convoke-agents 2.3.1 → 3.0.0

package/_bmad/bme/_enhance/extensions/bmm-pm.yaml

@@ -0,0 +1,9 @@
+# Extension descriptor for John PM agent
+# v1: Documentation-only — describes the patch-based menu item added by the installer
+# v3: Will be read dynamically by agents via <extensions> tag (future BMAD Method proposal)
+
+target_agent: bmm/pm
+menu_items:
+  - cmd: "IB or fuzzy match on initiatives-backlog"
+    exec: "{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/workflow.md"
+    label: "[IB] 📦 Initiatives Backlog (Convoke Enhance)"

package/_bmad/bme/_enhance/guides/ENHANCE-GUIDE.md

@@ -0,0 +1,252 @@
+# Enhance Module — Pattern Guide for Module Authors
+
+Create new enhancement workflows for existing BMAD agents by following the patterns established in the initiatives-backlog workflow. This guide covers directory layout, step file architecture, agent menu patching, config registration, and verification.
+
+---
+
+## Directory Structure
+
+Every enhancement workflow lives under `_bmad/bme/_enhance/workflows/[name]/`:
+
+```
+_bmad/bme/_enhance/
+├── config.yaml                                # Module config — register all workflows here
+├── extensions/
+│   └── bmm-[agent].yaml                       # Extension descriptor (v1: docs-only)
+├── workflows/
+│   └── [workflow-name]/
+│       ├── workflow.md                         # Entry point — mode menu + dispatch
+│       ├── SKILL.md                            # Skill wrapper (auto-generated by installer)
+│       ├── steps-[mode]/                       # One folder per mode
+│       │   ├── step-[mode]-01-[name].md
+│       │   ├── step-[mode]-02-[name].md
+│       │   └── ...
+│       └── templates/                          # Reference docs loaded by steps at runtime
+│           ├── [template-1].md
+│           └── [template-2].md
+└── guides/
+    └── ENHANCE-GUIDE.md                        # This file
+```
+
+**Canonical example:** `workflows/initiatives-backlog/` — tri-modal workflow (Triage/Review/Create) with 11 step files across 3 mode folders and 2 templates.
+
+**Naming conventions:**
+- Workflow folders: kebab-case (`initiatives-backlog`, `sprint-health`)
+- Step folders: `steps-[mode-letter]/` (e.g., `steps-t/`, `steps-r/`, `steps-c/`)
+- Step files: `step-[mode]-[NN]-[name].md` (e.g., `step-t-01-ingest.md`)
+- Templates: descriptive kebab-case (e.g., `rice-scoring-guide.md`, `backlog-format-spec.md`)
+
+---
+
+## Workflow Entry Point
+
+`workflow.md` is the entry point loaded when the user selects the enhancement from the agent menu. It should:
+
+1. **Load config** from `_bmad/bme/_enhance/config.yaml`
+2. **Present a mode menu** (if multi-modal) or proceed directly (if single-mode)
+3. **Dispatch to the first step file** based on user selection
+4. **Define return-to-menu convention** — final steps reload `workflow.md` to re-present the menu
+
+See `workflows/initiatives-backlog/workflow.md` for the canonical entry point pattern.
