convoke-agents 2.3.1 → 3.0.0

package/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-t/step-t-01-ingest.md

@@ -0,0 +1,86 @@
+---
+name: 'step-t-01-ingest'
+description: 'Accept text input — review transcript, meeting notes, or any findings source'
+nextStepFile: '{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-t/step-t-02-extract.md'
+outputFile: '{planning_artifacts}/initiatives-backlog.md'
+---
+
+# Step 1: Ingest Review Findings
+
+## STEP GOAL:
+
+Accept the Product Owner's text input (review transcript, meeting notes, audit output, or any findings source) and prepare it for extraction 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 FACILITATOR, not a content generator
+
+### Role Reinforcement:
+- ✅ You are a **findings intake specialist** — your job is to receive and preserve input, not analyze it
+- ✅ Accept whatever format the user provides — do not ask them to restructure
+- ✅ The user brings the review content; you bring careful preservation
+
+### Step-Specific Rules:
+- 🎯 Focus ONLY on accepting and preserving input text
+- 🚫 FORBIDDEN to extract findings, classify, or score in this step — that is step-t-02's job
+- 🚫 FORBIDDEN to truncate, summarize, or skip any part of the input regardless of length (FR46)
+- 💬 Approach: brief prompts, minimal overhead, get to the content quickly
+
+## EXECUTION PROTOCOLS:
+- 🎯 Follow the MANDATORY SEQUENCE exactly
+- 📖 Load existing backlog if present — it will be needed for overlap detection in step-t-02
+
+## CONTEXT BOUNDARIES:
+- Available context: Enhance config (loaded by workflow.md), existing backlog file (if present)
+- Focus: Accepting user input only
+- Limits: Do NOT analyze, classify, or score input
+- Dependencies: workflow.md T dispatch (completed in Story 1.3)
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
+
+### 1. Check for Existing Backlog
+
+Check if an existing backlog file exists at `{planning_artifacts}/initiatives-backlog.md`.
+
+- **If found:** Load it silently — it will be used for overlap detection in step-t-02. Briefly note to the user: "Existing backlog loaded — overlap detection will be available during extraction."
+- **If not found:** Note silently — step-t-02 will skip overlap detection. Briefly note: "No existing backlog found — a new one will be created."
+
+### 2. Prompt for Text Input
+
+Display:
+
+> **Triage Mode — Paste your review findings below.**
+>
+> Accepted formats: review transcripts, meeting notes, audit outputs, party-mode outputs, code review findings, retrospective notes, or any text containing actionable observations.
+>
+> Paste your content and press Enter when done.
+
+### 3. Accept and Preserve Input
+
+- Accept the user's complete text input
+- Preserve it exactly as provided — do not modify, reformat, or summarize
+- Process the **entire** input regardless of length (FR46)
+- Confirm receipt: "Received [N] lines of input. Ready to extract findings."
+
+### 4. Present MENU OPTIONS
+
+Display: "**Select:** [C] Continue to finding extraction"
+
+#### Menu Handling Logic:
+- IF C: Load, read the entire file, and execute `{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-t/step-t-02-extract.md`
+- IF any other input: Display "Enter **C** to continue to finding extraction." 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: User's complete text input accepted and preserved, existing backlog loaded if present, proceeding to step-t-02
+### ❌ SYSTEM FAILURE: Input truncated, content modified, findings extracted prematurely, or user forced to restructure input
+**Master Rule:** Skipping steps is FORBIDDEN.

package/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-t/step-t-02-extract.md

