@hailer/mcp 1.1.16 → 1.1.17-beta.1

package/.claude/commands/app-squad.md

@@ -1,135 +1,131 @@
 ---
-description: Design and build a Hailer app with UI Designer and Giuseppe
+description: Build a Hailer app with hyper-parallel component teams
 argument-hint: "app description"
-allowed-tools: Task, Bash, Read
+allowed-tools: Task, Bash, Read, Skill
 ---
 # App Squad
 
-Sequential pipeline with data discovery, design, build, and test loop.
-
-**Agents:**
-1. **Kenji** - Discovers real workflow/insight schemas, field IDs, column names
-2. **UI Designer** - Creates design spec (layout, components, aesthetic direction)
-3. **Giuseppe** - Builds the app from the design spec + real schema data
-4. **Tanya** - Build verification and tests (loop trigger)
+Hyper-parallel: orchestrator does ALL prep, then spawns one agent per component with everything pre-loaded. Agents do ZERO discovery — just write code.
 
 **Goal:** $ARGUMENTS
 
 ## Protocol
 
-### Step 1: Gather Context
-
-Before spawning agents, determine:
-- Does `workspace/` exist? If yes, this is a Hailer project.
-- Does `apps/` directory exist? Create if needed.
-- What workflows/data will the app use?
-
-If context is unclear, use AskUserQuestion:
-- What data should the app display?
-- Authenticated or public app?
-- Any specific layout preferences?
+### Step 1: Full Prep (YOU do everything — fast)
 
-### Step 2: Data Discovery (Kenji)
+**Schema discovery (MCP calls, parallel):**
+- `list_workflows_minimal` → find relevant workflows
+- `list_workflow_phases` per workflow → phase IDs/names
+- `get_workflow_schema` per workflow → field IDs/types/labels
+- `list_insights` → existing insights
 
-**CRITICAL: Giuseppe MUST NOT guess IDs or column names.** Kenji looks them up first.
+**Scaffold:**
+- `scaffold_hailer_app` MCP tool (NEVER copy an existing app)
 
-Spawn Kenji to discover the actual schema data the app will need:
+**Read scaffold SDK files:**
+- `src/hailer/use-app.ts` — the Zustand store, understand the API
+- `src/hailer/use-hailer.tsx` — the raw hook (if use-app isn't available)
+- `src/main.tsx` — entry point (ChakraProvider + theme)
+- Check available icons: `ls src/hailer/theme/icons/`
 
-```
-Task(subagent_type="agent-kenji-data-reader", prompt='{"task":"app_data_discovery","description":"Look up all schema data needed for this app: $ARGUMENTS","gather":["workflow IDs and names","field IDs, labels, and types for each workflow","phase IDs and names","insight IDs and their column names (if the app uses insights)","any ActivityLink field targets"],"output":"Return a structured JSON with all IDs, field definitions, insight columns, and phase maps. This will be passed directly to the app builder."}')
-```
+**Load skills (YOU load, paste into prompts):**
+- Load `hailer-app-builder` skill via Skill tool
+- Load `hailer-design-system` skill via Skill tool
+- Save the content — you'll paste it into every agent prompt
 
-Wait for result. Save the **schema data** output - this is passed to both UI Designer and Giuseppe.
+**Read one existing working app** for reference:
+- Pick an app from `apps/` that works, read its App.tsx
+- Extract the SDK integration patterns (how it fetches, how it reads fields)
 