+
+---
+
+## Step File Architecture
+
+Every step file follows the BMAD standard structure:
+
+```markdown
+---
+name: 'step-[mode]-[NN]-[name]'
+description: '[one-line description]'
+nextStepFile: '{project-root}/_bmad/bme/_enhance/workflows/[name]/steps-[mode]/step-[mode]-[NN+1]-[name].md'
+outputFile: '{planning_artifacts}/[output-file].md'
+templateFile: '{project-root}/_bmad/bme/_enhance/workflows/[name]/templates/[template].md'
+---
+
+# Step N: [Title]
+
+## STEP GOAL:
+## MANDATORY EXECUTION RULES (READ FIRST):
+### Universal Rules:
+### Role Reinforcement:
+### Step-Specific Rules:
+## EXECUTION PROTOCOLS:
+## CONTEXT BOUNDARIES:
+## MANDATORY SEQUENCE
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
+```
+
+### Frontmatter Fields
+
+| Field | Required | Description |
+|---|---|---|
+| `name` | Yes | Step identifier |
+| `description` | Yes | One-line purpose |
+| `nextStepFile` | Steps 1–(N-1) | Full path to next step in chain |
+| `outputFile` | If writing output | Path to artifact file (uses `{planning_artifacts}` variable) |
+| `templateFile` | If loading reference | Path to template loaded during execution |
+| `workflowFile` | Final step + cancel paths | Path to `workflow.md` for return-to-menu |
+| `advancedElicitationTask` | Interactive steps | Path to Advanced Elicitation workflow |
+| `partyModeWorkflow` | Interactive steps | Path to Party Mode workflow |
+
+### Step Types
+
+| Type | Menu | Use Case | Example |
+|---|---|---|---|
+| **Type 4** (Standard) | A, P, C + custom commands | Interactive steps with user decisions | `step-t-03-score.md` |
+| **Type 5** (Simple) | C only | Non-interactive load/setup steps | `step-t-01-ingest.md` |
+| **Type 10** (Final) | None (auto-return) | Last step — writes output, returns to menu | `step-t-04-update.md` |
+
+**Final step convention:** No `nextStepFile`. Has `workflowFile` instead. After completion summary, loads and executes `{workflowFile}` to return to the mode menu.
+
+### Step Chaining
+
+Steps form a sequential chain within each mode:
+
+```
+workflow.md → step-[mode]-01 → step-[mode]-02 → ... → step-[mode]-NN → workflow.md
+```
+
+Each step hardcodes the full path to the next step in its menu handling logic (consistent with the `nextStepFile` frontmatter). The final step reloads `workflow.md` via `{workflowFile}`.
+
+---
+
+## Templates
+
+Templates are pure markdown reference documents loaded by steps at runtime. They contain no template variables or runtime logic.
+
+- **Audience separation:** Create separate templates for different purposes (e.g., one for scoring methodology, one for file format specification)
+- **Installer-managed:** `templates/` is overwritten on update. Users should not customize template files directly — customizations belong in the target project's output folder
+- **Round-trip parseability:** If a template defines a file format, the workflow must be able to reload its own output
+
+---
+
+## Agent Menu Patching
+
+The installer adds an `<item>` tag to the target agent's menu:
+
+```xml
+<item cmd="IB or fuzzy match on initiatives-backlog"
+      exec="{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/workflow.md">
+  [IB] 📦 Initiatives Backlog (Convoke Enhance)
+</item>
+```
+
+**Conventions:**
+- `cmd`: Short code + fuzzy match phrase (e.g., `"SH or fuzzy match on sprint-health"`)
+- `exec`: Full path using `{project-root}/_bmad/...` form
+- Display label: `[CODE] 📦 [Name] (Convoke Enhance)` — the 📦 prefix and "(Convoke Enhance)" suffix identify enhanced menu items
+- The installer inserts the tag before `</menu>` in the target agent file
+
+**Max 2-3 items per agent.** More than that creates menu bloat and dilutes the agent's focus. If you need more capabilities, consider whether they belong as modes within an existing workflow rather than separate workflows.
