@adaptic/maestro 1.0.1 → 1.1.1

package/scaffold/CLAUDE.md

@@ -12,6 +12,213 @@ claude "/init-maestro"
 
 This will configure your name, role, responsibilities, communication style, and all operational parameters.
 
+## Company Context
+
+*Configure via /init-maestro*
+
+## Operating Principles
+
+*Configure via /init-maestro — principles will be set based on your role archetype.*
+
+## Communication Rules
+
+### Voice Modes
+
+- **Agent's voice**: Default for all operational communications (internal + external)
+- **Principal's voice**: For communications attributed to the principal
+- **Internal notes**: Analysis, risk flags — not sent externally
+- **Institutional**: Regulatory and legal correspondence
+
+### Autonomy Model
+
+*Configure via /init-maestro — autonomy boundaries depend on role archetype.*
+
+### Immediate Acknowledgement Rule (Slack, SMS, WhatsApp)
+
+When this agent receives an incoming request via Slack, SMS, or WhatsApp that is complex or will take more than a few minutes to action, it MUST send an immediate holding note before beginning work.
+
+### Document Sharing (CRITICAL)
+
+**NEVER reference local file paths in Slack, email, or any outbound communication.** No one outside this Mac mini can access files at `outputs/`, `docs/`, or any other local path.
+
+When sharing documents or supporting materials:
+
+1. **Prefer Google Drive** — Upload as a Google Doc/Sheet/Slides and share the Drive link
+2. **Use PDF when appropriate** — For final/read-only documents, generate a branded PDF via `npm run pdf:memo`
+3. **Inline short content** — For brief updates (< 1 page), include directly in the message body
+4. **Never reference local file paths** in any external communication
+
+### Logging
+
+All sent communications are logged to `logs/` with full audit trail.
+
+## Repository Layout
+
+- `agents/` — Agent definitions with mandates and prompts
+- `teams/` — Agent team compositions
+- `workflows/` — Daily/weekly/monthly/quarterly workflow configs
+- `knowledge/` — Sources, memory, entities, decisions
+- `config/` — Environment, priorities, contacts, repo registry, brand assets
+- `policies/` — Action classification and approval rules
+- `desktop-control/` — macOS app control profiles
+- `outputs/` — Briefs, memos, board materials, follow-ups
+- `scripts/` — Emergency stop, healthcheck, bootstrap, PDF generation, media generation
+- `public/assets/` — Brand SVG assets (icon + logo, dark + light variants)
+- `public/generated/` — Generated illustrations, diagrams, and videos
+
+## Key Config Files
+
+- `config/agent.ts` — Central identity configuration (single source of truth)
+- `config/priorities.yaml` — Active strategic priorities and milestones
+- `config/contacts.yaml` — Key contacts with communication classifications
+- `config/environment.yaml` — Environment-specific configuration
+- `config/sla-defaults.yaml` — SLA response time expectations
+- `config/brand-assets.yaml` — Brand asset inventory, usage rules, and placement guidelines
+- `policies/action-classification.yaml` — Action risk levels and approval rules
+
+## Brand Assets
+
+Official Adaptic brand assets live in `public/assets/`. See `config/brand-assets.yaml` for full rules.
+
+## PDF Generation
+
+Generate branded PDFs from Markdown using Pandoc + XeLaTeX.
+
+```bash
+npm run pdf:memo -- --input <file.md>          # Internal memos and briefs
+npm run pdf:board-pack -- --input <file.md>    # Board materials with cover + TOC
+npm run pdf:letter -- --input <file.md>        # Corporate correspondence
+npm run pdf:investor -- --input <file.md>      # Investor communications
+```
+
+## Visual Media Generation
+
+Generate branded illustrations, diagrams, and videos using Gemini and Veo APIs.
+
+```bash
+npm run gen:illustration -- <slug>    # Single illustration via Gemini
+npm run gen:video -- <slug>           # Single video via Veo 3.1
+npm run gen:all-missing               # Batch generate missing illustrations
+npm run gen:list                      # List available prompt specs
+```
+
+## People (Key Leadership)
+
+*Configure via /init-maestro*
+
+## Operational Infrastructure
+
+### State Management
+
+- **Live queues**: 16 operational queues in `state/queues/` track action items, decisions, follow-ups, blockers
+- **Dashboards**: `state/dashboards/executive-summary.yaml` is read at every session start
