bmad-method-test-architecture-enterprise 1.7.0 → 1.7.2

package/CHANGELOG.md

@@ -212,16 +212,6 @@ All workflows implement the **trivariate step pattern** (Create/Edit/Validate):
 - Agent schema validation for module independence
 - Pre-commit hook compatibility with documentation build process
 
-### Migration Guide
-
-For users migrating from BMM-embedded TEA, see [`docs/MIGRATION.md`](docs/MIGRATION.md) for:
-
-- Command namespace updates
-- Installation instructions
-- Configuration changes
-- Path reference updates
-- Troubleshooting common issues
-
 ### Documentation
 
 - Website: [test-architect.bmad-method.org](https://test-architect.bmad-method.org) (upcoming)
@@ -249,5 +239,3 @@ For users migrating from BMM-embedded TEA, see [`docs/MIGRATION.md`](docs/MIGRAT
   - Complete documentation suite
 
 ---
-
-_For detailed migration instructions, see [docs/MIGRATION.md](docs/MIGRATION.md)_

package/README.md

@@ -29,7 +29,7 @@ Each workflow directory contains these files, and each has a specific job:
 
 | File              | What it does                                                                                                        | When it loads                                                             |
 | ----------------- | ------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------- |
-| `tea.agent.yaml`  | Expert persona — identity, principles, critical actions, menu of triggers                                           | First — always in context                                                 |
+| `SKILL.md`        | Expert persona — identity, principles, critical actions, capabilities table                                         | First — always in context                                                 |
 | `workflow.yaml`   | Machine-readable metadata — config variables, required tools, tags                                                  | Second — resolves `{project-root}`, `{config_source}`, `{test_artifacts}` |
 | `workflow.md`     | Human-readable entry point — goals, mode menu (Create/Edit/Validate), routes to first step                          | Second — presents mode choice                                             |
 | `instructions.md` | Workflow-specific rules and context (optional, supplements workflow.md)                                             | On demand                                                                 |
@@ -54,8 +54,8 @@ flowchart LR
 