+
+### Extension Descriptor
+
+Create `extensions/bmm-[agent].yaml` to document the menu patch:
+
+```yaml
+# v1: Documentation-only — describes the patch added by the installer
+# v3: Will be read dynamically by agents via <extensions> tag (future BMAD Method proposal)
+
+target_agent: bmm/pm
+menu_items:
+  - cmd: "IB or fuzzy match on initiatives-backlog"
+    exec: "{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/workflow.md"
+    label: "[IB] 📦 Initiatives Backlog (Convoke Enhance)"
+```
+
+---
+
+## Config Registration
+
+Register every workflow in `_bmad/bme/_enhance/config.yaml`:
+
+```yaml
+name: enhance
+version: 1.0.0
+description: "Enhance module — capability upgrades for existing BMAD agents"
+workflows:
+  - name: initiatives-backlog
+    entry: workflows/initiatives-backlog/workflow.md
+    target_agent: bmm/agents/pm.md
+    menu_patch_name: "initiatives-backlog"
+```
+
+**Required fields per workflow:**
+
+| Field | Description | Example |
+|---|---|---|
+| `name` | Workflow identifier (matches folder name) | `initiatives-backlog` |
+| `entry` | Entry point path relative to `_enhance/` | `workflows/initiatives-backlog/workflow.md` |
+| `target_agent` | Agent file path relative to `_bmad/` | `bmm/agents/pm.md` |
+| `menu_patch_name` | Name attribute for installer detection/dedup | `"initiatives-backlog"` |
+
+### Adding a Second Workflow — Example
+
+A "Sprint Health Check" enhancement for the SM agent:
+
+```yaml
+workflows:
+  - name: initiatives-backlog
+    entry: workflows/initiatives-backlog/workflow.md
+    target_agent: bmm/agents/pm.md
+    menu_patch_name: "initiatives-backlog"
+  - name: sprint-health
+    entry: workflows/sprint-health/workflow.md
+    target_agent: bmm/agents/sm.md
+    menu_patch_name: "sprint-health"
+```
+
+This requires creating:
+- `workflows/sprint-health/workflow.md` + step files + templates
+- `extensions/bmm-sm.yaml` (extension descriptor)
+- Menu item: `[SH] 📦 Sprint Health Check (Convoke Enhance)` in `sm.md`
+
+---
+
+## Verification Integration
+
+`verifyInstallation()` runs a 6-point check for the Enhance module (see `scripts/update/lib/validator.js` → `validateEnhanceModule()`):
+
+| # | Check | What It Validates |
+|---|---|---|
+| 1 | Directory exists | `_bmad/bme/_enhance/` is present |
+| 2 | Entry point resolves | Each `workflows[].entry` file exists on disk |
+| 3 | Menu patch present | Target agent file contains `<item>` with matching `name` attribute |
+| 4 | Config valid | `config.yaml` has required fields (`name`, `version`, `workflows[]`) |
+| 5 | Filesystem consistency | Workflow directory exists for each registered workflow name |
+| 6 | Skill wrapper exists | `.claude/skills/bmad-enhance-{name}/SKILL.md` is present |
+
+If the Enhance directory doesn't exist, all checks pass (Enhance is optional). If it exists, all 6 checks must pass.
+
+### Skill Wrapper
+
+The installer generates a skill wrapper at `.claude/skills/bmad-enhance-{workflow-name}/SKILL.md`:
+
+```yaml
+---
+name: bmad-enhance-{workflow-name}
+description: '[One-line description of what the workflow does]'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bme/_enhance/workflows/{workflow-name}/workflow.md, READ its entire contents and follow its directions exactly!
+```
+
+The installer also appends entries to `workflow-manifest.csv` and `skill-manifest.csv` (using `canonicalId` column for dedup).
+
+---
+
+## Quick Verification Checklist
+
+Minimum files to create/update for a valid new workflow:
+
+- [ ] `_bmad/bme/_enhance/workflows/{name}/workflow.md` — entry point
+- [ ] `_bmad/bme/_enhance/workflows/{name}/steps-*/step-*-*.md` — step files
+- [ ] `_bmad/bme/_enhance/workflows/{name}/templates/*.md` — templates (if needed)
+- [ ] `_bmad/bme/_enhance/config.yaml` — add workflow entry
+- [ ] `_bmad/bme/_enhance/extensions/bmm-{agent}.yaml` — extension descriptor
+- [ ] `.claude/skills/bmad-enhance-{name}/SKILL.md` — skill wrapper (installer creates this)
+- [ ] `workflow-manifest.csv` + `skill-manifest.csv` — manifest entries (installer creates these)
+
+Run `verifyInstallation()` after setup — all 6 checks should pass.

