Adds the missing harness subsystems so future agent sessions can start,
stay in scope, verify work, and resume reliably:
- feature_list.json: local mirror of active/next-up work (GitHub Issues
on Project #6 remains the source of truth for the full backlog)
- progress.md / session-handoff.md / archive/2026-07.md: session state,
restart point, and monthly archive of finished work
- init.sh: install + lint + test + build verification entrypoint
- AGENTS.md: added Startup Workflow, Definition of Done, Stay in Scope,
and End of Session sections (existing agent-tier content kept as-is)
- CLAUDE.md: added a short Agent Workflow section routing to the above
Validated with the firstsun-harness audit script: 100/100 across all
five subsystems (instructions, state, verification, scope, lifecycle).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YYCTyZw7gUmJ7oh1VTmAqh
- Add 'npm run test' to development commands.
- Include 'Cost Optimization' rule for using Haiku subagents.
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
- Implement conflict detection in pushFile and pullFile using SHA comparison.
- Use SyncConflictModal to prompt users for manual resolution ('Use local' or 'Use remote').
- Added unit tests in sync-manager.test.ts to verify conflict handling logic.
- Fixed linting issues related to unhandled promises and mock type safety.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
