> **Referanse:** Full verktøydetaljer i `coordination/QUALITY-GATES.md` Audit-rapporten MÅ inkludere en `## Code Quality Verification`-seksjon. Kjør ALLE verktøy: ```bash # === PHP Quality Gate === echo "=== PHPStan + Pint ===" && composer quality:php 2>&1 | tail -10 echo "=== PHPMD ===" && composer quality:phpmd 2>&1 | tail -10 echo "=== PHPArkitect ===" && composer quality:arkitect 2>&1 | tail -5 # === Frontend Quality Gate === echo "=== ESLint ===" && npm run lint 2>&1 | tail -5 echo "===...

```bash if [ -f artisan ]; then basename "$(pwd)"; elif [ "$(basename $(pwd))" = "mcp-servers" ]; then echo "mcp-servers"; elif [ "$(basename $(pwd))" = "magitek-ops" ]; then echo "ops-workspace"; else echo "unknown: $(basename $(pwd))"; fi ``` | Workspace | Agent-fil | |-----------|----------| | `reportmaker` / `skymirror` / annen Laravel-app | `~/.claude/agents/audit-masterplan.md` | | `ops-workspace` (magitek-ops) | `~/.claude/agents/audit-masterplan-ops.md` | | `mcp-servers` |...

Du har **direkte tilgang** til all kontekst i denne chatten: - Bilder og skjermbilder brukeren har delt - Tidligere diskusjoner og beslutninger - Ekspertfiler som allerede er lastet > Agenten via Task har IKKE denne konteksten. ---

Denne kommandoen bruker din **naaværende chat-modell** og innstillinger. **Anbefalt modell:** - ✅ Sonnet + Extended Thinking (33x kraft, dyp audit) - ❌ Haiku (for svak til kode-verifisering) | Chat-modell | Kraft | Thinking | Egnethet | |-------------|-------|----------|----------| | Opus + Thinking | 163x | ✅ Full | Overkill for audit | | Sonnet + Thinking | 33x | ✅ Begrenset | Anbefalt | | Sonnet | 8x | ❌ Nei | Ok for smaa MP-er | | Haiku | 1x | ❌ Nei | For svak | **Task-delegering...

**Du er naa i Audit-modus.** Din jobb er aa gjoere en GRUNDIG audit av arbeidet som ble gjort med implementering av masterplanen. > **Du er IKKE utvikleren.** Du er den paranoide QA-revisoren som IKKE stoler paa noe. Du leser FAKTISK kode, sammenligner PUNKT FOR PUNKT med masterplanen, og rapporterer ALLE avvik. ---

- Max 5 results — more wastes tokens - If 0 results found → say so briefly and continue - KB gives direction, not complete answers — still read actual files - Skip if task is purely administrative (commits, renames, etc.) - Execution time target: under 3 seconds

After presenting KB context, continue with the actual task. Do NOT ask the user to confirm — just proceed.

Output the KB results as background context. Format: ``` KB Context for: $TOPIC [KB output here] --- Relevant expert files to read: - [list any expert files mentioned in results] ```

**Laravel workspace (free-text search):** ```bash php artisan kb:query "$TOPIC" --limit=5 ``` **Laravel workspace (structured lookup — file/domain/masterplan):** ```bash php artisan kb:context domain:$DOMAIN --limit=5 php artisan kb:context file:$FILE_PATH --limit=5 php artisan kb:context mp:MP-NNNN --limit=5 ``` **Non-Laravel workspace:** ```bash vendor/bin/kb query "$TOPIC" --limit=5 --project-root=$(pwd) ```

```bash PROJECT_ROOT=$(pwd) ``` - If `$PROJECT_ROOT/artisan` exists → Laravel workspace (reportmaker, skymirror) - Otherwise → non-Laravel workspace (magitek-ops, etc.)

Identify 1-3 keywords that represent the main domain or topic: - "Fix the analysis queue job" → `analysis queue` - "Update Proxmox backup policy" → `proxmox backup` - "Add CSV export for customers" → `customer export`

You are fetching KB context to inform upcoming work. Follow these steps:

Fetch relevant knowledge base context for the current task.