supervisord.conf, entrypoint.sh)
- `internal/web/` — Web Dashboard: HTTP server, REST API handlers, WebSocket endpoints (stats/logs/events), embedded frontend
- `internal/version/` — build version info (injected via ldflags)
Each claw instance is a Docker container running
cases around the user's real path and don't skip steps.
- For any frontend UI, write E2E with **Playwright**, issuing requests to a **real backend API** — no stubbed network
Symfony UX Frontend Stack
This project uses the Symfony UX frontend stack. Seven agent skills are installed to help you work with it.
## Which tool to use
- **Pure JS behavior
honest through role, context, and schema.
- Do not add dead surfaces “just in case”.
## Frontend quick map
- `frontend/src/App.tsx`: app shell and state wiring
- `frontend/src/components/WorkspaceShell.tsx`: sidebar and workspace chrome
- `frontend/src/components/GraphCanvas.tsx`: graph
debug.
## Build Verification
Always verify after changes:
```bash
cd backend && go build ./...
cd frontend && npx tsc --noEmit
```
## Dependent Project Deployment (CRITICAL)
Any project built on the LastSaaS boilerplate — whether using
hypertool-mcp persona add ./personas/frontend-dev
# Run with the persona
hypertool-mcp mcp run --persona frontend-dev
# The persona's default toolset is automatically activated
# Or specify a different persona toolset
example_route():
...
```
## Security — Settings Sanitization
**NEVER send raw settings or configuration data to the frontend without sanitization.**
- Always use `sanitize_settings_for_user()` from `functions_settings.py` before passing settings to `render
remove components** and measure impact. Simplest solution first, complexity only when needed.
### Quality Criteria (Frontend)
- **Design Quality** -- coherence, not a collection of parts
- **Originality** -- penalize template layouts, library defaults
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.