-### Step 3: Design (UI Designer)
+### Step 2: Define Shared Contract
 
-Spawn UI Designer with the schema data so it knows what real fields/columns exist:
+Write this contract — every agent gets the exact same copy:
 
 ```
-Task(subagent_type="agent-ui-designer", prompt="Design a Hailer app: $ARGUMENTS.\n\nAvailable data schema:\n[PASTE KENJI'S SCHEMA OUTPUT]\n\nOutput a design spec with: tone, signature element, layout structure, key components, and data flow. Reference actual field IDs and column names from the schema. Format as structured JSON that Giuseppe can consume.")
-```
+## SHARED CONTRACT
 
-Wait for result. Save the design spec output.
+### Constants
+[Paste all workflow IDs, field IDs, phase IDs from schema discovery]
 
-### Step 4: Build-Test Loop
+### SDK API (from scaffold)
+[Paste the actual use-app.ts store shape — what useApp() returns]
+[Paste how to fetch: hailer.activity.list(workflowId, phaseId, { limit: 500 })]
+[Paste how fields work: activity.fields?.[fieldId] with value wrappers]
 
-**Set:** `iteration = 1`
+### Helper Functions
+[getField, getNumField, formatValue, getRating — whatever the app needs]
 
-#### Step 4a: Giuseppe (Build)
+### Component Manifest
+[List every component: name, file path, props interface, what it renders]
 
-**Before spawning Giuseppe, enable builder mode:**
-```
-Bash: node .claude/hooks/app-edit-guard.cjs --agent-on
-```
+### Import Paths
+[Exact import paths for SDK: '../hailer/use-app', icons, theme, etc.]
 
-Spawn Giuseppe with BOTH the design spec AND the schema data:
+### Icon Paths
+[Available icons with exact import paths: '../hailer/theme/icons/HailerSearch']
 
-```
-Task(subagent_type="agent-giuseppe-app-builder", prompt="Build this Hailer app using the following design spec and schema data:\n\n## Design Spec\n[PASTE FULL DESIGN SPEC FROM STEP 3]\n\n## Schema Data (from Kenji - use these EXACT IDs)\nSchema data from Kenji: [PASTE KENJI'S SCHEMA OUTPUT FROM STEP 2 - Kenji already ran in Step 2 and returned all IDs. The orchestrator doesn't need to read workspace/ directly.]\n\nApp goal: $ARGUMENTS\n\n[IF iteration > 1: Previous build failed. Here are the errors to fix:\n[PASTE TANYA'S BUILD/TEST ERRORS]\nFix these specific issues while keeping the rest of the app intact.]\n\nIMPORTANT: Use the EXACT field IDs, workflow IDs, insight IDs, and column names from the schema data above. Do NOT guess or invent any IDs.\n\nFollow the design spec for layout, components, and aesthetic. Use @hailer/app-sdk with Chakra UI and Hailer Design System.")
-```
+### SDK Patterns (from existing working app)
+[Paste the patterns that WORK — how ready/inside/outside are handled]
+[CRITICAL: Apps must render even when outside Hailer — never block on `inside`]
 
-**After Giuseppe completes, disable builder mode:**
-```
-Bash: node .claude/hooks/app-edit-guard.cjs --agent-off
+### Skill Content
+[Paste hailer-app-builder skill content]
+[Paste hailer-design-system skill content]
 ```
 
-#### Step 4b: Tanya (Build Verification)
+### Step 3: Spawn ALL Agents in One Message
 
-Spawn Tanya to verify the build:
+Every agent gets the FULL shared contract. They do ZERO skill loading, ZERO file reading.
 