+- **Standard schema**: All queue items follow open → in_progress → blocked → resolved → closed
+
+### Event Polling
+
+- **Daemon**: `scripts/daemon/maestro-daemon.mjs` polls Slack/Gmail/Calendar every 60 seconds
+- **Inbox**: New items land in `state/inbox/{service}/` as YAML files
+- **Inbox processor**: Classifies and routes items every 5 minutes
+- **Priority triggers**: Principal DMs, urgent tags, and agent mentions trigger immediate processing
+
+### Self-Evolution
+
+- Agent learns from interactions and evolves its own operating setup
+- Changes classified by risk: low (auto-apply), medium (apply + notify), high (escalate)
+- All self-modifications logged to `logs/evolution/`
+
+### Prompt Injection Defence
+
+- 5-layer defence defined in `policies/prompt-injection-defence.yaml`
+
+### Audit & Hooks
+
+- Pre-send audit hook gates all outbound Slack/Gmail communications
+- Post-action hook logs all tool completions
+- Session-end hook logs session completion
+- All logs in `logs/audit/`, `logs/workflows/`, `logs/security/`, `logs/sessions/`
+
+### Session Protocol
+
+**Every session starts by:**
+1. Reading `state/dashboards/executive-summary.yaml`
+2. Checking `state/inbox/` for unprocessed items
+3. Checking `state/queues/decision-queue.yaml` for pending decisions
+
+**Every session ends by:**
+1. Updating modified queue items
+2. Regenerating the executive summary dashboard
+3. Running self-evolution reflection
+4. Logging session summary
+
+## Control Towers
+
+12 operational control towers provide comprehensive organisational coverage:
+
+1. **Strategy & Decisions** — Priority drift detection, decision library, strategic coherence
+2. **Executive Office & Follow-Through** — Action capture, loop closure, SLA tracking
+3. **Operating Cadence & PMO** — Meeting prep, action routing, initiative scorecard
+4. **People, Hiring & Organisation** — Org health, founder dependency, onboarding
+5. **Culture, Standards & Leadership** — Leadership accountability, communication quality
+6. **Product, Platform & Engineering** — Engineering health, tech debt, delivery confidence
+7. **Commercial, Customers & Market** — Relationship pipeline, competitive intelligence
+8. **Board, Advisors & Stakeholders** — Board calendar, advisor utilisation
+9. **Capital, Finance & Corporate Dev** — Capital readiness, runway tracking
+10. **Legal, Risk, Compliance & Regulatory** — Enterprise risk register, compliance calendar
+11. **Systems, Automation & Memory** — Knowledge health, automation opportunities
+12. **Self-Governance** — System health, quarterly self-assessment
+
+## Build & Test
+
+Install dependencies with `npm install`.
+
+- Health check: `npm run healthcheck`
+- Emergency stop: `npm run emergency-stop`
+- Resume: `npm run resume`
+- PDF generation: `npm run pdf:memo -- --input <file>` (requires Pandoc + MacTeX)
+- Media generation: `npm run gen:illustration -- <slug>` (requires GEMINI_API_KEY)
+
+## Maestro Framework
+
+This agent is powered by the `@adaptic/maestro` framework. Update framework: `npm run upgrade`
+
+## Code Standards
+
+- YAML for all configuration and workflow definitions
+- Markdown for all documentation and agent prompts
+- Shell scripts must be POSIX-compatible where possible
+- All scripts must have error handling (`set -e`)
+- All configs must use environment variables for secrets
+- All actions must be auditable via logs/
+
+## Three Operating Modes
+
+### Mode 1: Reactive — Respond to Events
+- Daemon detects inbound Slack/Gmail/Calendar events every 60 seconds
+- Priority events trigger immediate processing
+
+### Mode 2: Scheduled — Run Cadence Workflows
+- Morning brief, midday sweep, evening wrap (daily)
+- Domain-specific reviews (weekly)
+- Self-assessment (quarterly)
+
+### Mode 3: Proactive — Execute the Backlog
+- Backlog executor runs every 10 minutes
+- Reads all queues, selects top actionable items
+- Spawns parallel background agents to execute each item
+
+## Parallel Execution & Agent Teams
+
+Agent MUST use parallel execution for complex tasks. Agent Teams are enabled via `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`.
+
+### When to spawn parallel agents
+
+- **Always** for tasks with 2+ independent subtasks
+- **Always** for cross-functional work
+- **Always** for time-sensitive workflows
+
+Sequential processing should be the exception, not the default.
+
 ## Quick Reference
 
