@hailer/mcp 1.1.16 → 1.1.17-beta.0

package/.claude/commands/help:agents.md

@@ -1,151 +1,182 @@
 ---
-description: Agent usage help for Hailer MCP
+description: Help for working with skills and general-purpose sub-agents
 ---
 
-# Agents Help
+# Skills & Roles Help
 
-Display agent usage instructions to the user.
+Display how to work with the skill-based model and general-purpose sub-agents.
 
 ## Output
 
 ```
 ╭─────────────────────────────────────────╮
-│          HAILER MCP - AGENTS            │
+│    HAILER MCP - SKILLS & WORKFLOWS      │
 ╰─────────────────────────────────────────╯
 
-Agents are AI specialists that handle specific tasks. The orchestrator
-(Claude) delegates work to them based on the task type.
+The new model: General-purpose sub-agents + skills. No named agents.
+Load the right skills for the domain, spawn a sub-agent with them.
 
 HOW IT WORKS:
 
   1. You ask Claude to do something
-  2. Claude identifies the right agent
-  3. Claude spawns the agent with your task
-  4. Agent does the work, returns JSON result
+  2. Claude picks the relevant skills for context
+  3. Claude spawns a general-purpose sub-agent with skill instructions
+  4. Sub-agent executes using domain knowledge from skills
   5. Claude interprets result and reports back
 
 ─────────────────────────────────────────────────────────────────────────
 
-AGENT RELATIONSHIPS (who calls who):
-
-  Kenji → Dmitri       Kenji gets IDs, Dmitri creates/updates
-  Kenji → Helga        Kenji gets structure, Helga modifies config
-  Kenji → Alejandro    Kenji gets field IDs, Alejandro creates functions
-  Kenji → Viktor       Kenji gets schema, Viktor creates insights
-  Kenji → Giuseppe     Kenji gets data structure, Giuseppe builds app
-  Marco → Giuseppe     Marco validates mockup, Giuseppe builds production
-  Ada ← (any failure)  Ada creates skills from repeated failures
-
-  Common chains:
-  • Add field:     Kenji → Helga → (push) → Kenji (verify)
-  • Create app:    Kenji → Viktor → Giuseppe → Tanya
-  • Activity CRUD: Kenji → Dmitri
+SKILL CATALOG:
+
+  Workspace & Config:
+    sdk-ws-config-skill        - Understanding workflows, fields, phases, type generation
+    sdk-function-fields        - Creating calculated fields
+    sdk-activity-patterns      - Creating/updating activities
+    sdk-insight-queries        - Writing insight queries
+    sdk-document-templates     - Creating PDF/CSV templates
+
+  App Development:
+    hailer-app-builder         - Building Hailer apps (React/Chakra)
+    hailer-design-system       - Theme, colors, icons, components, UI/UX patterns
+    hailer-apps-pictures       - Working with images in apps
+    publish-hailer-app         - Publishing to production
+    hailer-api-client          - Making REST API calls
+
+  Integrations:
+    hailer-monolith-automations - Webhook handlers, scheduled jobs, phase cascade bots
+    zapier-hailer-patterns      - Zapier integrations
+    integration-patterns        - General integration patterns
+    hailer-api-client           - Using HailerApiClient
+
+  Testing & Quality:
+    testing-patterns           - vitest/playwright patterns
+    lsp-setup                  - Code inspection tools
+    api-documentation-patterns - API endpoint documentation
+    tool-builder               - Building MCP tools
+
+  Error Handling:
+    tool-parameter-usage       - MCP validation errors
+    tool-response-verification - Tool failures
+    optional-parameters        - Optional param errors
+    json-only-output          - JSON formatting issues
 
 ─────────────────────────────────────────────────────────────────────────
 
-AGENT TOOL ACCESS:
+ROLE-BASED WORKFLOWS:
 
-  MCP Tools Only (restricted):
-    Kenji     - list_workflows, count_activities, list_activities
-    Dmitri    - create_activity, update_activity
-    Permissions - list_apps, add/remove_app_member, search_users
-    Yevgeni   - discussion tools (list, fetch, post, invite)
+  Data Operations:
+    • Data Reader       - Read workflows, fields, activities (LOCAL FIRST)
+    • Activity Writer   - Create/update activities
+    • Data Analyzer     - Query patterns, anomalies, analysis
+    • Access Controller - Manage app access
 
-  Code Tools (Bash, Read, Write, Edit):
-    Giuseppe  - App building (+scaffold_hailer_app)
-    Gunther   - MCP tool building
-    Helga     - Workflow config
-    Igor      - Activity movers
-    Ivan      - Monolith automations
-    Marco     - Mockups
-    Ingrid    - Document templates
+  Configuration:
+    • Workflow Config   - Manage workflows, fields, phases
+    • Function Fields   - Calculated fields + nameFunction
+    • SQL Insights      - SQL-like reports
+    • Template Designer - PDF/CSV document templates
 
-  Read-Only (Read, Glob, Grep):
-    Svetlana  - Code review
-    Bjorn     - Config audit
-    Tanya     - Test runner (+ Bash for test execution)
+  Development:
+    • App Builder       - Build Hailer apps (production)
+    • UI Designer       - Design specs (layout, components)
+    • Code Builder      - Build MCP tools, backends
+    • Activity Mover    - Phase cascade microservices
+    • Automation Builder - Webhooks, scheduled jobs
 
-  Light Edit (Read, Edit, Glob):
-    Simple Writer - Basic edits only (haiku model, fast)
-    Code Simplifier - Simplify code for clarity (sonnet model)
+  Quality:
+    • Code Reviewer     - Code review, security
+    • Test Runner       - Run tests, verify builds
+    • Code Inspector    - Find dead code, type errors
+    • Config Auditor    - Audit configuration