package/_bmad/bme/_enhance/workflows/initiatives-backlog/SKILL.md

@@ -0,0 +1,6 @@
+---
+name: bmad-enhance-initiatives-backlog
+description: 'Manage RICE initiatives backlog — triage review findings, rescore existing items, or bootstrap new backlogs. Use when the user says triage findings or manage backlog.'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/workflow.md, READ its entire contents and follow its directions exactly!

package/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-c/step-c-01-init.md

@@ -0,0 +1,106 @@
+---
+name: 'step-c-01-init'
+description: 'Check for existing backlog, warn on overwrite, initialize new backlog using format spec'
+nextStepFile: '{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-c/step-c-02-gather.md'
+outputFile: '{planning_artifacts}/initiatives-backlog.md'
+templateFile: '{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/templates/backlog-format-spec.md'
+workflowFile: '{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/workflow.md'
+---
+
+# Step 1: Initialization & Existing File Guard
+
+## STEP GOAL:
+
+Check whether a backlog file already exists at the output location, warn the user if so, and initialize a new backlog session using the backlog format specification.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+- 🛑 NEVER generate content without user input at overwrite prompt
+- 📖 CRITICAL: Read this complete step file before taking action
+- 🔄 CRITICAL: When loading next step with 'C', read the entire file
+- 📋 YOU ARE AN INITIALIZATION SPECIALIST setting up a new backlog
+
+### Role Reinforcement:
+- ✅ You are an **initialization specialist** — your job is to guard against accidental overwrites and prepare the session
+- ✅ Do not gather initiatives, score items, or write the backlog file — those are later steps
+- ✅ The user must explicitly confirm before any existing file is overwritten
+
+### Step-Specific Rules:
+- 🎯 Focus ONLY on existing file detection, overwrite confirmation, and session setup
+- 🚫 FORBIDDEN to gather initiatives (that is step-c-02's job)
+- 🚫 FORBIDDEN to score items (that is step-c-03's job)
+- 🚫 FORBIDDEN to write the backlog file (that is step-c-04's job)
+- 💬 Approach: check file, warn if needed, confirm readiness, move on
+
+## EXECUTION PROTOCOLS:
+- 🎯 Follow the MANDATORY SEQUENCE exactly
+- 📖 Load `{templateFile}` (backlog-format-spec.md) for structural reference — the format spec defines the file structure that step-c-04 will generate
+
+## CONTEXT BOUNDARIES:
+- Available context: Enhance config (loaded by workflow.md), existing backlog file (if present), backlog format spec template
+- Focus: File existence check and session initialization only
+- Limits: Do NOT gather, score, or write anything
+- Dependencies: workflow.md C dispatch (Create mode selected)
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
+
+### 0. Check for Existing Backlog File
+
+Check if a backlog file exists at `{outputFile}`.
+
+- **If found:** Display:
+
+  > **⚠️ Existing backlog detected at `{outputFile}`.**
+  >
+  > Create mode will generate a **new** backlog file, replacing the existing one. All current backlog data will be lost.
+  >
+  > **[Y] Yes, overwrite and create new backlog**
+  > **[X] Cancel and return to mode selection**
+
+  **ALWAYS halt and wait for user input.**
+
+  - IF Y: Continue to step 1.
+  - IF X: Display "Cancelling Create mode." then load, read the entire file, and execute `{workflowFile}` to return to T/R/C menu. **Do NOT proceed further.**
+  - IF any other input: Display "Please select **Y** or **X**." then redisplay the prompt.
+
+- **If NOT found:** Continue to step 1 silently.