+Each agent prompt:
 ```
-Task(subagent_type="agent-tanya-test-runner", prompt="Verify the app build for: $ARGUMENTS.\n\nRun:\n1. TypeScript compilation (tsc --noEmit)\n2. Build (npm run build)\n3. Any existing tests (npm test if configured)\n\nReport: build pass/fail, type errors, test results.")
-```
+You are building ONE component of a Hailer app.
 
-**If build PASSES:** proceed to Step 5 (report).
+[PASTE FULL SHARED CONTRACT]
 
-**If build FAILS:**
-- Classify errors:
-  - **Code-fixable** (type errors, missing imports, wrong API usage, JSX issues): Giuseppe can handle these
-  - **Infrastructure** (missing dependency/package, wrong Node version, environment config, missing workspace data): escalate immediately to user
-- If only infrastructure errors: skip to Step 5 with clear explanation of what the user needs to fix
-- If code-fixable errors AND `iteration < 3`: increment iteration, go back to **Step 4a** with Tanya's error output
-- If `iteration >= 3`: escalate to user with the remaining errors (see Step 5)
-
-### Step 5: Report
+## Your Mission: [COMPONENT NAME]
+[What to build, what props it takes, what it renders]
 
-```markdown
-## App Squad Complete
+Return ONLY the complete TypeScript/React code. No file operations, no skill loading, no discovery.
+```
 
-### Loop Summary
-- Build iterations: [count] of 3 max
-- Final build status: PASS / FAIL (escalated)
+Typical team:
+| Agent | Builds | Model |
+|-------|--------|-------|
+| Shell | App.tsx — nav, state, data fetching, renders children | sonnet |
+| Overview | Dashboard — stat cards, summaries, charts | sonnet |
+| List View | Table — filters, sorting, row click | sonnet |
+| Detail | Modal content — full record view | sonnet |
+| (per extra workflow) | Additional list+detail | sonnet |
 
-### Design (UI Designer)
-- Tone: [from spec]
-- Signature element: [from spec]
-- Components: [list]
+### Step 4: Assemble + Verify (YOU)
 
-### Build (Giuseppe)
-- App path: [path]
-- Build status: Pass/Fail
-- Files created: [list]
-- [If multiple iterations: summary of what was fixed each round]
+1. Write each component to its file
+2. Delete scaffold demo components (ChartDemo, ActivityTable, etc.)
+3. Fix integration issues (import paths, prop mismatches)
+4. `npx tsc --noEmit` → fix any errors
+5. `npx vite build` → verify
+6. If < 5 errors, fix directly. If major, re-spawn failing agent with error + context.
 
-### Verification (Tanya)
-- TypeScript: Pass/Fail
-- Build: Pass/Fail
-- Tests: X passed, X failed
+### Step 5: Report
 
-[If ESCALATED:]
-### Remaining Build Errors
-[List errors Giuseppe couldn't resolve in 3 attempts]
-- Suggested manual fixes: [hints based on error types]
+```markdown
+## App Built: [name]
+- Path: apps/[name]/
+- Components: [N] built in parallel
+- Build: PASS
+- TypeScript: 0 errors
 
 ### Next Steps
-- Run `npm run dev` to test locally
-- Test inside Hailer iframe
+- `cd apps/[name] && npm run dev`
+- Open in Hailer iframe to test with live data
 ```
 
-## Notes
+## Rules
 
-- Giuseppe defaults to local dev (localhost:3000). Publishing only when user explicitly asks (loads publish-hailer-app skill)
-- **Kenji runs FIRST** to discover all real IDs - Giuseppe must NEVER guess workflow IDs, field IDs, insight IDs, or column names
-- If the app needs an insight for public data, mention it in the goal - Kenji will look up existing insight columns
-- Build verification catches type errors and compilation issues before the user tries to run
-- Each iteration gives Giuseppe the specific errors to fix, avoiding repeated mistakes
+- NEVER copy existing apps — scaffold fresh
+- NEVER let agents load skills — you pre-load and paste
+- NEVER let agents read files — you read and paste
+- Apps must work when opened outside Hailer (show empty state, not error)
+- Include the ACTUAL SDK code in the contract, not a summary
+- Agents return code as text — you write the files

package/.claude/commands/audit-squad.md

@@ -1,5 +1,5 @@
 ---
-description: Run parallel security and permissions audit with Svetlana, Permissions Handler, and Gunther
+description: Run parallel security and permissions audit
 argument-hint: [files, app name, or blank for full audit]
 allowed-tools: Task, Bash
 ---
@@ -8,10 +8,10 @@ allowed-tools: Task, Bash
 
 Parallel security and permissions audit: code hardening, access control verification, and MCP tool validation.
 
-**Agents:**
-- **Svetlana** - Code review (hardcoded secrets, injection vulnerabilities, insecure patterns, OWASP top 10)
-- **Permissions Handler** - Access control audit (effective permissions, team access levels, permission matrix)
-- **Gunther** - MCP tools security (input validation, data exposure, security best practices)
+**Roles:**
+- **Code Reviewer** - Code review (hardcoded secrets, injection vulnerabilities, insecure patterns, OWASP top 10)
+- **Permissions Auditor** - Access control audit (effective permissions, team access levels, permission matrix)
+- **Tool Security Auditor** - MCP tools security (input validation, data exposure, security best practices)
 
 **Target:** $ARGUMENTS (if blank, use full project scope)
 
@@ -29,11 +29,11 @@ Otherwise, scope is the entire project (workspace/ + apps/ + integrations/).
 