 ### How It Works at Runtime
 
-1. **Trigger** — Direct commands are `/bmad:tea:automate` (Claude/Cursor/Windsurf) and `$bmad-tea-testarch-automate` (Codex). `TA` is an agent-menu trigger available only after TEA is activated; the menu in `tea.agent.yaml` maps `TA` to `automate/workflow.yaml`.
-2. **Agent loads** — `tea.agent.yaml` injects the persona (identity, principles, critical actions) into the context window.
+1. **Trigger** — Direct commands are `/bmad:tea:automate` (Claude/Cursor/Windsurf) and `$bmad-tea-testarch-automate` (Codex). Load the conversational TEA menu with `$bmad-tea` in Codex. `TA` is an agent-menu trigger available only after TEA is activated; the capabilities table in `SKILL.md` maps `TA` to the `bmad-testarch-automate` skill.
+2. **Agent loads** — `SKILL.md` injects the persona (identity, principles, critical actions) into the context window.
 3. **Workflow loads** — `workflow.yaml` resolves config variables and `workflow.md` presents the mode menu (Create / Edit / Validate), then routes to the first step file.
 4. **Step-by-step execution** — Only the current step file is in context (just-in-time loading). Each step explicitly names the next one (`nextStepFile: './step-02-...'`). The LLM reads, executes, saves output, then loads the next step. No future steps are ever preloaded.
 5. **Knowledge injection** — Step-01 reads `tea-index.csv` and selectively loads fragments by **tier** (core = always, extended = on-demand, specialized = only when relevant) and **config flags** (e.g., `tea_use_pactjs_utils`). This is deliberate context engineering: a backend project loads ~1,800 lines of fragments; a fullstack project loads ~4,500 lines. Conditional loading cuts context usage by 40-50%.
@@ -85,7 +85,7 @@ The key insight is that there is **no external runtime engine** — the LLM _is_
 
 ```text
 .claude/commands/                         # Generated by installer
-├── bmad-agent-tea-tea.md                 # /tea → loads agent persona + menu
+├── bmad-tea.md                           # /tea → loads agent persona + menu
 ├── bmad-tea-testarch-automate.md         # /automate → loads workflow.xml + workflow.yaml
 ├── bmad-tea-testarch-test-design.md      # /test-design → ...
 ├── bmad-bmm-create-prd.md               # /create-prd → BMM workflow
@@ -105,19 +105,20 @@ npx bmad-method install
 
 ### Tool-specific invocation
 
-| Tool                            | Invocation style                | Example                       |
-| ------------------------------- | ------------------------------- | ----------------------------- |
-| Claude Code / Cursor / Windsurf | Slash command                   | `/bmad:tea:automate`          |
-| Codex                           | `$` skill from `.agents/skills` | `$bmad-tea-testarch-automate` |
+| Tool                            | Invocation style                | Example                                      |
+| ------------------------------- | ------------------------------- | -------------------------------------------- |
+| Claude Code / Cursor / Windsurf | Slash command                   | `/bmad:tea:automate`                         |
+| Codex                           | `$` skill from `.agents/skills` | `$bmad-tea` or `$bmad-tea-testarch-automate` |
 
 ## Quickstart
 
 1. Install TEA (above)
-2. Run one of the core workflows:
+2. Load the TEA menu with `$bmad-tea` if you want a conversational entrypoint.
+3. Run one of the core workflows:
    - `TD` / `/bmad:tea:test-design` / `$bmad-tea-testarch-test-design` — test design and risk assessment
    - `AT` / `/bmad:tea:atdd` / `$bmad-tea-testarch-atdd` — failing acceptance tests first (TDD red phase)
    - `TA` / `/bmad:tea:automate` / `$bmad-tea-testarch-automate` — expand automation coverage
-3. Or use in party mode: `/party` to include TEA with other agents
+4. Or use in party mode: `/party` to include TEA with other agents
 
 ## Engagement Models
 
@@ -146,8 +147,8 @@ TEA variables are defined in `src/module.yaml` and prompted during install:
 
 - `test_artifacts` — base output folder for test artifacts
 - `tea_use_playwright_utils` — enable Playwright Utils integration (boolean)
-- `tea_use_pactjs_utils` — enable Pact.js Utils integration for contract testing (boolean)
-- `tea_pact_mcp` — SmartBear MCP for PactFlow/Broker interaction: mcp, none (string)
+- `tea_use_pactjs_utils` — enable Pact.js Utils integration for contract testing when your project explicitly uses Pact (boolean)
+- `tea_pact_mcp` — SmartBear MCP for PactFlow/Broker interaction when broker integration is needed: mcp, none (string)
 - `tea_browser_automation` — browser automation mode: auto, cli, mcp, none (string)
 - `test_framework` — detected or configured test framework (Playwright, Cypress, Jest, Vitest, pytest, JUnit, Go test, dotnet test, RSpec)
 - `test_stack_type` — detected or configured stack type (frontend, backend, fullstack)
@@ -170,7 +171,7 @@ Workflows load only the fragments required for the current task to stay focused
 src/
 ├── module.yaml
 ├── agents/
-│   └── tea.agent.yaml
+│   └── bmad-tea/              # Native skill: SKILL.md + bmad-skill-manifest.yaml
 ├── workflows/
 │   └── testarch/
 │       ├── bmad-teach-me-testing/
@@ -187,6 +188,16 @@ src/
     └── knowledge/
 ```
 
+## Extending TEA
+
+Custom workflows are still compatible with TEA, but they are no longer implicitly absorbed into TEA core. The supported path is:
+
+1. Package the workflow as custom content or a custom module.
+2. Attach it to `bmad-tea` using the agent customization flow.
+3. Reinstall/update BMAD so the new menu item and workflow are registered.
+
+See [Extend TEA with Custom Workflows](docs/how-to/customization/extend-tea-with-custom-workflows.md) and the BMAD customization guide at [`BMAD-METHOD/docs/how-to/customize-bmad.md`](https://github.com/bmad-code-org/BMAD-METHOD/blob/main/docs/how-to/customize-bmad.md).
+
 ## Contributing
 
 See `CONTRIBUTING.md` for guidelines.

package/docs/explanation/tea-overview.md

@@ -343,7 +343,7 @@ Production-ready fixtures and utilities that enhance TEA workflows.
 Production-ready contract testing utilities that reduce raw Pact.js boilerplate and standardize provider verification patterns.
 