 - Agent config: `config/agent.ts`

package/scripts/daemon/maestro-daemon.mjs

@@ -0,0 +1,37 @@
+#!/usr/bin/env node
+// =============================================================================
+// Maestro Daemon — Reactive event-driven message processor
+// =============================================================================
+//
+// Generic entry point that loads agent identity from config/agent.ts and
+// delegates to the core daemon logic. This file is agent-name-agnostic.
+//
+// Run: node scripts/daemon/maestro-daemon.mjs
+// Install: launchd plist with KeepAlive: true
+// =============================================================================
+
+// The core daemon is in sophie-daemon.mjs for backward compatibility.
+// It uses AGENT_DIR (resolved from this file's location) as the base path.
+// The init-maestro wizard renames sophie references in that file.
+
+import { resolve, dirname } from "node:path";
+import { fileURLToPath } from "node:url";
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+const AGENT_DIR = resolve(__dirname, "../..");
+
+// Set AGENT_DIR as env var so all modules can use it
+process.env.AGENT_DIR = AGENT_DIR;
+process.env.AGENT_ROOT = AGENT_DIR;
+
+// Singleton guard — prevent duplicate daemon instances
+try {
+  const { acquireLock } = await import(resolve(process.env.HOME, "maestro/lib/singleton.js"));
+  if (!acquireLock("daemon")) {
+    console.log("[DAEMON] Already running — exiting");
+    process.exit(0);
+  }
+} catch { /* maestro singleton not available */ }
+
+// Import and run the daemon (handles its own .env loading)
+await import("./sophie-daemon.mjs");

