@devo-bmad-custom/agent-orchestration 1.0.2 → 1.0.3

package/src/bmm/workflows/bmad-quick-flow/quick-spec/steps/step-02-investigate.md

@@ -1,152 +1,152 @@
----
-name: 'step-02-investigate'
-description: 'Map technical constraints and anchor points within the codebase'
-
-wipFile: '{implementation_artifacts}/tech-spec-wip.md'
----
-
-# Step 2: Map Technical Constraints & Anchor Points
-
-**Progress: Step 2 of 4** - Next: Generate Plan
-
-## RULES:
-
-- MUST NOT skip steps.
-- MUST NOT optimize sequence.
-- MUST follow exact instructions.
-- MUST NOT generate the full spec yet (that's Step 3).
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## CONTEXT:
-
-- Requires `{wipFile}` from Step 1 with the "Problem Statement" defined.
-- Focus: Map the problem statement to specific anchor points in the codebase.
-- Output: Exact files to touch, classes/patterns to extend, and technical constraints identified.
-- Objective: Provide the implementation-ready ground truth for the plan.
-
-## SEQUENCE OF INSTRUCTIONS
-
-### 1. Load Current State
-
-**Read `{wipFile}` and extract:**
-
-- Problem statement and scope from Overview section
-- Any context gathered in Step 1
-
-### 2. Execute Investigation Path
-
-**Universal Code Investigation:**
-
-_Isolate deep exploration in sub-agents/tasks where available. Return distilled summaries only to prevent context snowballing._
-
-a) **Build on Step 1's Quick Scan**
-
-Review what was found in Step 1's orient scan. Then ask:
-
-"Based on my quick look, I see [files/patterns found]. Are there other files or directories I should investigate deeply?"
-
-b) **Read and Analyze Code**
-
-For each file/directory provided:
-
-- Read the complete file(s)
-- Identify patterns, conventions, coding style
-- Note dependencies and imports
-- Find related test files
-
-**If NO relevant code is found (Clean Slate):**
-
-- Identify the target directory where the feature should live.
-- Scan parent directories for architectural context.
-- Identify standard project utilities or boilerplate that SHOULD be used.
-- Document this as "Confirmed Clean Slate" - establishing that no legacy constraints exist.
-
-
-c) **Document Technical Context**
-
-Capture and confirm with user:
-
-- **Tech Stack**: Languages, frameworks, libraries
-- **Code Patterns**: Architecture patterns, naming conventions, file structure
-- **Files to Modify/Create**: Specific files that will need changes or new files to be created
-- **Test Patterns**: How tests are structured, test frameworks used
-
-d) **Look for project-context.md**
-
-If `**/project-context.md` exists and wasn't loaded in Step 1:
-
-- Load it now
-- Extract patterns and conventions
-- Note any rules that must be followed
-
-### 3. Update WIP File
-
-**Update `{wipFile}` frontmatter:**
-
-```yaml
----
-# ... existing frontmatter ...
-stepsCompleted: [1, 2]
-tech_stack: ['{captured_tech_stack}']
-files_to_modify: ['{captured_files}']
-code_patterns: ['{captured_patterns}']
-test_patterns: ['{captured_test_patterns}']
----
-```
-
-**Update the Context for Development section:**
-
-Fill in:
-
-- Codebase Patterns (from investigation)
-- Files to Reference table (files reviewed)
-- Technical Decisions (any decisions made during investigation)
-
-**Report to user:**
-
-"**Context Gathered:**
-
-- Tech Stack: {tech_stack_summary}
-- Files to Modify: {files_count} files identified
-- Patterns: {patterns_summary}
-- Tests: {test_patterns_summary}"
-
-### 4. Proceed to Spec Generation
-
-> 💡 **Agile note — why we do this:** Step 2 maps the *exact terrain* of the codebase before writing a single line of the spec. Skipping investigation is how teams end up implementing the right feature in the wrong place — fixing it after the fact costs 3× the effort.
-
-**Report to user and proceed automatically:**
-
-```
-✅ Step 2 complete — technical context mapped.
-
-📝 Moving to Step 3: Generate Spec
-I'll translate everything we found into an implementation-ready plan.
-
-Optional tools available any time:
-  [A] Advanced Elicitation — structured discovery to surface hidden constraints
-  [P] Party Mode Review — multi-agent critique of the investigation findings
-  [AR] Adversarial Review — challenge the technical decisions before we write the spec
-Type one of these to use them now, otherwise I'm proceeding.