+    • Code Simplifier   - Refactor for clarity
 
-  Special:
-    Lars      - LSP only (code inspection)
-    Ada       - Read, Write, Edit, Glob (skill creation)
+  Meta:
+    • Skill Builder     - Create skills from patterns
+    • Documentation Generator - API endpoint docs
+    • Publisher         - Publish to marketplace
+    • Reviewer          - PR review
 
 ─────────────────────────────────────────────────────────────────────────
 
-AGENT CATEGORIES:
+COMMON WORKFLOWS:
 
-  Data Operations:
-    agent-kenji-data-reader    - Read workflows, fields, activities (LOCAL FIRST)
-    agent-dmitri-activity-crud - Create/update activities
-    agent-yevgeni-discussions  - Read/post discussion messages
-    agent-permissions-handler  - Manage app access
-    agent-simple-writer        - Basic code edits (ID swaps, string replacements)
+  Add a field:
+    Data Reader (get IDs) → Workflow Config (create field) → (push)
+    → Data Reader (verify)
 
-  Configuration:
-    agent-helga-workflow-config     - Manage workflows, fields, phases
-    agent-alejandro-function-fields - Calculated fields + name functions
-    agent-viktor-sql-insights       - SQL-like reports
-    agent-ingrid-doc-templates      - PDF/CSV document templates
+  Create an activity:
+    Data Reader (get schema) → Activity Writer (create)
 
-  Development:
-    agent-giuseppe-app-builder - Build Hailer apps (production)
-    agent-marco-mockup-builder - Build demo apps (validation)
-    agent-gunther-mcp-tools    - Build MCP tools
-    agent-igor-activity-mover  - Phase cascade microservices
-    agent-ivan-monolith        - Monolith automations
-    agent-zara-zapier          - Zapier integrations
+  Build an app:
+    Data Reader (discover schema) → UI Designer (design spec)
+    → App Builder (build) → Test Runner (verify)
 
-  Quality:
-    agent-svetlana-code-review - Code review (READ-ONLY)
-    agent-tanya-test-runner    - Run tests
-    agent-lars-code-inspector  - Find bugs, dead code (LSP)
-    agent-bjorn-config-audit   - Audit configuration
-    agent-code-simplifier      - Simplify code for clarity
+  Create a report:
+    Data Reader (get schema) → Function Fields (if needed)
+    → SQL Insights (build queries)
 
-  Meta:
-    agent-ada-skill-builder       - Create skills from failures
-    agent-builder-agent-creator   - Create new agents
-    agent-marcus-api-documenter   - Document API endpoints
-    agent-marketplace-publisher   - Publish plugins
-    agent-marketplace-reviewer    - Review plugin PRs
+  Review code:
+    Code Reviewer (find issues) → Code Fixer (fix) → Code Reviewer (verify)
 
 ─────────────────────────────────────────────────────────────────────────
 
-CRITICAL BOUNDARIES:
+HOW TO SPAWN SUB-AGENTS:
 
-  Kenji vs Dmitri:
-    Kenji = READ (schema, lists, counts)
-    Dmitri = WRITE (create, update)
-    Dmitri needs IDs from Kenji first!
+  With skills:
+    Task(prompt="Load <skill-name> for understanding the domain.
+    
+    Your mission: [detailed task description]")
 
-  Marco vs Giuseppe:
-    Marco = DEMO apps (non-functional, for validation)
-    Giuseppe = PRODUCTION apps (real data, functional)
-    Use Marco first to validate concept, then Giuseppe
+  Multiple skills:
+    Task(prompt="Load <skill-1> and <skill-2> skills.
+    
+    Your mission: [detailed task description]")
+
+  Example:
+    Task(prompt="Load sdk-ws-config-skill for workspace understanding.
+    
+    List all workflows and their fields for the Customer workflow.")
 
 ─────────────────────────────────────────────────────────────────────────
 
-EXAMPLE USAGE:
+DATA OPERATION RULES:
+
+  Read First: Always check workspace/ before API calls
+    - workflow/ directory has all structural data (IDs, field types, phases)
+    - API only needed for live activity data, counts, discussion messages
 
-  "Create a customer activity in the CRM workflow"
-  → Kenji (get IDs) → Dmitri (create activity)
+  Refresh Often: `npm run pull` updates workspace/ from Hailer
+    - After pushing new config, pull to get new IDs
+    - Between pipeline steps
+
+  ID Format: Field IDs, workflow IDs, phase IDs come from workspace/
+    - Never guess IDs - always read them from workspace/ files
+    - Always verify types match before using in code
+
+  Activity Updates: Use correct wrapper format
+    - Correct: `{type: "string", value: "x"}`
+    - Wrong: Raw value `"x"`
+
+─────────────────────────────────────────────────────────────────────────
 
-  "Build a dashboard app showing orders"
-  → Kenji (get schema) → Giuseppe (build app)
+SQUAD WORKFLOWS:
 
-  "Add a calculated total field"
-  → Kenji (get field IDs) → Alejandro (create function)
+  Pre-built multi-step orchestrations:
+    /app-squad         - Build apps end-to-end
+    /review-squad      - Code review + auto-fix
+    /config-squad      - Workflow config + functions + insights
+    /hotfix-squad      - Test → fix → security review
+    /debug-squad       - Parallel investigation
+    /crud-squad        - Schema discovery → CRUD → verify
+    /data-squad        - Build reports (discover → functions → insights)
 
-  "Review my code changes"
-  → Svetlana (code review)
+  Large-scale parallel:
+    /swarm <desc>      - Auto-select roles, split work across workers
 
 ─────────────────────────────────────────────────────────────────────────
 
 SEE ALSO:
-  /stats         - View agent usage statistics
-  /help plugins  - Install more agents
-  /help commands - All slash commands
+  /stats         - Task statistics
+  /help:skills   - Skill details
+  /help:commands - All commands
 ```