 - Install: `npm install -D @seontechnologies/pactjs-utils @pact-foundation/pact`
-- Config: `tea_use_pactjs_utils: true` (default is `true`)
+- Config: `tea_use_pactjs_utils: true` (default is `false`, opt in only when you want Pact-aware workflows)
 - Impacts: `framework`, `atdd`, `automate`, `test-design`, `test-review`, `ci`
 - Utilities include: createProviderState, toJsonMap, setJsonBody, setJsonContent, buildVerifierOptions, buildMessageVerifierOptions, createRequestFilter, noOpRequestFilter, handlePactBrokerUrlAndSelectors, getProviderVersionTags
 - Supports local monorepo flow (`pactUrls`) and remote broker flow (`PACT_BROKER_BASE_URL`, `PACT_BROKER_TOKEN`)
@@ -386,12 +386,12 @@ Optional MCP integration for design-time broker interaction in contract testing
 
 **Configuration** (`_bmad/tea/config.yaml`):
 
-    tea_pact_mcp: "mcp"  # mcp | none
+    tea_pact_mcp: "none"  # none | mcp
 
 | Mode   | What happens                                                                                                        |
 | ------ | ------------------------------------------------------------------------------------------------------------------- |
 | `mcp`  | TEA can use SmartBear MCP tools for provider-state discovery, test review support, can-i-deploy, and matrix checks. |
-| `none` | TEA uses CLI/script guidance only for broker interactions.                                                          |
+| `none` | Default. TEA skips broker/MCP integration entirely unless you explicitly enable it.                                 |
 
 **Setup:**
 

package/docs/how-to/customization/extend-tea-with-custom-workflows.md

@@ -0,0 +1,73 @@
+---
+title: 'Extend TEA with Custom Workflows'
+description: Add your own workflows to bmad-tea without patching TEA core
+---
+
+# Extend TEA with Custom Workflows
+
+TEA is a standalone module now. That means custom workflows are still supported, but they are not automatically folded into TEA core during updates.
+
+## The Supported Model
+
+Use one of these approaches:
+
+1. Package the workflow as custom content or a custom module.
+2. Add a menu entry to `bmad-tea` through BMAD agent customization.
+3. Reinstall or quick-update BMAD so the workflow and menu entry are registered.
+
+This keeps your TEA extensions compatible with upstream updates.
+
+## Recommended Approach
+
+### 1. Create the workflow as custom content
+
+Use BMad Builder or your own custom module structure to create a workflow that lives outside TEA core.
+
+- BMAD supports custom modules during install/update.
+- BMad Builder is the recommended path for creating reusable custom agents and workflows.
+
+See:
+
+- [How to Customize BMad](https://github.com/bmad-code-org/BMAD-METHOD/blob/main/docs/how-to/customize-bmad.md)
+- [BMad Builder (BMB)](https://github.com/bmad-code-org/bmad-builder)
+
+### 2. Attach the workflow to `bmad-tea`
+
+After TEA is installed, use the generated agent customization file for `bmad-tea` under `_bmad/_config/agents/` and append a menu item:
+
+```yaml
+menu:
+  - trigger: my-custom-workflow
+    workflow: 'my-custom/workflows/my-custom-workflow.yaml'
+    description: My custom TEA extension workflow
+```
+
+This keeps the `bmad-tea` chat/menu experience intact while routing to your custom workflow.
+
+### 3. Reinstall or quick-update BMAD
+
+Run:
+
+```bash
+npx bmad-method install
+```
+
+Then choose a normal update path so BMAD re-applies the customization and refreshes the workflow registration.
+
+## What Not to Do
+
+- Do not patch TEA core files directly if the workflow is project-specific.
+- Do not rely on old embedded-TEA behavior where local workflows appeared to be attached automatically.
+- Do not keep custom workflow logic only in chat instructions. Put it in a real workflow or module so it survives updates.
+
+## When to Use Which Approach
+
+- **Project-specific workflow**: add custom content and attach it to `bmad-tea`
+- **Reusable internal workflow**: package it as a custom module
+- **Reusable public workflow**: consider publishing a standalone BMAD module
+
+## Related Docs
+
+- [TEA Command Reference](/docs/reference/commands.md)
+- [TEA Configuration Reference](/docs/reference/configuration.md)
+- [How to Customize BMad](https://github.com/bmad-code-org/BMAD-METHOD/blob/main/docs/how-to/customize-bmad.md)

package/docs/index.md

@@ -34,7 +34,7 @@ npx bmad-method install
 Then trigger workflows via chat:
 
 ```
-tea         # Load TEA agent
+bmad-tea    # Load TEA agent/menu
 test-design # Run Test Design workflow
 ```
 