 If `$ARGUMENTS` contains `--code-only`:
 - Remove flag from target
-- Skip Permissions Handler and Gunther in Step 2
+- Skip Permissions Auditor and Tool Security Auditor in Step 2
 
 If `$ARGUMENTS` contains `--permissions-only`:
 - Remove flag from target
-- Skip Svetlana and Gunther in Step 2
+- Skip Code Reviewer and Tool Security Auditor in Step 2
 
 If `$ARGUMENTS` contains `--bg`:
 - Launch all agents in background mode
@@ -42,19 +42,19 @@ If `$ARGUMENTS` contains `--bg`:
 
 Spawn all applicable agents simultaneously using multiple Task tool calls in a single message:
 
-**Svetlana:**
+**Code Reviewer:**
 ```
-Task(subagent_type="agent-svetlana-code-review", prompt="Security audit of these files: [TARGET]. Focus on: hardcoded secrets, API keys, credentials, injection vulnerabilities (SQL/XSS/Command), insecure crypto usage, missing input validation, OWASP Top 10 issues, unsafe deserialization, missing authentication/authorization checks. Return verdict (PASS/FAIL), critical count, and detailed findings per file.")
+Task(prompt="Security audit of these files: [TARGET]. Focus on: hardcoded secrets, API keys, credentials, injection vulnerabilities (SQL/XSS/Command), insecure crypto usage, missing input validation, OWASP Top 10 issues, unsafe deserialization, missing authentication/authorization checks. Return verdict (PASS/FAIL), critical count, and detailed findings per file.")
 ```
 
-**Permissions Handler:**
+**Permissions Auditor:**
 ```
-Task(subagent_type="agent-permissions-handler", prompt="Audit access control for the entire project. Map effective permissions: who has access to which apps, which teams have what access levels, which users are admins, workspace-wide versus app-specific permissions. Produce a permission matrix showing [User/Team] → [App] → [Access Level]. Flag any excessive or unclear permissions.")
+Task(prompt="Load hailer-permissions-system skill for understanding the permissions model.\n\nAudit access control for the entire project. Map effective permissions: who has access to which apps, which teams have what access levels, which users are admins, workspace-wide versus app-specific permissions. Produce a permission matrix showing [User/Team] → [App] → [Access Level]. Flag any excessive or unclear permissions.")
 ```
 
-**Gunther:**
+**Tool Security Auditor:**
 ```
-Task(subagent_type="agent-gunther-mcp-tools", prompt="Security audit of custom MCP tools (if any exist in src/mcp/tools/). Verify: input validation with Zod schemas, no unintended data exposure, proper error handling, rate limiting awareness, secure defaults. Report security posture per tool. If no custom tools exist, report that.")
+Task(prompt="Load tool-builder skill for understanding MCP tool patterns.\n\nSecurity audit of custom MCP tools (if any exist in src/mcp/tools/). Verify: input validation with Zod schemas, no unintended data exposure, proper error handling, rate limiting awareness, secure defaults. Report security posture per tool. If no custom tools exist, report that.")
 ```
 
 ### Step 3: Categorize and Aggregate Results
@@ -94,14 +94,14 @@ Collect results from all agents. Categorize findings into three tiers:
 - Warnings: X
 - Info items: X
 
-### Svetlana (Code Security Review)
+### Code Reviewer
 **Verdict:** PASS / FAIL / WARNINGS
 - Critical: X [list]
 - Warnings: X [list]
 - Info: X [list]
 - Files affected: [grouped summary]
 
-### Permissions Handler (Access Control)
+### Permissions Auditor
 **Matrix Status:** [OK / EXCESSIVE / UNCLEAR]
 - Total apps: X
 - Total teams: X
@@ -109,7 +109,7 @@ Collect results from all agents. Categorize findings into three tiers:
 - Flagged permissions: [list]
 - [Permission matrix if findings exist]
 
-### Gunther (MCP Tools Security)
+### Tool Security Auditor
 **Status:** [No tools / PASS / WARNINGS / CRITICAL]
 [If tools exist:]
 - Tools audited: X
@@ -152,7 +152,7 @@ If `--bg` is present, launch all agents with `run_in_background: true` and tell
 ## Notes
 