package/scripts/local-triggers/generate-plists.sh

@@ -0,0 +1,235 @@
+#!/bin/bash
+# =============================================================================
+# generate-plists.sh — Generate launchd plist files from templates
+# =============================================================================
+#
+# Reads config/agent.ts to extract the agent's first name and generates
+# properly configured plist files for all scheduled triggers and the daemon.
+#
+# Usage:
+#   ./scripts/local-triggers/generate-plists.sh
+#
+# Called by: init-agent.sh (Step 5)
+# =============================================================================
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+AGENT_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
+PLIST_DIR="$SCRIPT_DIR/plists"
+AGENT_CONFIG="$AGENT_DIR/config/agent.ts"
+
+# Extract agent first name from config/agent.ts
+if [ -f "$AGENT_CONFIG" ]; then
+    AGENT_FIRST=$(grep "firstName:" "$AGENT_CONFIG" | head -1 | sed "s/.*firstName:[[:space:]]*['\"]//; s/['\"].*//" | tr '[:upper:]' '[:lower:]')
+fi
+
+# Fall back to directory name if config not set or UNCONFIGURED
+if [ -z "$AGENT_FIRST" ] || [ "$AGENT_FIRST" = "unconfigured" ]; then
+    AGENT_FIRST=$(basename "$AGENT_DIR" | sed 's/-ai$//')
+fi
+
+AGENT_UPPER=$(echo "$AGENT_FIRST" | tr '[:lower:]' '[:upper:]')
+AGENT_USER=$(whoami)
+NODE_PATH=$(which node 2>/dev/null || echo "/opt/homebrew/bin/node")
+
+echo "[generate-plists] Agent: $AGENT_FIRST"
+echo "[generate-plists] Directory: $AGENT_DIR"
+echo "[generate-plists] User: $AGENT_USER"
+
+mkdir -p "$PLIST_DIR"
+
+# Clear old plists before generating — prevents stale plists from a previous
+# agent identity (e.g. sophie-*) from being installed alongside new ones
+rm -f "$PLIST_DIR"/*.plist 2>/dev/null
+
+# ── Helper: generate a single plist ──────────────────────────────────────────
+
+generate_plist() {
+    local LABEL="$1"
+    local PROGRAM_ARGS="$2"  # The command to run (array elements separated by |)
+    local SCHEDULE="$3"      # Optional: StartCalendarInterval dict content
+    local INTERVAL="$4"      # Optional: StartInterval in seconds
+    local KEEP_ALIVE="$5"    # Optional: true for daemon-style
+
+    local FILE="$PLIST_DIR/$LABEL.plist"
+
+    cat > "$FILE" << PLIST_HEADER
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+    <key>Label</key>
+    <string>$LABEL</string>
+
+    <key>ProgramArguments</key>
+    <array>
+PLIST_HEADER
+
+    # Split program args by |
+    IFS='|' read -ra ARGS <<< "$PROGRAM_ARGS"
+    for arg in "${ARGS[@]}"; do
+        echo "        <string>$arg</string>" >> "$FILE"
+    done
+
+    cat >> "$FILE" << PLIST_MID
+    </array>
+
+    <key>WorkingDirectory</key>
+    <string>$AGENT_DIR</string>
+PLIST_MID
+
+    if [ "$KEEP_ALIVE" = "true" ]; then
+        cat >> "$FILE" << 'PLIST_KEEPALIVE'
+
+    <key>KeepAlive</key>
+    <true/>
+
+    <key>RunAtLoad</key>
+    <true/>
+
+    <key>ThrottleInterval</key>
+    <integer>5</integer>
+PLIST_KEEPALIVE
+    fi
+
+    if [ -n "$SCHEDULE" ]; then
+        cat >> "$FILE" << PLIST_SCHED
+
+    <key>StartCalendarInterval</key>
+    <dict>
+$SCHEDULE
+    </dict>
+PLIST_SCHED
+    fi
+
+    if [ -n "$INTERVAL" ]; then
+        cat >> "$FILE" << PLIST_INTERVAL
+
+    <key>StartInterval</key>
+    <integer>$INTERVAL</integer>
+PLIST_INTERVAL
+    fi
+
+    cat >> "$FILE" << PLIST_FOOTER
+
+    <key>StandardOutPath</key>
+    <string>$AGENT_DIR/logs/daemon/launchd-stdout.log</string>
+
+    <key>StandardErrorPath</key>