package/.claude/commands/help:commands.md

@@ -46,19 +46,19 @@ PLANNING
   /project-status        Sync DEVELOPMENT.md with PRD statuses
 
 SQUADS (multi-agent commands)
-  /review-squad [files]    Parallel+Loop: Svetlana + Lars + Tanya + Simple Writer
-  /cleanup-squad [files]   Parallel: Bjorn + Code Simplifier + Lars
-  /app-squad <desc>        Pipeline+Loop: Kenji → UI Designer → Giuseppe → Tanya (build verify)
-  /config-squad <desc>     Pipeline: Helga → Alejandro → Viktor
-  /crud-squad <desc>       Pipeline: Kenji → Dmitri → Kenji (verify)
-  /data-squad <desc>       Pipeline: Kenji → Alejandro → Viktor
-  /integration-squad <desc> Pipeline: Kenji → Ivan → Tanya
-  /doc-squad <desc>        Pipeline: Lars → Marcus
-  /hotfix-squad <desc>     Pipeline+Loop: Tanya → Simple Writer → Svetlana (max 3 iter)
-  /debug-squad <desc>      Parallel+Loop: Kenji + Viktor + Svetlana + Tanya (--debate for competing hypotheses)
-  /audit-squad             Parallel: Svetlana + Permissions + Gunther (security audit)
-  /onboard-squad <desc>    Pipeline+Loop: Helga → Alejandro → Giuseppe → Bjorn (bootstrap)
-  /janitor-squad           Parallel+Loop: Lars + Bjorn + Viktor → Simple Writer (cleanup)
+  /review-squad [files]    Parallel+Loop: Code Reviewer + LSP Inspector + Test Runner + Code Editor
+  /cleanup-squad [files]   Parallel: Config Auditor + Code Simplifier + LSP Inspector
+  /app-squad <desc>        Pipeline+Loop: Data Reader → UI Designer → App Builder → Test Runner (build verify)
+  /config-squad <desc>     Pipeline: Workflow Config → Function Fields → SQL Insights
+  /crud-squad <desc>       Pipeline: Data Reader → Activity Writer → Data Reader (verify)
+  /data-squad <desc>       Pipeline: Data Reader → Function Fields → SQL Insights
+  /integration-squad <desc> Pipeline: Data Reader → Monolith Automations → Test Runner
+  /doc-squad <desc>        Pipeline: LSP Inspector → API Documenter
+  /hotfix-squad <desc>     Pipeline+Loop: Test Runner → Code Editor → Code Reviewer (max 3 iter)
+  /debug-squad <desc>      Parallel+Loop: Data Reader + SQL Insights + Code Reviewer + Test Runner (--debate for competing hypotheses)
+  /audit-squad             Parallel: Code Reviewer + Permissions Auditor + Tool Security Auditor (security audit)
+  /onboard-squad <desc>    Pipeline+Loop: Workflow Config → Function Fields → App Builder → Config Auditor (bootstrap)
+  /janitor-squad           Parallel+Loop: LSP Inspector + Config Auditor + SQL Insights → Code Editor (cleanup)
   /swarm <desc>            Swarm: orchestrator picks agents, splits work, dispatches parallel workers
 
 SESSION
@@ -66,7 +66,7 @@ SESSION
   /save <message>    Save changes to git (local commit)
   /restore           Restore to a previous save point
   /handoff           Create session handoff for next session
-  /learn <cat> <desc> Capture learning and apply fix
+  /learn <cat> <desc> Capture learning and apply fix (cat: skill/X, pattern, bug, gotcha)
 