-```
-
-#### Auto-Proceed Rules:
-
-- Proceed immediately to Step 3 unless the user types `[A]`, `[P]`, or `[AR]` in response
-- If `[A]`: Read fully and follow `{advanced_elicitation}` with current tech-spec content, process enhanced insights, ask user "Accept improvements? (y/n)", if yes update WIP file then proceed to Step 3
-- If `[P]`: Read fully and follow `{party_mode_exec}` with current tech-spec content, process collaborative insights, ask user "Accept changes? (y/n)", if yes update WIP file then proceed to Step 3
-- If `[AR]`: Execute `{project-root}/_bmad/core/tasks/review-adversarial-general.xml` with the current WIP file, display findings, then proceed to Step 3
-- If user asks questions or requests changes: respond and handle them, then proceed
-- **No confirmation gate** — the only reason to pause is if the user actively invokes one of the above tools or asks a question
-
----
-
-## REQUIRED OUTPUTS:
-
-- MUST document technical context (stack, patterns, files identified).
-- MUST update `{wipFile}` with functional context.
-
-## VERIFICATION CHECKLIST:
-
-- [ ] Technical mapping performed and documented.
-- [ ] `stepsCompleted: [1, 2]` set in frontmatter.
+---
+name: 'step-02-investigate'
+description: 'Map technical constraints and anchor points within the codebase'
+
+wipFile: '{implementation_artifacts}/tech-spec-wip.md'
+---
+
+# Step 2: Map Technical Constraints & Anchor Points
+
+**Progress: Step 2 of 4** - Next: Generate Plan
+
+## RULES:
+
+- MUST NOT skip steps.
+- MUST NOT optimize sequence.
+- MUST follow exact instructions.
+- MUST NOT generate the full spec yet (that's Step 3).
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
+
+## CONTEXT:
+
+- Requires `{wipFile}` from Step 1 with the "Problem Statement" defined.
+- Focus: Map the problem statement to specific anchor points in the codebase.
+- Output: Exact files to touch, classes/patterns to extend, and technical constraints identified.
+- Objective: Provide the implementation-ready ground truth for the plan.
+
+## SEQUENCE OF INSTRUCTIONS
+
+### 1. Load Current State
+
+**Read `{wipFile}` and extract:**
+
+- Problem statement and scope from Overview section
+- Any context gathered in Step 1
+
+### 2. Execute Investigation Path
+
+**Universal Code Investigation:**
+
+_Isolate deep exploration in sub-agents/tasks where available. Return distilled summaries only to prevent context snowballing._
+
+a) **Build on Step 1's Quick Scan**
+
+Review what was found in Step 1's orient scan. Then ask:
+
+"Based on my quick look, I see [files/patterns found]. Are there other files or directories I should investigate deeply?"
+
+b) **Read and Analyze Code**
+
+For each file/directory provided:
+
+- Read the complete file(s)
+- Identify patterns, conventions, coding style
+- Note dependencies and imports
+- Find related test files
+
+**If NO relevant code is found (Clean Slate):**
+
+- Identify the target directory where the feature should live.
+- Scan parent directories for architectural context.
+- Identify standard project utilities or boilerplate that SHOULD be used.
+- Document this as "Confirmed Clean Slate" - establishing that no legacy constraints exist.
+
+
+c) **Document Technical Context**
+
+Capture and confirm with user:
+
+- **Tech Stack**: Languages, frameworks, libraries
+- **Code Patterns**: Architecture patterns, naming conventions, file structure
+- **Files to Modify/Create**: Specific files that will need changes or new files to be created
+- **Test Patterns**: How tests are structured, test frameworks used
+
+d) **Look for project-context.md**
+
+If `**/project-context.md` exists and wasn't loaded in Step 1:
+
+- Load it now
+- Extract patterns and conventions
+- Note any rules that must be followed
+
+### 3. Update WIP File
+
+**Update `{wipFile}` frontmatter:**
+
+```yaml
+---
+# ... existing frontmatter ...
+stepsCompleted: [1, 2]
+tech_stack: ['{captured_tech_stack}']
+files_to_modify: ['{captured_files}']
+code_patterns: ['{captured_patterns}']
+test_patterns: ['{captured_test_patterns}']
+---
+```
+
+**Update the Context for Development section:**
+
+Fill in:
+
+- Codebase Patterns (from investigation)
+- Files to Reference table (files reviewed)
+- Technical Decisions (any decisions made during investigation)
+
+**Report to user:**
+
+"**Context Gathered:**
+
+- Tech Stack: {tech_stack_summary}
+- Files to Modify: {files_count} files identified
+- Patterns: {patterns_summary}
+- Tests: {test_patterns_summary}"
+
+### 4. Proceed to Spec Generation
+
+> 💡 **Agile note — why we do this:** Step 2 maps the *exact terrain* of the codebase before writing a single line of the spec. Skipping investigation is how teams end up implementing the right feature in the wrong place — fixing it after the fact costs 3× the effort.