@@ -46,6 +46,7 @@ Pick a path:
 - **TEA Lite**: Start with [Test Automation](/how-to/workflows/run-automate) only (30 minutes)
 - **Full TEA**: Start with the [TEA Overview](/explanation/tea-overview) for the complete workflow map
 - **Enterprise**: Choose [Greenfield](/how-to/brownfield/use-tea-for-enterprise) or [Brownfield](/how-to/brownfield/use-tea-with-existing-tests)
+- **Custom Extensions**: See [Extend TEA with Custom Workflows](/how-to/customization/extend-tea-with-custom-workflows)
 
 ## Core Workflows
 

package/docs/reference/commands.md

@@ -7,10 +7,13 @@ description: Quick reference for all 9 TEA workflows - inputs, outputs, and link
 
 Quick reference for all 9 TEA (Test Engineering Architect) workflows. For detailed step-by-step guides, see the how-to documentation.
 
+All workflows listed here are current and supported in TEA, including `nfr-assess`.
+
 **Invocation by tool:**
 
 - Claude Code / Cursor / Windsurf: use slash commands (for example, `/bmad:tea:automate`)
 - Codex: use `$` skills from `.agents/skills` (for example, `$bmad-tea-testarch-automate`)
+- Custom TEA extensions: package the workflow as custom content/module and attach it to `bmad-tea` via customization. See [Extend TEA with Custom Workflows](../how-to/customization/extend-tea-with-custom-workflows.md)
 
 ## Quick Index
 

package/docs/reference/configuration.md

@@ -30,8 +30,8 @@ user_skill_level: intermediate
 output_folder: _bmad-output
 test_artifacts: _bmad-output/test-artifacts
 tea_use_playwright_utils: true
-tea_use_pactjs_utils: true
-tea_pact_mcp: 'mcp'
+tea_use_pactjs_utils: false
+tea_pact_mcp: 'none'
 tea_browser_automation: 'auto'
 tea_execution_mode: 'auto'
 tea_capability_probe: true
@@ -135,7 +135,7 @@ npm install -D @seontechnologies/playwright-utils
 
 ### tea_use_pactjs_utils
 
-Enable Pact.js Utils integration for production-ready contract testing utilities.
+Enable Pact.js Utils integration for production-ready consumer-driven contract testing utilities.
 
 **Schema Location:** `src/module.yaml` (TEA module config)
 
@@ -143,12 +143,12 @@ Enable Pact.js Utils integration for production-ready contract testing utilities
 
 **Type:** `boolean`
 
-**Default:** `true`
+**Default:** `false`
 
 **Installer Prompt:**
 
 ```
-Enable Pact.js Utils integration for contract testing?
+Enable Pact.js Utils for consumer-driven contract testing?
 ```
 
 **Purpose:** Enables TEA to:
@@ -168,6 +168,8 @@ Enable Pact.js Utils integration for contract testing?
 - `test-review` - Uses pactjs-utils provider/review patterns
 - `ci` - Adds contract-test stage and quality gates
 
+**Use this when:** your team already practices consumer-driven contract testing or wants TEA to scaffold Pact-aware patterns on purpose. Leave it off for projects that do not use Pact.
+
 **Example (Enable):**
 
 ```yaml
@@ -203,14 +205,14 @@ Pact MCP strategy for broker interaction during contract testing workflows.
 
 **Type:** `string`
 
-**Default:** `"mcp"`
+**Default:** `"none"`
 
 **Options:** `"mcp"` | `"none"`
 
 **Installer Prompt:**
 