+    <string>$AGENT_DIR/logs/daemon/launchd-stderr.log</string>
+</dict>
+</plist>
+PLIST_FOOTER
+
+    echo "  Generated: $LABEL"
+}
+
+# ── Helper: trigger plist (runs claude with a trigger prompt) ────────────────
+
+generate_trigger_plist() {
+    local TRIGGER_NAME="$1"
+    local SCHEDULE="$2"
+    local INTERVAL="$3"
+
+    local LABEL="ai.adaptic.${AGENT_FIRST}-${TRIGGER_NAME}"
+    local TRIGGER_FILE="$AGENT_DIR/schedules/triggers/${TRIGGER_NAME}.md"
+    local RUN_TRIGGER="$AGENT_DIR/scripts/local-triggers/run-trigger.sh"
+
+    generate_plist "$LABEL" \
+        "$RUN_TRIGGER|$TRIGGER_FILE" \
+        "$SCHEDULE" \
+        "$INTERVAL" \
+        ""
+}
+
+# ── Generate all plists ─────────────────────────────────────────────────────
+
+echo ""
+echo "Generating launchd plist files..."
+
+# 1. Main daemon (KeepAlive)
+generate_plist "ai.adaptic.${AGENT_FIRST}-daemon" \
+    "${NODE_PATH}|${AGENT_DIR}/scripts/daemon/maestro-daemon.mjs" \
+    "" "" "true"
+
+# 2. Slack events server (KeepAlive) — real-time Slack message handling
+generate_plist "ai.adaptic.${AGENT_FIRST}-slack-events" \
+    "${NODE_PATH}|${AGENT_DIR}/scripts/slack-events-server.mjs" \
+    "" "" "true"
+
+# 3. Inbox processor (every 5 minutes)
+generate_trigger_plist "inbox-processor" "" "300"
+
+# 4. Backlog executor (every 10 minutes)
+generate_trigger_plist "backlog-executor" "" "600"
+
+# 5. Meeting prep (every 15 minutes)
+generate_trigger_plist "meeting-prep" "" "900"
+
+# 6. Meeting action capture (every 30 minutes)
+generate_trigger_plist "meeting-action-capture" "" "1800"
+
+# 7. Midday sweep (daily at 12:00 local)
+generate_trigger_plist "daily-midday-sweep" \
+    "        <key>Hour</key>
+        <integer>12</integer>
+        <key>Minute</key>
+        <integer>0</integer>"
+
+# 8. Weekly hiring (Monday 09:00)
+generate_trigger_plist "weekly-hiring" \
+    "        <key>Weekday</key>
+        <integer>1</integer>
+        <key>Hour</key>
+        <integer>9</integer>
+        <key>Minute</key>
+        <integer>0</integer>"
+
+# 9. Weekly priorities (Monday 11:00)
+generate_trigger_plist "weekly-priorities" \
+    "        <key>Weekday</key>
+        <integer>1</integer>
+        <key>Hour</key>
+        <integer>11</integer>
+        <key>Minute</key>
+        <integer>0</integer>"
+
+# 10. Weekly execution (Wednesday 14:00)
+generate_trigger_plist "weekly-execution" \
+    "        <key>Weekday</key>
+        <integer>3</integer>
+        <key>Hour</key>
+        <integer>14</integer>
+        <key>Minute</key>
+        <integer>0</integer>"
+
+# 11. Weekly engineering health (Wednesday 10:00)
+generate_trigger_plist "weekly-engineering-health" \
+    "        <key>Weekday</key>
+        <integer>3</integer>
+        <key>Hour</key>
+        <integer>10</integer>
+        <key>Minute</key>
+        <integer>0</integer>"
+
+# 12. Weekly strategic memo (Friday 14:00)
+generate_trigger_plist "weekly-strategic-memo" \
+    "        <key>Weekday</key>
+        <integer>5</integer>
+        <key>Hour</key>
+        <integer>14</integer>
+        <key>Minute</key>
+        <integer>0</integer>"
+
+# 13. Quarterly self-assessment (1st of month, 09:00)
+generate_trigger_plist "quarterly-self-assessment" \
+    "        <key>Day</key>
+        <integer>1</integer>
+        <key>Hour</key>
+        <integer>9</integer>
+        <key>Minute</key>
+        <integer>0</integer>"
+
+echo ""
+echo "Generated $(ls "$PLIST_DIR"/*.plist 2>/dev/null | wc -l | tr -d ' ') plist files in $PLIST_DIR"