 ───────────────────────────────────────────
 Examples:
@@ -74,5 +74,5 @@ Examples:
   /autoplan "Add invoicing"     Quick planning for feature
   /prd "customer portal"        Create PRD for feature
   /save "Add customer form"     Local git commit
-  /learn agent/kenji "Check enums first"
+  /learn skill/data-reader "Check enums first"
 ```

package/.claude/commands/help:faq.md

@@ -20,41 +20,41 @@ A: Check two things:
       (the one with CLAUDE.md and .claude/ folder)
 
 Q: Why do I need to restart Claude Code after installing a plugin?
-A: Claude Code loads agent definitions at startup. New agents
-   won't be available until restart. Use 'claude -c' to keep context.
+A: Claude Code reloads configuration at startup. New skills and hooks
+   won't be active until restart. Use 'claude -c' to keep context.
 
 Q: What's the difference between /plugin install and /install-plugin?
 A: /plugin install - Claude's built-in plugin system (global)
    /install-plugin - Our local marketplace system (per-project)
 
-Q: Can I create my own agents?
-A: Yes! Add a markdown file to .claude/agents/ following the agent
-   structure. See existing agents for examples.
+Q: Can I create my own skills?
+A: Yes! Add a SKILL.md file to .claude/skills/<name>/ following the
+   skill structure. See existing skills for examples.
 
-Q: How do I publish my agent to the marketplace?
-A: Use /publish-plugin. It creates a PR that gets auto-reviewed.
+Q: How do I publish my skill or hook to the marketplace?
+A: Use /publish-plugin. It creates a PR that gets reviewed.
    See /help plugins for details.
 
-Q: Why does the orchestrator delegate instead of doing work directly?
-A: Delegation keeps specialized knowledge in focused agents,
-   reducing context size and improving accuracy.
+Q: Why does Claude spawn sub-agents instead of doing work directly?
+A: Sub-agents with focused skills produce better results for domain-
+   specific tasks by loading only the relevant context.
 
-Q: What happens if an agent fails?
-A: The orchestrator receives an error JSON and reports the failure.
+Q: What happens if a sub-agent fails?
+A: The orchestrator receives an error and reports the failure.
    It should identify root cause and fix it, never apply bandaids.
 
-Q: How do I know which agent will handle my request?
-A: Check the <agents> table in CLAUDE.md. The orchestrator matches
-   your request to the appropriate agent based on patterns.
+Q: How does Claude decide which skills to use?
+A: Check the skill catalog in CLAUDE.md. Skills are loaded based on
+   the task domain (workspace config, app building, testing, etc.).
 
 Q: Can I use MCP tools directly without agents?
 A: Yes! Tools like list_workflows, create_activity, etc. are
    available directly. Agents just provide structured workflows.
 
 Q: Where is configuration stored?
-A: - Agents: .claude/agents/
-   - Skills: .claude/skills/
+A: - Skills: .claude/skills/
    - Hooks: .claude/hooks/
+   - Commands: .claude/commands/
    - Settings: .claude/settings.json
    - Instructions: CLAUDE.md
 

package/.claude/commands/help:plugins.md

@@ -24,7 +24,7 @@ COMMANDS:
 
   /install-plugin <name>
     Install a plugin to .claude/ folder.
-    Example: /install-plugin tanya-test-runner
+    Example: /install-plugin my-custom-plugin
 
   /uninstall-plugin <name>
     Remove a plugin from .claude/ folder.

package/.claude/commands/help:skills.md

@@ -22,36 +22,29 @@ HOW SKILLS WORK:
   SubagentStart hook injects them automatically when the agent spawns.
 
   On-demand: The orchestrator tells an agent to load a skill via the
-  Skill tool. Only 6 agents have it: Giuseppe, Helga, Viktor,
-  Alejandro, Ingrid, Ada.
+  Skill tool. Load skills before spawning sub-agents or doing domain-specific work.
 
 ─────────────────────────────────────────────────────────────────────────
 
 SDK SKILLS (core patterns):
-  SDK-activity-patterns    - Field value formats, dates, users, links
-  SDK-document-templates   - PDF/CSV template structure + generation
-  SDK-function-fields      - Calculated fields in Hailer workflows
-  SDK-generate-skill       - TypeScript type generation from workspace
-  SDK-init-skill           - Initialize new Hailer SDK projects
-  SDK-insight-queries      - SQL query patterns for insights