+
+### 1. Load Backlog Format Specification
+
+Load `{templateFile}` (backlog-format-spec.md) and internalize:
+- **Section hierarchy** — All 7 required H2 sections and their order
+- **Table formats** — Category table (10 columns), Prioritized View (6 columns), Exploration Candidates (4 columns)
+- **Category names** — Existing convention (Documentation & Onboarding, Update & Migration System, etc.)
+- **Item ID format** — Category prefix letter + sequential number
+- **Provenance format** — "Added from Create mode, [date]"
+- **Changelog format** — Table with Date and Change columns, newest first
+
+### 2. Confirm Session Ready
+
+Display:
+
+> **Create Mode — New Backlog Initialized**
+>
+> A new RICE-scored backlog will be created at `{outputFile}`.
+>
+> **Next:** You'll describe your initiatives one at a time — title, description, and category. Then we'll score them using RICE methodology and generate your prioritized backlog.
+
+### 3. Present MENU OPTIONS
+
+Display: "**Select:** [C] Continue to initiative gathering"
+
+#### Menu Handling Logic:
+- IF C: Load, read the entire file, and execute `{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-c/step-c-02-gather.md`
+- IF any other input: Display "Enter **C** to continue to initiative gathering." then redisplay menu
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input after presenting the menu
+- ONLY proceed to next step when user selects 'C'
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
+### ✅ SUCCESS: Existing file check performed, overwrite warning shown if needed, format spec loaded, session initialized, proceeding to step-c-02
+### ❌ SYSTEM FAILURE: Existing file overwritten without warning, format spec not loaded, initiatives gathered prematurely, user not given overwrite choice
+**Master Rule:** Skipping steps is FORBIDDEN.

package/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-c/step-c-02-gather.md

@@ -0,0 +1,136 @@
+---
+name: 'step-c-02-gather'
+description: 'Interactively gather initiatives from the Product Owner with title, description, and category'
+nextStepFile: '{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-c/step-c-03-score.md'
+outputFile: '{planning_artifacts}/initiatives-backlog.md'
+templateFile: '{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/templates/backlog-format-spec.md'
+advancedElicitationTask: '{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.md'
+partyModeWorkflow: '{project-root}/_bmad/core/workflows/bmad-party-mode/workflow.md'
+---
+
+# Step 2: Interactive Initiative Gathering
+
+## STEP GOAL:
+
+Interactively gather initiatives from the Product Owner — each with a title, description, and category — building a list for RICE scoring in the next step.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+- 🛑 NEVER generate content without user input
+- 📖 CRITICAL: Read this complete step file before taking action
+- 🔄 CRITICAL: When loading next step with 'C', read the entire file
+- 📋 YOU ARE A GATHERING FACILITATOR collecting initiative descriptions
+
+### Role Reinforcement:
+- ✅ You are a **gathering facilitator** — your job is to collect and organize, not to score or write
+- ✅ Accept the user's descriptions faithfully — do not rewrite, editorialize, or merge initiatives
+- ✅ Suggest existing category names from the format spec but allow new categories
+- ✅ The user decides how many initiatives to add — you prompt until they say done
+
+### Step-Specific Rules:
+- 🎯 Focus ONLY on gathering initiative details (title, description, category)
+- 🚫 FORBIDDEN to propose RICE scores (that is step-c-03's job)
+- 🚫 FORBIDDEN to write the backlog file (that is step-c-04's job)
+- 🚫 FORBIDDEN to reorder, merge, or drop initiatives without user instruction
+- 💬 Approach: prompt for one initiative at a time, confirm capture, ask for next or done
+
+## EXECUTION PROTOCOLS:
+- 🎯 Follow the MANDATORY SEQUENCE exactly