 ```
-Enable SmartBear MCP for PactFlow/Pact Broker interaction?
+Enable SmartBear MCP for PactFlow/Pact Broker? Only needed if you already use a broker.
 ```
 
 **Purpose:** Controls whether TEA can use SmartBear MCP tools for:
@@ -226,6 +228,8 @@ Enable SmartBear MCP for PactFlow/Pact Broker interaction?
 - `test-review` - MCP-assisted pact review context
 - `ci` - MCP can-i-deploy/matrix guidance references
 
+**Use this when:** your project already uses PactFlow or Pact Broker and you want TEA to query broker state during review, generation, or gate guidance. Otherwise leave it set to `none`.
+
 **Prerequisites:**
 
 ```bash
@@ -960,8 +964,8 @@ project_name: my-project
 user_skill_level: beginner # or intermediate/expert
 output_folder: _bmad-output
 tea_use_playwright_utils: true # Recommended
-tea_use_pactjs_utils: true # Recommended - production-ready contract testing utilities
-tea_pact_mcp: 'mcp' # Recommended - SmartBear MCP for PactFlow/Broker interaction
+tea_use_pactjs_utils: false # Recommended unless you actively use contract testing
+tea_pact_mcp: 'none' # Recommended unless you already use PactFlow/Broker
 tea_browser_automation: 'auto' # Recommended
 tea_execution_mode: 'auto' # Recommended - capability-aware mode selection
 tea_capability_probe: true # Recommended - fallback safely if mode unsupported
@@ -970,7 +974,7 @@ tea_capability_probe: true # Recommended - fallback safely if mode unsupported
 **Why recommended:**
 
 - Playwright Utils: Production-ready fixtures and utilities
-- Pact.js Utils: Optional contract-testing acceleration for backend/fullstack services
+- Pact.js Utils: Leave disabled until the project explicitly needs contract testing
 - Browser automation (auto): Smart CLI/MCP selection with fallback
 - Together: The three-part stack (see [Testing as Engineering](/docs/explanation/testing-as-engineering.md))
 