-  SDK-ws-config-skill      - Workflow config: fields, phases, schemas
+  sdk-activity-patterns    - Field value formats, dates, users, links
+  sdk-document-templates   - PDF/CSV template structure + generation
+  sdk-function-fields      - Calculated fields in Hailer workflows
+  sdk-insight-queries      - SQL query patterns for insights, cross-workflow JOINs
+  sdk-ws-config-skill      - Workflow config: fields, phases, schemas, type generation, project setup
 
 HAILER PLATFORM SKILLS:
-  hailer-activity-mover    - Phase cascade microservice patterns
-  hailer-api-client        - @hailer/cli auth, requests, signals
+  hailer-api-client        - @hailer/cli auth, requests, signals, direct HTTP API endpoints
   hailer-app-builder       - Build apps with @hailer/app-sdk
   hailer-apps-pictures     - Fetch and display images from Hailer
-  hailer-design-system     - Chakra UI theme, colors, icons, components
-  hailer-monolith-automations - Webhooks, scheduled jobs in monolith
+  hailer-design-system     - Chakra UI theme, colors, icons, components, UI/UX patterns
+  hailer-monolith-automations - Webhooks, scheduled jobs in monolith, phase cascade bots
   hailer-permissions-system - Users, teams, access control
   hailer-project-protocol  - Full SDK workflow reference
-  hailer-rest-api          - Direct HTTP API endpoints
 
 INTEGRATION SKILLS:
   integration-patterns     - Activity movers, webhooks, SCIM, Kafka
   zapier-hailer-patterns   - Zapier triggers, actions, Zap configs
-  insight-join-patterns    - JOIN syntax for cross-workflow insights
-
 TOOL & AGENT SKILLS:
   agent-structure          - Template for creating new agents
   delegation-routing       - Full routing table + chaining patterns
@@ -66,23 +59,24 @@ QUALITY & FIX SKILLS (auto-loaded on errors):
   testing-patterns         - vitest, playwright, build verification
 
 REFERENCE SKILLS:
-  api-documentation-patterns - API doc standards for Marcus
+  api-documentation-patterns - API endpoint documentation standards
   chrome-mcp-reference     - Browser automation reference
-  frontend-design          - UI design patterns
   lsp-setup                - Language Server Protocol setup
   publish-hailer-app       - App publishing to production
 
 ─────────────────────────────────────────────────────────────────────────
 
-ON-DEMAND SKILL LOADING (tell the orchestrator):
+ON-DEMAND SKILL LOADING:
 
-  "Load hailer-apps-pictures for Giuseppe"
-  → Giuseppe gets image handling patterns
+  Tell the orchestrator which skill a sub-agent needs:
+  "Load hailer-apps-pictures for the app builder sub-agent"
+  → Sub-agent gets image handling patterns
 
-  "Viktor needs insight-join-patterns for this query"
-  → Viktor gets JOIN syntax for cross-workflow data
+  "Load sdk-insight-queries for this SQL query"
+  → Sub-agent gets insight patterns including JOIN syntax for cross-workflow data
 
-  Only works with: Giuseppe, Helga, Viktor, Alejandro, Ingrid, Ada
+  Skill content is loaded by the orchestrator and pasted directly
+  into the sub-agent prompt — agents never load skills themselves.
 
 ─────────────────────────────────────────────────────────────────────────
 

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

@@ -1,5 +1,5 @@
 ---
-description: Quick bug fix with Tanya, Simple Writer, and Svetlana
+description: Quick bug fix with test creation, code editing, and security review
 argument-hint: "bug description"
 allowed-tools: Task, Bash
 ---
@@ -7,21 +7,21 @@ allowed-tools: Task, Bash
 
 Sequential pipeline with iterative loop: Reproduce bug, apply fix, verify, review. Loops back if review fails.
 
-**Agents:**
-1. **Tanya** - Test runner (create failing test, verify fix)
-2. **Simple Writer** - Code editor (apply minimal fix)
-3. **Svetlana** - Code review (security audit of the fix)
+**Roles:**
+1. **Test Runner** - Test runner (create failing test, verify fix)
+2. **Code Editor** - Code editor (apply minimal fix)
+3. **Code Reviewer** - Code review (security audit of the fix)
 
 **Goal:** $ARGUMENTS
 
 ## Protocol
 
-### Step 1: Tanya (Reproduce Bug)
+### Step 1: Reproduce Bug
 
-Spawn Tanya to create a test that demonstrates the bug:
+Spawn a test runner to create a test that demonstrates the bug:
 