+- 📖 Reference `{templateFile}` (backlog-format-spec.md) for category name suggestions
+- 💾 Track all gathered initiatives in a running list
+
+## CONTEXT BOUNDARIES:
+- Available context: Backlog format spec (for category names), session state from step-c-01
+- Focus: Initiative gathering only
+- Limits: Do NOT score, write to file, or analyze initiatives
+- Dependencies: step-c-01-init.md (session initialized)
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
+
+### 1. Initialize Gathering State
+
+Set up tracking:
+- `gathered_items` = []
+- `item_count` = 0
+
+### 2. Prompt for Initiative
+
+Display:
+
+> **Initiative #[item_count + 1]**
+>
+> Describe your initiative:
+> - **Title:** A short name for this initiative
+> - **Description:** What it does and why it matters
+> - **Category:** Suggested categories: Documentation & Onboarding, Update & Migration System, Testing & CI, Infrastructure, Agent Quality & Consistency, Platform & Product Vision — or name a new one
+>
+> *You can provide all three in one message, or just describe the initiative and I'll help structure it.*
+
+**ALWAYS halt and wait for user input.**
+
+### 3. Capture and Confirm
+
+Parse the user's input to extract:
+- **Title** — short, bold-formatted name
+- **Description** — one-line explanation
+- **Category** — one of the suggested categories or a new one
+
+If any field is unclear, ask the user to clarify before confirming.
+
+Display the captured initiative:
+
+> **Captured:**
+> - **Title:** [title]
+> - **Description:** [description]
+> - **Category:** [category]
+
+Add to `gathered_items` with: title, description, category, source = "Create mode".
+Increment `item_count`.
+
+### 4. Present Per-Initiative Menu
+
+Display:
+
+> **Initiatives gathered so far: [item_count]**
+>
+> **[N] Next** — Add another initiative
+> **[D] Done** — Finish gathering and proceed to scoring
+> **[A] Advanced Elicitation** — Deeper analysis to surface more initiatives
+> **[P] Party Mode** — Multi-perspective brainstorming for initiatives
+
+#### Menu Handling Logic:
+- IF N: Go to step 2 (prompt for next initiative).
+- IF D:
+  - **If `item_count` >= 1:** Display gathered items summary table, then go to step 5.
+  - **If `item_count` == 0:** Display "You must add at least one initiative before proceeding." then redisplay this menu.
+- IF A: Execute `{advancedElicitationTask}` for deeper initiative discovery. When finished, redisplay this menu.
+- IF P: Execute `{partyModeWorkflow}` for multi-perspective brainstorming. When finished, redisplay this menu.
+- IF any other input: Display "Unknown command. Use **N**, **D**, **A**, or **P**." then redisplay menu.
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input after presenting the menu
+- After A or P execution, return to this menu (not to the prompt)
+- The user may add as many initiatives as they want — no upper limit
+- Do NOT auto-continue — the user must explicitly select D to finish gathering
+
+### 5. Gathering Complete — Summary and Advance
+
+Display the complete gathered list:
+
+> **Gathering Complete — [item_count] initiatives collected**
+>
+> | # | Title | Category |
+> |---|-------|----------|
+> | 1 | [title] | [category] |
+> | 2 | [title] | [category] |
+> | ... | ... | ... |
+
+Then load, read the entire file, and execute `{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-c/step-c-03-score.md`, passing the `gathered_items` list.
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
+### ✅ SUCCESS: Each initiative captured with title, description, and category, user prompted for next or done, at least 1 initiative gathered, complete list passed to step-c-03
+### ❌ SYSTEM FAILURE: Initiatives scored prematurely, descriptions rewritten without user approval, zero initiatives accepted, user forced to use specific format, gathered items not passed to next step
+**Master Rule:** Skipping steps is FORBIDDEN.