@@ -1022,8 +1026,8 @@ tea_capability_probe: true
 project_name: monorepo
 output_folder: _bmad-output
 tea_use_playwright_utils: true
-tea_use_pactjs_utils: true
-tea_pact_mcp: 'mcp'
+tea_use_pactjs_utils: false
+tea_pact_mcp: 'none'
 tea_execution_mode: 'auto'
 ```
 
@@ -1061,10 +1065,10 @@ planning_artifacts: _bmad-output/planning-artifacts
 implementation_artifacts: _bmad-output/implementation-artifacts
 project_knowledge: docs
 
-# TEA Configuration (Recommended: Enable both for full stack)
+# TEA Configuration (Recommended baseline)
 tea_use_playwright_utils: true # Recommended - production-ready utilities
-tea_use_pactjs_utils: true # Recommended - production-ready contract testing utilities
-tea_pact_mcp: 'mcp' # Recommended - SmartBear MCP for broker integration
+tea_use_pactjs_utils: false # Opt in only if your service uses contract testing
+tea_pact_mcp: 'none' # Opt in only if your service uses PactFlow/Broker
 tea_browser_automation: 'auto' # Recommended - smart CLI/MCP selection
 tea_execution_mode: 'auto' # Recommended - capability-aware team/subagent fallback
 tea_capability_probe: true # Recommended - safe fallback
@@ -1098,6 +1102,24 @@ document_output_language: english
 
 ---
 
+### Contract Testing Setup (Opt-In)
+
+Use this profile only for services that already use Pact or want TEA to scaffold contract-testing patterns on purpose.
+
+```yaml
+tea_use_pactjs_utils: true
+tea_pact_mcp: 'none' # Use 'mcp' only if you already use PactFlow/Broker
+```
+
+If you also use PactFlow or Pact Broker:
+
+```yaml
+tea_use_pactjs_utils: true
+tea_pact_mcp: 'mcp'
+```
+
+---
+
 ## See Also
 
 ### How-To Guides

package/docs/reference/troubleshooting.md

@@ -149,16 +149,16 @@ If the BMAD installer can run but cannot fetch the Test Architect module from Gi
 
 **Solutions**:
 
-1. Verify TEA agent file exists:
+1. Verify TEA agent skill exists:
 
    ```bash
-   ls -la _bmad/tea/agents/tea.agent.yaml
+   ls -la _bmad/tea/agents/bmad-tea/SKILL.md
    ```
 
-2. Validate agent YAML syntax:
+2. Validate agent schema:
 
    ```bash
-   # Check for YAML syntax errors
+   # Check for schema errors
    node tools/validate-agent-schema.js
    ```
 
@@ -204,6 +204,20 @@ If the BMAD installer can run but cannot fetch the Test Architect module from Gi
    $bmad-tea-testarch-test-design
    ```
 
+### Custom TEA Workflow Does Not Appear
+
+**Symptom**: A custom workflow used to be available from TEA, but it no longer appears in the `bmad-tea` menu after updates.
+
+**Cause**: TEA is now a standalone module. Custom workflows are not merged into TEA core automatically.
+
+**Solution**:
+
+1. Package the workflow as custom content or a custom module instead of editing TEA directly.
+2. Attach it to `bmad-tea` using the generated agent customization file under `_bmad/_config/agents/`.
+3. Re-run `npx bmad-method install` so the customization and workflow registration are refreshed.
+
+See [Extend TEA with Custom Workflows](../how-to/customization/extend-tea-with-custom-workflows.md).
+
 ---
 
 ## Workflow Execution Issues
@@ -682,7 +696,6 @@ When reporting issues, include:
 1. **Documentation**: [test-architect.bmad-method.org](https://test-architect.bmad-method.org)
 2. **GitHub Issues**: [Report a bug](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise/issues/new?template=issue.md)
 3. **GitHub Discussions**: [Ask a question](https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise/discussions)
-4. **Migration Guide**: [docs/MIGRATION.md](/docs/MIGRATION.md) for upgrade issues
 
 ### Before Reporting an Issue
 
@@ -737,11 +750,11 @@ Run this validation script:
 #!/bin/bash
 echo "Validating TEA Installation..."
 
-# Check agent file
-if [ -f "_bmad/tea/agents/tea.agent.yaml" ]; then
-  echo "✓ Agent file exists"
+# Check agent skill directory
+if [ -f "_bmad/tea/agents/bmad-tea/SKILL.md" ]; then
+  echo "✓ Agent skill exists"
 else
-  echo "✗ Agent file missing"
+  echo "✗ Agent skill missing"
 fi
 
 # Check workflows

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "bmad-method-test-architecture-enterprise",
-  "version": "1.7.0",
+  "version": "1.7.2",
   "description": "Master Test Architect for quality strategy, test automation, and release gates",
   "keywords": [
     "bmad",

package/release_notes.md

@@ -1,11 +1,11 @@
-## 🚀 What's New in v1.7.0
+## 🚀 What's New in v1.7.2
 
-### ✨ New Features
-- feat: skills migration part1
+### 🐛 Bug Fixes
+- fix: tighten framework loading
+- fix: addressed Augment code comment
 
 ### 📦 Other Changes
-- addressed review comments
-- Merge pull request #54 from bmad-code-org/feat/skill-migration-part1
+- Merge pull request #58 from bmad-code-org/fix/tighten-framework-loading
 
 
 ## 📦 Installation
@@ -15,4 +15,4 @@ npx bmad-method install
 # Select "Test Architect" from module menu
 ```
 
-**Full Changelog**: https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise/compare/v1.6.0...v1.7.0
+**Full Changelog**: https://github.com/bmad-code-org/bmad-method-test-architecture-enterprise/compare/v1.7.1...v1.7.2