 ```
-Task(subagent_type="agent-tanya-test-runner", prompt="Create a test that reproduces this bug: $ARGUMENTS.\n\nThe test should:\n- Fail with the current code (red)\n- Clearly demonstrate the bug\n- Be minimal and focused\n\nDo NOT fix the bug yet. Just create the failing test and report the failure.")
+Task(prompt="Load testing-patterns skill for writing focused tests.\n\nCreate a test that reproduces this bug: $ARGUMENTS.\n\nThe test should:\n- Fail with the current code (red)\n- Clearly demonstrate the bug\n- Be minimal and focused\n\nDo NOT fix the bug yet. Just create the failing test and report the failure.")
 ```
 
 Wait for result. The test should be failing (RED state).
@@ -32,38 +32,38 @@ Track iteration count. Max **3 iterations** before escalating to user with remai
 
 **Set:** `iteration = 1`
 
-#### Step 2a: Simple Writer (Apply Fix)
+#### Step 2a: Apply Fix
 
-Spawn Simple Writer with accumulated context from all previous iterations:
+Spawn a code editor with accumulated context from all previous iterations:
 
 ```
-Task(subagent_type="agent-simple-writer", prompt="Fix the bug in: $ARGUMENTS.\n\nContext:\nTanya created a failing test that reproduces the bug:\n[PASTE TANYA'S TEST CODE AND FAILURE OUTPUT]\n\n[IF iteration > 1: Include ALL accumulated feedback:\n- Tanya's latest test results (pass/fail details)\n- Svetlana's review feedback (if review was reached in previous iteration)\n- What was already tried and why it didn't fully work\nThis prevents repeating previous mistakes.]\n\nMake the MINIMAL change needed to make the test pass (GREEN state). Do not refactor or improve surrounding code.")
+Task(prompt="Fix the bug in: $ARGUMENTS.\n\nContext:\nTest runner created a failing test that reproduces the bug:\n[PASTE TEST CODE AND FAILURE OUTPUT]\n\n[IF iteration > 1: Include ALL accumulated feedback:\n- Test runner's latest test results (pass/fail details)\n- Code Reviewer's feedback (if review was reached in previous iteration)\n- What was already tried and why it didn't fully work\nThis prevents repeating previous mistakes.]\n\nMake the MINIMAL change needed to make the test pass (GREEN state). Do not refactor or improve surrounding code.")
 ```
 
-#### Step 2b: Tanya (Verify Fix)
+#### Step 2b: Verify Fix
 
 Run the test to confirm the fix works:
 