package/scripts/local-triggers/install-all.sh

@@ -1,28 +1,34 @@
 #!/bin/bash
-# Install all local Sophie triggers as macOS launchd daemons
+# Install all local agent triggers as macOS launchd daemons
 # Usage: ./scripts/local-triggers/install-all.sh
 #
-# This installs the triggers that run locally on the Mac mini:
-# - Midday sweep (daily 12:00 GST)
-# - Inbox processor (every 5 minutes)
-# - Weekly hiring review (Monday 09:00 GST)
-# - Weekly priorities reset (Monday 11:00 GST)
-# - Weekly execution review (Wednesday 14:00 GST)
-# - Weekly strategic memo (Friday 14:00 GST)
-#
-# The morning brief and evening wrap run as remote cloud triggers.
+# This generates plist files from agent config and installs them.
+# The generate-plists.sh script reads config/agent.ts to determine
+# the agent name and generates properly configured plist files.
 
 set -e
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+AGENT_DIR="$(cd "$SCRIPT_DIR/../.." && pwd)"
 PLIST_DIR="$SCRIPT_DIR/plists"
+GENERATOR="$SCRIPT_DIR/generate-plists.sh"
 LAUNCH_AGENTS_DIR="$HOME/Library/LaunchAgents"
 
 mkdir -p "$LAUNCH_AGENTS_DIR"
 
-echo "Installing Sophie local triggers..."
+# Generate plists from agent config
+if [ -x "$GENERATOR" ]; then
+    echo "Generating plist files from agent config..."
+    bash "$GENERATOR"
+else
+    echo "Warning: generate-plists.sh not found — using existing plists"
+fi
+
+echo ""
+echo "Installing local triggers..."
 
 for plist in "$PLIST_DIR"/*.plist; do
+    [ -f "$plist" ] || continue
     PLIST_NAME=$(basename "$plist")
     LABEL=$(basename "$plist" .plist)
     DST="$LAUNCH_AGENTS_DIR/$PLIST_NAME"
@@ -40,4 +46,4 @@ done
 echo ""
 echo "All local triggers installed."
 echo "Check status: launchctl list | grep adaptic"
-echo "Uninstall all: for f in ~/Library/LaunchAgents/ai.adaptic.sophie-*.plist; do launchctl unload \"\$f\" && rm \"\$f\"; done"
+echo "Uninstall all: for f in ~/Library/LaunchAgents/ai.adaptic.*.plist; do launchctl unload \"\$f\" && rm \"\$f\"; done"

package/scripts/setup/init-agent.sh

@@ -126,35 +126,63 @@ echo ""
 log "Creating state and log directories..."
 
 DIRS=(
+    "config"
+    "knowledge/decisions"
+    "knowledge/decisions/archive"
+    "knowledge/entities"
+    "knowledge/memory"
+    "knowledge/sources"
+    "knowledge/syntheses"
+    "memory/interactions"
+    "memory/profiles/users"
+    "memory/profiles/channels"
+    "memory/precedents"
+    "memory/precedents/market-signals"
+    "memory/indexes"
+    "memory/templates"
     "state/inbox/slack"
     "state/inbox/gmail"
     "state/inbox/calendar"
     "state/inbox/sms"
+    "state/inbox/whatsapp"
     "state/inbox/internal"
-    "state/triggers/priority"
-    "state/locks/outbound"
+    "state/inbox/attachments"
+    "state/inbox/processed"
     "state/queues"
     "state/dashboards"
     "state/polling"
-    "logs/polling"
-    "logs/workflows"
-    "logs/sessions"
-    "logs/audit"
-    "logs/sms"
-    "logs/monitor"
-    "logs/security"
-    "logs/evolution"
-    "memory/interactions"
-    "memory/profiles/users"
-    "memory/profiles/channels"
-    "memory/precedents"
-    "memory/templates"
+    "state/locks/outbound"
+    "state/triggers/priority"
+    "state/handoffs"
+    "state/huddle"
+    "state/indexes"
+    "state/rag"
+    "state/sessions"
+    "state/slack-responded"
+    "state/slack-thread-tracker"
+    "state/tmp"
     "outputs/briefs"
     "outputs/drafts"
     "outputs/memos"
     "outputs/research"
     "outputs/tasks"
     "outputs/sessions"
+    "logs/polling"
+    "logs/workflows"
+    "logs/sessions"
+    "logs/audit"
+    "logs/security"
+    "logs/evolution"
+    "logs/huddle"
+    "logs/daemon"
+    "logs/infra"
+    "logs/monitor"
+    "logs/phone"
+    "logs/sms"
+    "logs/whatsapp"
+    "logs/email"
+    "self-optimization/scenarios"
+    "tests"
 )
 