package/src/agents/bmad-tea/SKILL.md

@@ -0,0 +1,70 @@
+---
+name: bmad-tea
+description: Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.
+---
+
+# Murat
+
+## Overview
+
+This skill provides a Master Test Architect and Quality Advisor specializing in risk-based testing, fixture architecture, ATDD, API testing, backend services, UI automation, CI/CD governance, and scalable quality gates. Act as Murat — data-driven, strong opinions weakly held, speaking in risk calculations and impact assessments.
+
+## Identity
+
+Test architect specializing in risk-based testing, fixture architecture, ATDD, API testing, backend services, UI automation, CI/CD governance, and scalable quality gates. Equally proficient in pure API/service-layer testing (pytest, JUnit, Go test, xUnit, RSpec) as in browser-based E2E testing (Playwright, Cypress), consumer driven contract testing (Pact) and performance/load/chaos testing (k6). Supports GitHub Actions, GitLab CI, Jenkins, Azure DevOps, and Harness CI platforms.
+
+## Communication Style
+
+Blends data with gut instinct. "Strong opinions, weakly held" is their mantra. Speaks in risk calculations and impact assessments.
+
+## Principles
+
+- Risk-based testing - depth scales with impact
+- Quality gates backed by data
+- Tests mirror usage patterns (API, UI, or both)
+- Flakiness is critical technical debt
+- Tests first AI implements suite validates
+- Calculate risk vs value for every testing decision
+- Prefer lower test levels (unit > integration > E2E) when possible
+- API tests are first-class citizens, not just UI support
+
+## Critical Actions
+
+- Consult `{project-root}/_bmad/tea/testarch/tea-index.csv` to select knowledge fragments under `knowledge/` and load only the files needed for the current task
+- Load the referenced fragment(s) from `{project-root}/_bmad/tea/testarch/knowledge/` before giving recommendations
+- Cross-check recommendations with the current official Playwright, Cypress, Pact, k6, pytest, JUnit, Go test, and CI platform documentation
+
+You must fully embody this persona so the user gets the best experience and help they need, therefore its important to remember you must not break character until the users dismisses this persona.
+
+When you are in this persona and the user calls a skill, this persona must carry through and remain active.
+
+## Capabilities
+
+| Code | Description                                                                                                                        | Skill                     |
+| ---- | ---------------------------------------------------------------------------------------------------------------------------------- | ------------------------- |
+| TMT  | Teach Me Testing: Interactive learning companion - 7 progressive sessions teaching testing fundamentals through advanced practices | bmad-teach-me-testing     |
+| TF   | Test Framework: Initialize production-ready test framework architecture                                                            | bmad-testarch-framework   |
+| AT   | ATDD: Generate failing acceptance tests plus an implementation checklist before development                                        | bmad-testarch-atdd        |
+| TA   | Test Automation: Generate prioritized API/E2E tests, fixtures, and DoD summary for a story or feature                              | bmad-testarch-automate    |
+| TD   | Test Design: Risk assessment plus coverage strategy for system or epic scope                                                       | bmad-testarch-test-design |
+| TR   | Trace Requirements: Map requirements to tests (Phase 1) and make quality gate decision (Phase 2)                                   | bmad-testarch-trace       |
+| NR   | Non-Functional Requirements: Assess NFRs and recommend actions                                                                     | bmad-testarch-nfr         |
+| CI   | Continuous Integration: Recommend and Scaffold CI/CD quality pipeline                                                              | bmad-testarch-ci          |
+| RV   | Review Tests: Perform a quality check against written tests using comprehensive knowledge base and best practices                  | bmad-testarch-test-review |
+
+## On Activation
+
+1. **Load config via bmad-init skill** — Store all returned vars for use:
+   - Use `{user_name}` from config for greeting
+   - Use `{communication_language}` from config for all communications
+   - Store any other config variables as `{var-name}` and use appropriately
+
+2. **Continue with steps below:**
+   - **Load project context** — Search for `**/project-context.md`. If found, load as foundational reference for project standards and conventions. If not found, continue without it.
+   - **Greet and present capabilities** — Greet `{user_name}` warmly by name, always speaking in `{communication_language}` and applying your persona throughout the session.
+
+3. Remind the user they can invoke the `bmad-help` skill at any time for advice and then present the capabilities table from the Capabilities section above.
+
+   **STOP and WAIT for user input** — Do NOT execute menu items automatically. Accept a capability code, skill name, or fuzzy description match from the Capabilities table.
+
+**CRITICAL Handling:** When user responds with a capability code (e.g., TMT, TF, AT), an exact registered skill name, or a fuzzy description match (e.g., "teach me testing", "continuous integration", "test framework"), invoke the corresponding skill from the Capabilities table. DO NOT invent capabilities on the fly or attempt to map arbitrary numeric inputs to skills.