 - Default scope is full project if no arguments provided
-- Svetlana focuses on secrets and injection attacks; general code quality is separate (/review-squad)
-- Permissions Handler is organization-wide - includes team and app-level settings
-- Gunther only validates if custom MCP tools exist in the project
+- Code Reviewer focuses on secrets and injection attacks; general code quality is separate (/review-squad)
+- Permissions Auditor is organization-wide - includes team and app-level settings
+- Tool Security Auditor only validates if custom MCP tools exist in the project
 - Critical findings should block deployment; warnings should be tracked for next sprint

package/.claude/commands/autoplan.md

@@ -38,7 +38,7 @@ Create a complete project plan: workspace structure, DEVELOPMENT.md (big picture
    ls docs/prd-*.md 2>/dev/null  # List existing PRDs
    ```
 
-   Use Kenji agent to read:
+   Use Data Reader to check:
    - Existing workflows and their fields/phases
    - Existing insights
    - Existing apps and their purpose
@@ -352,7 +352,7 @@ project/
 1. [ ] Add workflow via SDK
 2. [ ] Define fields in fields.ts
 3. [ ] Define phases in phases.ts
-4. [ ] Push and pull (get IDs) - Helga auto-spawns Alejandro for nameFunction + function fields (if any)
+4. [ ] Push and pull (get IDs) - Workflow Config auto-spawns Function Fields for nameFunction + function fields (if any)
 5. [ ] Verify in Hailer
 
 ---
@@ -453,7 +453,7 @@ project/
 ---
 
 ## Implementation Steps
-1. [ ] Create insight via Viktor agent
+1. [ ] Create insight via SQL Insights sub-agent
 2. [ ] Test query results
 3. [ ] Set public flag (if needed for public app)
 

package/.claude/commands/cleanup-squad.md

@@ -1,5 +1,5 @@
 ---
-description: Clean up codebase with Bjorn, Code Simplifier, and Lars
+description: Clean up codebase with config audit, code simplification, and dead code detection
 argument-hint: [files, directory, or blank for recent changes]
 allowed-tools: Task, Bash
 ---
@@ -7,10 +7,10 @@ allowed-tools: Task, Bash
 
 Run parallel codebase cleanup using three agents simultaneously.
 
-**Agents:**
-- **Bjorn** - Configuration audit (verify CLAUDE.md, hooks, workspace structure)
+**Roles:**
+- **Config Auditor** - Configuration audit (verify CLAUDE.md, hooks, workspace structure)
 - **Code Simplifier** - Refactor (improve code clarity and maintainability)
-- **Lars** - Dead code detection (find unused imports, dead code, type errors)
+- **Dead Code Inspector** - Dead code detection (find unused imports, dead code, type errors)
 
 **Target:** $ARGUMENTS (if blank, use recent git changes)
 
@@ -26,29 +26,29 @@ Otherwise, use the changed files list above as the target.
 
 If `$ARGUMENTS` contains `--skip-config`:
 - Remove flag from target
-- Skip Bjorn in Step 2
+- Skip Config Auditor in Step 2
 
 If `$ARGUMENTS` contains `--skip-dead-code`:
 - Remove flag from target
-- Skip Lars in Step 2
+- Skip Dead Code Inspector in Step 2
 
 ### Step 2: Launch Agents in Parallel
 
 Spawn all agents simultaneously using multiple Task tool calls in a single message:
 
-**Bjorn:**
+**Config Auditor:**
 ```
-Task(subagent_type="agent-bjorn-config-audit", prompt="Audit codebase configuration for: [TARGET]. Check:\n- CLAUDE.md accuracy and completeness\n- Hook configurations\n- Workspace structure\n- Agent definitions\n\nReturn list of issues found with severity levels.")
+Task(prompt="Audit codebase configuration for: [TARGET]. Check:\n- CLAUDE.md accuracy and completeness\n- Hook configurations\n- Workspace structure\n- Agent definitions\n\nReturn list of issues found with severity levels.")
 ```
 
 **Code Simplifier:**
 ```
-Task(subagent_type="agent-code-simplifier", prompt="Refactor these files for clarity and maintainability: [TARGET]. Focus on:\n- Variable naming\n- Function complexity\n- Comment clarity\n- Code organization\n\nReturn refactoring suggestions with before/after examples.")
+Task(prompt="Refactor these files for clarity and maintainability: [TARGET]. Focus on:\n- Variable naming\n- Function complexity\n- Comment clarity\n- Code organization\n\nReturn refactoring suggestions with before/after examples.")
 ```
 