package/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-c/step-c-03-score.md

@@ -0,0 +1,146 @@
+---
+name: 'step-c-03-score'
+description: 'Propose RICE scores for gathered initiatives in batch, validate with user, assign track labels'
+nextStepFile: '{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-c/step-c-04-prioritize.md'
+outputFile: '{planning_artifacts}/initiatives-backlog.md'
+templateFile: '{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/templates/rice-scoring-guide.md'
+advancedElicitationTask: '{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.md'
+partyModeWorkflow: '{project-root}/_bmad/core/workflows/bmad-party-mode/workflow.md'
+---
+
+# Step 3: Batch RICE Scoring
+
+## STEP GOAL:
+
+Propose RICE scores and Track assignments for all gathered initiatives, present the scored batch for user validation, and finalize scores before backlog generation.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+- 🛑 NEVER generate content without user input at the scoring menu
+- 📖 CRITICAL: Read this complete step file before taking action
+- 🔄 CRITICAL: When loading next step with 'C', read the entire file
+- 📋 YOU ARE A SCORING ANALYST proposing calibrated RICE scores
+
+### Role Reinforcement:
+- ✅ You are a **RICE scoring analyst** — systematic, calibrated, evidence-based
+- ✅ Propose scores grounded in the scoring guide's definitions and calibration examples
+- ✅ The user validates and adjusts your proposals — you propose, they decide
+- ✅ Assign Track labels based on initiative nature: maintenance/stability = "Keep the lights on", growth/new capability = "Move the needle"
+
+### Step-Specific Rules:
+- 🎯 Focus on scoring, rationale, Track assignment, and composite calculation
+- 🚫 FORBIDDEN to write to the backlog file (that is step-c-04's job)
+- 🚫 FORBIDDEN to re-gather or add new initiatives (that was step-c-02's job)
+- 💬 Approach: propose entire batch at once so user sees relative positioning, then collaborative refinement
+
+## EXECUTION PROTOCOLS:
+- 🎯 Follow the MANDATORY SEQUENCE exactly
+- 📖 Load `{templateFile}` for RICE factor definitions, scales, and calibration examples
+- 💾 Recalculate and re-sort after every score adjustment
+
+## CONTEXT BOUNDARIES:
+- Available context: Gathered initiatives from step-c-02, RICE scoring guide template
+- Focus: Scoring and user validation only
+- Limits: Do NOT write to backlog or modify gathered initiative descriptions
+- Dependencies: step-c-02-gather.md (gathered initiatives list)
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
+
+### 1. Load RICE Scoring Guide
+
+Load `{templateFile}` (rice-scoring-guide.md) and internalize:
+- **Factor definitions:** Reach (1-10), Impact (0.25-3), Confidence (20-100%), Effort (1-10)
+- **Guided questions** for each factor
+- **Calibration examples** (study the reasoning, not just the numbers)
+- **Composite formula:** Score = (R x I x C) / E, where C is decimal (e.g., 70% = 0.7)
+- **Score rounding:** One decimal place for display
+
+### 2. Propose RICE Scores and Track for All Initiatives
+
+For each gathered initiative, propose RICE scores using the guided questions:
+
+- **Reach (1-10):** "How many users per quarter will this affect?"
+- **Impact (0.25-3):** "What's the per-user impact?"
+- **Confidence (20-100%):** "How confident are we in these estimates?" Default to 50% when no direct evidence exists.
+- **Effort (1-10):** "Relative effort in story points?"