 ```
-Task(subagent_type="agent-tanya-test-runner", prompt="Re-run the test for: $ARGUMENTS. Confirm it now passes with Simple Writer's fix. Also run any related tests to check for regressions.")
+Task(prompt="Load testing-patterns skill for test execution.\n\nRe-run the test for: $ARGUMENTS. Confirm it now passes with the code editor's fix. Also run any related tests to check for regressions.")
 ```
 
 If tests FAIL:
 - If `iteration < 3`: increment iteration, go back to **Step 2a** with the test failure output
 - If `iteration >= 3`: escalate to user (see Step 3)
 
-#### Step 2c: Svetlana (Security Review)
+#### Step 2c: Security Review
 
-Tests passed. Spawn Svetlana to audit the fix:
+Tests passed. Spawn a code reviewer to audit the fix:
 
 ```
-Task(subagent_type="agent-svetlana-code-review", prompt="Security review of the hotfix for: $ARGUMENTS.\n\nFix applied by Simple Writer:\n[PASTE SIMPLE WRITER'S CHANGES]\n\nIteration: [iteration] of 3\n\nCheck for:\n- Security vulnerabilities\n- Data validation issues\n- Authentication/authorization concerns\n- Edge cases that could be exploited\n\nReturn verdict: APPROVED or REQUEST_CHANGES with specific issues to fix.")
+Task(prompt="Security review of the hotfix for: $ARGUMENTS.\n\nFix applied by code editor:\n[PASTE CODE EDITOR'S CHANGES]\n\nIteration: [iteration] of 3\n\nCheck for:\n- Security vulnerabilities\n- Data validation issues\n- Authentication/authorization concerns\n- Edge cases that could be exploited\n\nReturn verdict: APPROVED or REQUEST_CHANGES with specific issues to fix.")
 ```
 
 **If APPROVED:** proceed to Step 3 (report).
 
 **If REQUEST_CHANGES:**
-- If `iteration < 3`: increment iteration, go back to **Step 2a** with Svetlana's feedback
+- If `iteration < 3`: increment iteration, go back to **Step 2a** with Code Reviewer's feedback
 - If `iteration >= 3`: escalate to user (see Step 3)
 
 ### Step 3: Report
@@ -75,18 +75,18 @@ Task(subagent_type="agent-svetlana-code-review", prompt="Security review of the
 - Iterations: [count] of 3 max
 - Final status: FIXED / ESCALATED
 
-### Tanya (Test)
+### Test Runner
 - Bug reproduced: YES
 - Test status before fix: FAILED
 - Test status after fix: PASSED / STILL FAILING
 - Regressions found: [yes/no]
 
-### Simple Writer (Fix)
+### Code Editor
 - Files modified: [list]
 - Lines changed: [count]
 - Approach: [brief description]
 
-### Svetlana (Security)
+### Code Reviewer
 - Verdict: APPROVED / REQUEST_CHANGES
 - Critical issues: [count]
 - Warnings: [count]
@@ -99,7 +99,7 @@ Task(subagent_type="agent-svetlana-code-review", prompt="Security review of the
 
 [If ESCALATED after 3 iterations:]
 - Manual intervention needed
-- Remaining issues: [list from Svetlana/Tanya]
+- Remaining issues: [list from security reviewer/test runner]
 - Attempted fixes: [summary of what was tried]
 ```
 
@@ -108,5 +108,5 @@ Task(subagent_type="agent-svetlana-code-review", prompt="Security review of the
 - RED -> GREEN -> REVIEW loop ensures quality
 - Fix must be minimal - no refactoring
 - Max 3 iterations prevents infinite loops
-- Each iteration passes previous feedback to Simple Writer so it doesn't repeat mistakes
+- Each iteration passes previous feedback to the code editor so it doesn't repeat mistakes
 - Security check is mandatory before reporting success