+
+**Report to user and proceed automatically:**
+
+```
+✅ Step 2 complete — technical context mapped.
+
+📝 Moving to Step 3: Generate Spec
+I'll translate everything we found into an implementation-ready plan.
+
+Optional tools available any time:
+  [A] Advanced Elicitation — structured discovery to surface hidden constraints
+  [P] Party Mode Review — multi-agent critique of the investigation findings
+  [AR] Adversarial Review — challenge the technical decisions before we write the spec
+Type one of these to use them now, otherwise I'm proceeding.
+```
+
+#### Auto-Proceed Rules:
+
+- Proceed immediately to Step 3 unless the user types `[A]`, `[P]`, or `[AR]` in response
+- If `[A]`: Read fully and follow `{advanced_elicitation}` with current tech-spec content, process enhanced insights, ask user "Accept improvements? (y/n)", if yes update WIP file then proceed to Step 3
+- If `[P]`: Read fully and follow `{party_mode_exec}` with current tech-spec content, process collaborative insights, ask user "Accept changes? (y/n)", if yes update WIP file then proceed to Step 3
+- If `[AR]`: Execute `{project-root}/_bmad/core/tasks/review-adversarial-general.xml` with the current WIP file, display findings, then proceed to Step 3
+- If user asks questions or requests changes: respond and handle them, then proceed
+- **No confirmation gate** — the only reason to pause is if the user actively invokes one of the above tools or asks a question
+
+---
+
+## REQUIRED OUTPUTS:
+
+- MUST document technical context (stack, patterns, files identified).
+- MUST update `{wipFile}` with functional context.
+
+## VERIFICATION CHECKLIST:
+
+- [ ] Technical mapping performed and documented.
+- [ ] `stepsCompleted: [1, 2]` set in frontmatter.

package/src/bmm/workflows/bmad-quick-flow/quick-spec/steps/step-03-generate.md

@@ -1,123 +1,123 @@
----
-name: 'step-03-generate'
-description: 'Build the implementation plan based on the technical mapping of constraints'
-
-wipFile: '{implementation_artifacts}/tech-spec-wip.md'
----
-
-# Step 3: Generate Implementation Plan
-
-**Progress: Step 3 of 4** - Next: Review & Finalize
-
-## RULES:
-
-- MUST NOT skip steps or optimize sequence.
-- MUST NOT implement anything — just document.
-
-## CONTEXT:
-
-- Requires `{wipFile}` with defined "Overview" and "Context for Development" sections.
-- Focus: Create the implementation sequence that addresses the requirement delta using the captured technical context.
-- Output: Implementation-ready tasks with specific files and instructions.
-- Target: Meet the **READY FOR DEVELOPMENT** standard defined in `workflow.md`.
-
-## SEQUENCE OF INSTRUCTIONS
-
-### 1. Load Current State
-
-**Read `{wipFile}` completely and extract:**
-
-- All frontmatter values
-- Overview section (Problem, Solution, Scope)
-- Context for Development section (Patterns, Files, Decisions)
-
-### 2. Generate Implementation Plan
-
-Generate specific implementation tasks:
-
-a) **Task Breakdown**
-
-- Each task should be a discrete, completable unit of work
-- Tasks should be ordered logically (dependencies first)
-- Include the specific files to modify in each task
-- Be explicit about what changes to make
-
-b) **Task Format**
-
-```markdown
-- [ ] Task N: Clear action description
-  - File: `path/to/file.ext`
-  - Action: Specific change to make
-  - Notes: Any implementation details
-```
-
-### 3. Generate Acceptance Criteria
-
-**Create testable acceptance criteria:**
-
-Each AC should follow Given/When/Then format:
-
-```markdown
-- [ ] AC N: Given [precondition], when [action], then [expected result]
-```
-
-**Ensure ACs cover:**
-
-- Happy path functionality
-- Error handling
-- Edge cases (if relevant)
-- Integration points (if relevant)
-
-### 4. Complete Additional Context
-
-**Fill in remaining sections:**
-
-a) **Dependencies**
-
-- External libraries or services needed
-- Other tasks or features this depends on
-- API or data dependencies
-
-b) **Testing Strategy**
-
-- Unit tests needed
-- Integration tests needed
-- Manual testing steps
-
-c) **Notes**
-
-- High-risk items from pre-mortem analysis
-- Known limitations
-- Future considerations (out of scope but worth noting)
-
-### 5. Write Complete Spec
-
-a) **Update `{wipFile}` with all generated content:**
-
-- Ensure all template sections are filled in
-- No placeholder text remaining
-- All frontmatter values current
-- Update status to 'review' (NOT 'ready-for-dev' - that happens after user review in Step 4)
-
-b) **Update frontmatter:**
-
-```yaml
----
-# ... existing values ...