-**Lars:**
+**Dead Code Inspector:**
 ```
-Task(subagent_type="agent-lars-code-inspector", prompt="Inspect these files for dead code: [TARGET]. Find:\n- Unused imports\n- Unreachable code\n- Unused variables\n- Type errors\n\nUse LSP if available. Return detailed list grouped by file.")
+Task(prompt="Load lsp-setup skill for code inspection.\n\nInspect these files for dead code: [TARGET]. Find:\n- Unused imports\n- Unreachable code\n- Unused variables\n- Type errors\n\nUse LSP if available. Return detailed list grouped by file.")
 ```
 
 ### Step 3: Aggregate Results
@@ -58,18 +58,18 @@ Compile a unified cleanup report:
 ```markdown
 ## Cleanup Squad Report
 
-### Bjorn (Config Audit)
+### Config Auditor
 - Issues found: X
 - Critical: X
 - Warnings: X
 - [Issues grouped by category]
 
-### Code Simplifier (Refactoring)
+### Code Simplifier
 - Files analyzed: X
 - Refactoring suggestions: X
 - [Suggestions grouped by file]
 
-### Lars (Dead Code)
+### Dead Code Inspector
 - Unused imports: X
 - Dead code blocks: X
 - Type errors: X
@@ -91,8 +91,8 @@ If any agent fails or times out, report partial results from successful agents,
 
 | Flag | Effect |
 |------|--------|
-| `--skip-config` | Skip Bjorn (faster, no config validation) |
-| `--skip-dead-code` | Skip Lars (when LSP not configured) |
+| `--skip-config` | Skip Config Auditor (faster, no config validation) |
+| `--skip-dead-code` | Skip Dead Code Inspector (when LSP not configured) |
 | `--bg` | Run all agents in background mode |
 
 If `--bg` is present, launch all agents with `run_in_background: true` and tell the user they'll be notified when complete.

package/.claude/commands/config-squad.md

@@ -1,5 +1,5 @@
 ---
-description: Set up workflow config with Helga, Alejandro, and Viktor
+description: Set up workflow config with infrastructure, functions, and insights
 argument-hint: "workflow/config description"
 allowed-tools: Task, Bash, Read
 ---
@@ -7,10 +7,10 @@ allowed-tools: Task, Bash, Read
 
 Sequential pipeline: Create workflow infrastructure, then calculated fields, then insights.
 
-**Agents:**
-1. **Helga** - Workflow config (fields, phases, teams, groups)
-2. **Alejandro** - Function fields and nameFunction
-3. **Viktor** - SQL insights for reporting
+**Roles:**
+1. **Workflow Config** - Workflow configuration (fields, phases, teams, groups)
+2. **Function Fields** - Calculated fields and nameFunction
+3. **SQL Insights** - SQL insights for reporting
 
 **Goal:** $ARGUMENTS
 
@@ -20,11 +20,11 @@ Sequential pipeline: Create workflow infrastructure, then calculated fields, the
 
 Parse `$ARGUMENTS` to determine what's needed:
 
-| Keyword | Agents to Use |
-|---------|---------------|
-| "workflow", "fields", "phases" | Helga (+ Alejandro if function fields mentioned) |
-| "insight", "report", "dashboard" | Viktor (may need Kenji first for schema) |
-| "function", "calculated", "nameFunction" | Alejandro only |
+| Keyword | Steps to Run |
+|---------|-------------|
+| "workflow", "fields", "phases" | Workflow Config (+ Function Fields if calculated fields mentioned) |
+| "insight", "report", "dashboard" | SQL Insights (may need schema discovery first) |
+| "function", "calculated", "nameFunction" | Function Fields only |
 | General description | All three in sequence |
 
 If scope is unclear, use AskUserQuestion:
@@ -32,44 +32,44 @@ If scope is unclear, use AskUserQuestion:
 - Do you need calculated fields?
 - Do you need reports/insights?
 
-If `$ARGUMENTS` contains `--skip-insights`: skip Viktor.
-If `$ARGUMENTS` contains `--skip-functions`: skip Alejandro.
+If `$ARGUMENTS` contains `--skip-insights`: skip SQL Insights step.
+If `$ARGUMENTS` contains `--skip-functions`: skip Function Fields step.
 
-### Step 2: Helga (Workflow Config)
+### Step 2: Workflow Config
 
-Spawn Helga:
+Spawn a workflow config agent:
 