package/src/agents/bmad-tea/bmad-skill-manifest.yaml

@@ -0,0 +1,14 @@
+type: agent
+name: bmad-tea
+displayName: Murat
+title: Master Test Architect and Quality Advisor
+icon: "🧪"
+capabilities: "risk-based testing, fixture architecture, ATDD, API testing, backend services, UI automation, CI/CD governance, scalable quality gates, consumer-driven contract testing, performance/load/chaos testing"
+role: Master Test Architect
+identity: "Test architect specializing in risk-based testing, fixture architecture, ATDD, API testing, backend services, UI automation, CI/CD governance, and scalable quality gates. Equally proficient in pure API/service-layer testing (pytest, JUnit, Go test, xUnit, RSpec) as in browser-based E2E testing (Playwright, Cypress), consumer driven contract testing (Pact) and performance/load/chaos testing (k6). Supports GitHub Actions, GitLab CI, Jenkins, Azure DevOps, and Harness CI platforms."
+communicationStyle: "Blends data with gut instinct. 'Strong opinions, weakly held' is their mantra. Speaks in risk calculations and impact assessments."
+principles: "Risk-based testing - depth scales with impact. Quality gates backed by data. Tests mirror usage patterns (API, UI, or both). Flakiness is critical technical debt. Tests first AI implements suite validates. Calculate risk vs value for every testing decision. Prefer lower test levels (unit > integration > E2E) when possible. API tests are first-class citizens, not just UI support."
+module: tea
+canonicalId: bmad-tea
+webskip: true
+hasSidecar: false

package/src/module.yaml

@@ -38,27 +38,27 @@ tea_use_playwright_utils:
 # ✅ ACTIVELY USED - Pact.js Utils integration for contract testing (referenced in workflows: automate, atdd, framework, test-design, test-review, ci)
 # CRITICAL: Must be boolean (true/false) not string - workflows check "if config.tea_use_pactjs_utils: true"
 tea_use_pactjs_utils:
-  prompt: "Enable Pact.js Utils integration for contract testing?"
-  default: true
+  prompt: "Enable Pact.js Utils for consumer-driven contract testing?"
+  default: false
   result: "{value}"
   single-select:
     - value: true
-      label: "Yes - Use production contract testing utilities"
+      label: "Yes - Enable optional contract-testing utilities"
     - value: false
-      label: "No - Use raw @pact-foundation/pact patterns"
+      label: "No - Skip Pact integration"
 
 # ✅ ACTIVELY USED - Pact MCP integration for broker interaction during contract testing
 # Controls how TEA interacts with PactFlow/Pact Broker during test generation and review
 # CRITICAL: Must be a string value: "mcp" | "none"
 tea_pact_mcp:
-  prompt: "Enable SmartBear MCP for PactFlow/Pact Broker interaction?"
-  default: "mcp"
+  prompt: "Enable SmartBear MCP for PactFlow/Pact Broker? Only needed if you already use a broker."
+  default: "none"
   result: "{value}"
   single-select:
     - value: "mcp"
-      label: "Yes - Use SmartBear MCP for broker queries"
+      label: "Yes - Enable optional broker integration"
     - value: "none"
-      label: "No - Use CLI scripts only"
+      label: "No - No broker/MCP integration"
 
 # ✅ ACTIVELY USED - Browser automation strategy for TEA workflows
 # Controls how TEA interacts with live browsers during test generation

package/src/workflows/testarch/bmad-testarch-framework/steps-c/step-03-scaffold-framework.md

@@ -202,7 +202,8 @@ Read `{config_source}` and use `{knowledgeIndex}` to load fragments based on `co
 
 **If Playwright Utils enabled:**
 
-- `overview.md`, `fixtures-composition.md`, `auth-session.md`, `api-request.md`, `burn-in.md`, `network-error-monitor.md`, `data-factories.md`
+- `overview.md`, `fixtures-composition.md`, `auth-session.md`, `api-request.md`, `recurse.md`, `log.md`, `burn-in.md`, `network-error-monitor.md`, `data-factories.md`
+- If `{detected_stack}` is `frontend` or `fullstack`, also load `intercept-network-call.md`
 - Recommend installing `@seontechnologies/playwright-utils`
 
 **If disabled:**