-status: 'review'
-stepsCompleted: [1, 2, 3]
----
-```
-
-c) **Read fully and follow: `{project-root}/_bmad/bmm/workflows/bmad-quick-flow/quick-spec/steps/step-04-review.md` (Step 4)**
-
-## REQUIRED OUTPUTS:
-
-- Tasks MUST be specific, actionable, ordered logically, with files to modify.
-- ACs MUST be testable, using Given/When/Then format.
-- Status MUST be updated to 'review'.
-
-## VERIFICATION CHECKLIST:
-
-- [ ] `stepsCompleted: [1, 2, 3]` set in frontmatter.
-- [ ] Spec meets the **READY FOR DEVELOPMENT** standard.
+---
+name: 'step-03-generate'
+description: 'Build the implementation plan based on the technical mapping of constraints'
+
+wipFile: '{implementation_artifacts}/tech-spec-wip.md'
+---
+
+# Step 3: Generate Implementation Plan
+
+**Progress: Step 3 of 4** - Next: Review & Finalize
+
+## RULES:
+
+- MUST NOT skip steps or optimize sequence.
+- MUST NOT implement anything — just document.
+
+## CONTEXT:
+
+- Requires `{wipFile}` with defined "Overview" and "Context for Development" sections.
+- Focus: Create the implementation sequence that addresses the requirement delta using the captured technical context.
+- Output: Implementation-ready tasks with specific files and instructions.
+- Target: Meet the **READY FOR DEVELOPMENT** standard defined in `workflow.md`.
+
+## SEQUENCE OF INSTRUCTIONS
+
+### 1. Load Current State
+
+**Read `{wipFile}` completely and extract:**
+
+- All frontmatter values
+- Overview section (Problem, Solution, Scope)
+- Context for Development section (Patterns, Files, Decisions)
+
+### 2. Generate Implementation Plan
+
+Generate specific implementation tasks:
+
+a) **Task Breakdown**
+
+- Each task should be a discrete, completable unit of work
+- Tasks should be ordered logically (dependencies first)
+- Include the specific files to modify in each task
+- Be explicit about what changes to make
+
+b) **Task Format**
+
+```markdown
+- [ ] Task N: Clear action description
+  - File: `path/to/file.ext`
+  - Action: Specific change to make
+  - Notes: Any implementation details
+```
+
+### 3. Generate Acceptance Criteria
+
+**Create testable acceptance criteria:**
+
+Each AC should follow Given/When/Then format:
+
+```markdown
+- [ ] AC N: Given [precondition], when [action], then [expected result]
+```
+
+**Ensure ACs cover:**
+
+- Happy path functionality
+- Error handling
+- Edge cases (if relevant)
+- Integration points (if relevant)
+
+### 4. Complete Additional Context
+
+**Fill in remaining sections:**
+
+a) **Dependencies**
+
+- External libraries or services needed
+- Other tasks or features this depends on
+- API or data dependencies
+
+b) **Testing Strategy**
+
+- Unit tests needed
+- Integration tests needed
+- Manual testing steps
+
+c) **Notes**
+
+- High-risk items from pre-mortem analysis
+- Known limitations
+- Future considerations (out of scope but worth noting)
+
+### 5. Write Complete Spec
+
+a) **Update `{wipFile}` with all generated content:**
+
+- Ensure all template sections are filled in
+- No placeholder text remaining
+- All frontmatter values current
+- Update status to 'review' (NOT 'ready-for-dev' - that happens after user review in Step 4)
+
+b) **Update frontmatter:**
+
+```yaml
+---
+# ... existing values ...
+status: 'review'
+stepsCompleted: [1, 2, 3]
+---
+```
+
+c) **Read fully and follow: `{project-root}/_bmad/bmm/workflows/bmad-quick-flow/quick-spec/steps/step-04-review.md` (Step 4)**
+
+## REQUIRED OUTPUTS:
+
+- Tasks MUST be specific, actionable, ordered logically, with files to modify.
+- ACs MUST be testable, using Given/When/Then format.
+- Status MUST be updated to 'review'.
+
+## VERIFICATION CHECKLIST:
+
+- [ ] `stepsCompleted: [1, 2, 3]` set in frontmatter.
+- [ ] Spec meets the **READY FOR DEVELOPMENT** standard.