 ```
-Task(subagent_type="agent-helga-workflow-config", prompt="$ARGUMENTS")
+Task(prompt="Load sdk-ws-config-skill for understanding workspace configuration.\n\n$ARGUMENTS")
 ```
 
-Wait for result. If Helga returns `"status": "ready_to_push"`:
-- Run the push commands she provides (e.g., `npm run fields-push:force`)
+Wait for result. If the agent returns `"status": "ready_to_push"`:
+- Run the push commands it provides (e.g., `npm run fields-push:force`)
 - Then run `npm run pull` to refresh local workspace with new IDs
 
-**Important:** Helga ALWAYS spawns Alejandro for nameFunction after creating a workflow. Check Helga's result - if she reports Alejandro created the nameFunction and all needed function fields, skip Step 3. Only proceed to Step 3 if additional function fields are needed beyond what Helga+Alejandro already created.
+**Important:** The workflow config agent ALWAYS spawns a function fields agent for nameFunction after creating a workflow. Check the result - if it reports the function fields agent created the nameFunction and all needed function fields, skip Step 3. Only proceed to Step 3 if additional function fields are needed beyond what was already created.
 
-### Step 3: Alejandro (Function Fields)
+### Step 3: Function Fields
 
-Only if function fields or nameFunction are needed and weren't handled by Helga.
+Only if function fields or nameFunction are needed and weren't handled in Step 2.
 
-Spawn Alejandro:
+Spawn a function fields agent:
 
 ```
-Task(subagent_type="agent-alejandro-function-fields", prompt="Create function fields for: $ARGUMENTS. Helga created these workflows: [SUMMARIZE HELGA'S RESULT - workflow names and any IDs she returned]. Read workspace/ to discover field IDs and types. New fields created by Helga: [LIST FROM HELGA'S RESULT IF ANY].")
+Task(prompt="Load sdk-function-fields and sdk-ws-config-skill skills for creating calculated fields.\n\nCreate function fields for: $ARGUMENTS. Workflow config agent created these workflows: [SUMMARIZE STEP 2 RESULT - workflow names and any IDs returned]. Read workspace/ to discover field IDs and types. New fields created in Step 2: [LIST FROM STEP 2 RESULT IF ANY].")
 ```
 
 Wait for result. If `"status": "ready_to_push"`:
 - Run the push commands
 
-### Step 4: Viktor (Insights)
+### Step 4: SQL Insights
 
 Only if reporting/insights are needed.
 
-Spawn Viktor:
+Spawn an SQL insights agent:
 
 ```
-Task(subagent_type="agent-viktor-sql-insights", prompt="Create insights for: $ARGUMENTS. Read workspace/ to discover workflow IDs and field IDs for SQL queries. Helga created: [SUMMARIZE HELGA'S RESULT].")
+Task(prompt="Load sdk-insight-queries and sdk-ws-config-skill skills for building insights.\n\nCreate insights for: $ARGUMENTS. Read workspace/ to discover workflow IDs and field IDs for SQL queries. Workflow config agent created: [SUMMARIZE STEP 2 RESULT].")
 ```
 
 Wait for result. If `"status": "ready_to_push"`:
@@ -80,18 +80,18 @@ Wait for result. If `"status": "ready_to_push"`:
 ```markdown
 ## Config Squad Complete
 
-### Helga (Workflow Config)
+### Workflow Config
 - Workflows: [created/modified]
 - Fields: [count]
 - Phases: [count]
 - Commands run: [list]
 
-### Alejandro (Function Fields)
+### Function Fields
 - Function fields: [list with formulas]
 - Name function: [pattern]
 - Skipped: [reason if skipped]
 
-### Viktor (Insights)
+### SQL Insights
 - Insights: [list with descriptions]
 - Skipped: [reason if skipped]
 
@@ -102,5 +102,5 @@ Run `npm run pull` to ensure workspace/ is up to date.
 ## Notes
 
 - Each agent in the pipeline needs IDs from the previous step. Always `npm run pull` between steps.
-- Helga auto-spawns Alejandro for nameFunction - check her output before spawning Alejandro again.
-- Viktor needs real field IDs for SQL queries - never let him guess.
+- Workflow config auto-spawns function fields agent for nameFunction - check the output before spawning separately.
+- SQL insights agent needs real field IDs for SQL queries - never let it guess.