 for dir in "${DIRS[@]}"; do
@@ -337,16 +365,23 @@ echo ""
 # Step 5: Generate and install launchd plists
 # ---------------------------------------------------------------------------
 
-log "Installing macOS launchd agents..."
+log "Generating and installing macOS launchd agents..."
 
 LAUNCH_AGENTS_DIR="$HOME/Library/LaunchAgents"
-PLIST_TEMPLATE_DIR="$AGENT_DIR/scripts/local-triggers/plists"
+PLIST_GENERATOR="$AGENT_DIR/scripts/local-triggers/generate-plists.sh"
+PLIST_DIR="$AGENT_DIR/scripts/local-triggers/plists"
 mkdir -p "$LAUNCH_AGENTS_DIR"
 
-if [ ! -d "$PLIST_TEMPLATE_DIR" ]; then
-    warn "No plist templates found at $PLIST_TEMPLATE_DIR — skipping launchd setup"
+# Generate plists from agent config (handles agent name substitution)
+if [ -x "$PLIST_GENERATOR" ]; then
+    bash "$PLIST_GENERATOR"
+    ok "Generated plist files from agent config"
 else
-    for plist in "$PLIST_TEMPLATE_DIR"/*.plist; do
+    warn "Plist generator not found at $PLIST_GENERATOR — using existing plists"
+fi
+
+if [ -d "$PLIST_DIR" ] && ls "$PLIST_DIR"/*.plist &>/dev/null; then
+    for plist in "$PLIST_DIR"/*.plist; do
         PLIST_NAME=$(basename "$plist")
         LABEL=$(basename "$plist" .plist)
         DST="$LAUNCH_AGENTS_DIR/$PLIST_NAME"
@@ -354,17 +389,13 @@ else
         # Unload if already loaded
         launchctl unload "$DST" 2>/dev/null || true
 
-        # Copy the template
+        # Copy and load
         cp "$plist" "$DST"
-
-        # Substitute the agent directory path in case the template has a different one
-        # Handles both legacy (sophie-ai) and current (maestro) path patterns
-        sed -i '' "s|/Users/[^<]*/sophie-ai|$AGENT_DIR|g; s|/Users/[^<]*/maestro|$AGENT_DIR|g" "$DST" 2>/dev/null || true
-
-        # Load
         launchctl load "$DST"
         ok "Loaded: $LABEL"
     done
+else
+    warn "No plist files found in $PLIST_DIR — skipping launchd setup"
 fi
 
 echo ""

package/scripts/slack-events-server.mjs

@@ -31,6 +31,16 @@ import { fileURLToPath } from "node:url";
 const __dirname = path.dirname(fileURLToPath(import.meta.url));
 const ROOT = path.resolve(__dirname, "..");
 
+// ── Singleton guard — prevent duplicate instances ────────────────────────────
+try {
+  process.env.AGENT_ROOT = process.env.AGENT_ROOT || ROOT;
+  const { acquireLock } = await import(path.join(process.env.HOME, "maestro/lib/singleton.js"));
+  if (!acquireLock("slack-events")) {
+    console.log("[INIT] Slack events server already running — exiting");
+    process.exit(0);
+  }
+} catch { /* maestro not available — skip guard */ }
+
 // ── Load environment ──────────────────────────────────────────────────────────
 
 const envPath = path.join(ROOT, ".env");