existing functionality
+
+## Out of Scope
+
+Things explicitly NOT part of this story:
+- <!-- Thing 1 -->
+- <!-- Thing 2 -->
+
+## Key Files
+
+Files likely to be created or modified:
+- <!-- path/to/file.ext — what changes -->
+
+## Dependencies
+
+- Depends on: <!-- story IDs or "none" -->
+- Blocks: <!-- story IDs or "none" -->