+- **Track:** "Keep the lights on" (maintenance, stability, bug fixes) or "Move the needle" (growth, new capability, strategic)
+
+For each score, write a **one-line rationale** explaining the scoring basis. Example:
+
+> **#1: Add output examples for Noah agent** — R:5 I:1 C:70% E:2 = 1.8 | Move the needle
+> *Reach 5: affects users checking agent outputs. Impact 1: helpful but workarounds exist. Confidence 70%: pattern validated with other agents. Effort 2: single file addition.*
+
+### 3. Calculate Composite Scores and Sort
+
+For each initiative:
+1. Calculate composite: Score = (Reach x Impact x Confidence) / Effort
+2. Round to one decimal place
+3. Verify score falls within expected range (~0.0 to ~30.0)
+
+Sort the batch:
+1. **Primary:** Descending by composite score
+2. **Tiebreak 1:** Higher Confidence first
+3. **Tiebreak 2:** Newer insertion order first
+
+### 4. Present Scoring Batch
+
+Display the scored results:
+
+> **RICE Scoring — Review Proposed Scores**
+>
+> **Initiatives scored: [N]**
+>
+> | # | Initiative | R | I | C | E | Score | Track | Rationale |
+> |---|-----------|---|---|---|---|-------|-------|-----------|
+> | 1 | [title] | 5 | 2 | 80% | 3 | 2.7 | Move the needle | [one-line rationale] |
+> | 2 | [title] | 3 | 1 | 60% | 2 | 0.9 | Keep the lights on | [one-line rationale] |
+>
+> *Sorted by composite score (descending). Formula: (R x I x C) / E*
+
+### 5. Present SCORING MENU OPTIONS
+
+Display:
+
+> **Adjust scores or finalize:**
+>
+> **Score adjustments** (by item number):
+> - `#N R [value]` — Change Reach (1-10)
+> - `#N I [value]` — Change Impact (0.25, 0.5, 1, 2, or 3)
+> - `#N CF [value]` — Change Confidence (20-100%)
+> - `#N E [value]` — Change Effort (1-10)
+> - `#N T [value]` — Change Track ("keep" or "move")
+>
+> **Batch editing:**
+> - `D #N` — Drop item #N from the batch (will not be added to backlog)
+>
+> **[A] Advanced Elicitation** — Deeper analysis of scoring rationale
+> **[P] Party Mode** — Multi-perspective scoring discussion
+> **[C] Continue** — Finalize scores and proceed to backlog generation
+
+#### Menu Handling Logic:
+- IF `#N R [value]`: Update Reach for item #N. Recalculate composite. Re-sort batch. Redisplay table and menu.
+- IF `#N I [value]`: Update Impact for item #N. Recalculate composite. Re-sort batch. Redisplay table and menu.
+- IF `#N CF [value]`: Update Confidence for item #N. Recalculate composite. Re-sort batch. Redisplay table and menu.
+- IF `#N E [value]`: Update Effort for item #N. Recalculate composite. Re-sort batch. Redisplay table and menu.
+- IF `#N T [value]`: Update Track for item #N ("keep" = "Keep the lights on", "move" = "Move the needle"). Redisplay table and menu.
+- IF `D #N`: Remove item #N from the scoring batch. Redisplay table and menu.
+- IF A: Execute `{advancedElicitationTask}` for deeper scoring analysis, and when finished redisplay the menu.
+- IF P: Execute `{partyModeWorkflow}` for multi-perspective scoring discussion, and when finished redisplay the menu.
+- IF C: Finalize the scored batch. Load, read the entire file, and execute `{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-c/step-c-04-prioritize.md`
+- IF any other input: Display "Unknown command. Use `#N R/I/CF/E/T [value]`, `D #N`, **A**, **P**, or **C** to continue." then redisplay menu.
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input after presenting the menu
+- After EVERY score or Track adjustment, recalculate composite, re-sort, and redisplay the full table AND the menu
+- The user may make multiple adjustments before pressing C
+- ONLY proceed to step-c-04 when user selects 'C'
+- After A or P execution, return to this menu
+- Do NOT auto-continue — the user must explicitly approve the scores
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
+### ✅ SUCCESS: All initiatives scored with calibrated RICE components, rationale, and Track assignment, composites calculated correctly, batch sorted by score, user validated scores, finalized batch passed to step-c-04
+### ❌ SYSTEM FAILURE: Scores proposed without rationale, composite formula wrong, Track not assigned, scores outside valid ranges, user not given validation opportunity, items written to backlog prematurely
+**Master Rule:** Skipping steps is FORBIDDEN.