@@ -0,0 +1,169 @@
+---
+name: 'step-t-02-extract'
+description: 'Extract actionable findings from input, classify, detect overlaps, and validate at Gate 1'
+nextStepFile: '{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-t/step-t-03-score.md'
+outputFile: '{planning_artifacts}/initiatives-backlog.md'
+templateFile: '{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/templates/backlog-format-spec.md'
+---
+
+# Step 2: Extract Findings & Gate 1 Validation
+
+## STEP GOAL:
+
+Extract actionable findings from the ingested text, classify each into a backlog category, detect overlaps with existing backlog items, and present the batch for user validation at Gate 1.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+- 🛑 NEVER generate content without user input at Gate 1
+- 📖 CRITICAL: Read this complete step file before taking action
+- 🔄 CRITICAL: When loading next step with 'C', read the entire file
+- 📋 YOU ARE AN ANALYST extracting structured findings from unstructured input
+
+### Role Reinforcement:
+- ✅ You are a **findings extraction analyst** — thorough, systematic, evidence-based
+- ✅ Extract what the input actually says — do not invent findings or impose interpretations
+- ✅ The user validates your extraction at Gate 1 — you propose, they decide
+
+### Step-Specific Rules:
+- 🎯 Focus on extraction, classification, and overlap detection
+- 🚫 FORBIDDEN to score findings (RICE scoring is step-t-03's job)
+- 🚫 FORBIDDEN to write to the backlog file (that is step-t-04's job)
+- 🚫 FORBIDDEN to truncate or skip any part of the input text (FR46)
+- 💬 Approach: systematic extraction, then collaborative validation at Gate 1
+
+## EXECUTION PROTOCOLS:
+- 🎯 Follow the MANDATORY SEQUENCE exactly
+- 📖 Load {templateFile} for category reference
+- 💾 Track extraction state — redisplay updated batch after every Gate 1 edit
+
+## CONTEXT BOUNDARIES:
+- Available context: User's input text (from step-t-01), existing backlog (if loaded), backlog format spec template
+- Focus: Extraction and Gate 1 validation only
+- Limits: Do NOT score or write to backlog
+- Dependencies: step-t-01-ingest.md (input text accepted)
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
+
+### 1. Load Category Reference
+
+Load `{templateFile}` (backlog-format-spec.md) and extract the category names from the "Category Names" section. Current categories:
+
+- Documentation & Onboarding
+- Update & Migration System
+- Testing & CI
+- Infrastructure
+- Agent Quality & Consistency
+- Platform & Product Vision
+
+New categories may be proposed if a finding doesn't fit any existing category.
+
+### 2. Extract Actionable Findings
+
+Process the **complete** input text from step-t-01. Do NOT truncate, summarize, or skip sections (FR46).
+
+For each passage in the input, determine if it is **actionable**. A finding is actionable if it:
+- **Proposes a change** (something should be different)
+- **Identifies a gap** (something is missing)
+- **Flags a risk** (something could go wrong)
+
+Non-actionable content (general comments, praise, questions without implied action, status updates) should be set aside as **observations** — they are NOT included in the extraction batch but may be escalated at Gate 1.
+
+For each actionable finding, record:
+1. **Finding number** — sequential (1, 2, 3...)
+2. **Title** — concise summary (matches backlog Initiative column style)
+3. **Category** — one of the categories from step 1 (or propose a new one)
+4. **Source reference** — which part of the input it came from (e.g., "paragraph 3", "under 'Performance Issues' heading", "line about caching") (FR4)
+5. **Type** — Change / Gap / Risk
+
+### 3. Detect Overlaps with Existing Backlog
+
+**Skip this step if no existing backlog was loaded in step-t-01.**
+
+For each extracted finding, compare against existing backlog items by semantic similarity (title + description). Flag potential overlaps when a finding appears to address the same concern as an existing item.
+
+For each overlap flag, record:
+- The existing item's **ID** (e.g., D2, P4)
+- The existing item's **title**
+- Brief explanation of why it might overlap
+
+### 4. Handle Zero Findings
+
+**If zero actionable findings were extracted:**
+
+Display:
+
+> **No actionable findings extracted from the input.**
+>
+> The input contained no content that proposes a change, identifies a gap, or flags a risk.
+>
+> **Options:**
+> - Paste a specific passage you'd like me to re-examine
+> - Type **X** to return to the mode selection menu
+
+- If user pastes text → re-examine that specific passage for findings, then return to this decision point
+- If user types X → re-load `{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/workflow.md` to return to T/R/C menu
+
+**If observations (non-actionable) were found**, list them and note they can be escalated at Gate 1.
+
+**Do NOT proceed to Gate 1 if there are zero findings.**
+
+### 5. Present Extraction Batch (Gate 1)
+
+Display the extraction results in a numbered list:
+
+> **Gate 1 — Review Extracted Findings**
+>
+> **Actionable findings extracted: [N]**
+>
+> | # | Finding | Category | Source | Type | Overlap |
+> |---|---------|----------|--------|------|---------|
+> | 1 | [title] | [category] | [source ref] | Change | — |
+> | 2 | [title] | [category] | [source ref] | Gap | ⚠️ Overlaps D2: "[existing title]" |
+> | 3 | [title] | [category] | [source ref] | Risk | — |
+>
+> **Observations (not included — escalate with `E` if actionable):**
+> - [observation 1]
+> - [observation 2]
+
+### 6. Present GATE 1 MENU OPTIONS
+
+Display:
+
+> **Gate 1 — Edit the extraction batch:**
+>
+> **Overlap resolution** (for flagged items only):
+> - `merge #N` — Absorb finding into the existing overlapping item
+> - `skip #N` — Drop finding (existing item is sufficient)
+> - `new #N` — Override overlap flag, keep as separate new item
+>
+> **Batch editing:**
+> - `E #N` — Escalate observation #N to actionable finding
+> - `+ [title — description]` — Add a finding the workflow missed
+> - `R #N` — Remove finding #N from the batch
+>
+> **[C] Continue** — Finalize batch and proceed to RICE scoring
+
+#### Menu Handling Logic:
+- IF `merge #N`: Mark finding #N as merged with existing item. Remove from batch. Redisplay updated batch and menu.
+- IF `skip #N`: Remove finding #N from batch. Redisplay updated batch and menu.
+- IF `new #N`: Clear overlap flag on finding #N (will be added as new item). Redisplay updated batch and menu.
+- IF `E #N`: Move observation #N into the findings batch as actionable. Assign a category and source ref. Redisplay updated batch and menu.
+- IF `+ [text]`: Add a new finding to the batch. Ask user for category if not obvious. Redisplay updated batch and menu.
+- IF `R #N`: Remove finding #N from the batch. Redisplay updated batch and menu.
+- IF C: Finalize the batch. Load, read the entire file, and execute `{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-t/step-t-03-score.md`
+- IF any other input: Display "Unknown command. Use `merge/skip/new #N`, `E #N`, `+ [text]`, `R #N`, or **C** to continue." then redisplay menu.
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input after presenting the menu
+- After EVERY edit action, redisplay the updated extraction batch table AND the menu
+- The user may perform multiple edits before pressing C
+- ONLY proceed to step-t-03 when user selects 'C'
+- Do NOT auto-continue — the user must explicitly approve the batch
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
+### ✅ SUCCESS: All actionable findings extracted with categories and source refs, overlaps detected, user validated batch at Gate 1, confirmed findings passed to step-t-03
+### ❌ SYSTEM FAILURE: Input truncated, findings invented (not from input), overlaps missed, user not given Gate 1 validation opportunity, findings scored prematurely
+**Master Rule:** Skipping steps is FORBIDDEN.

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

@@ -0,0 +1,147 @@
+---
+name: 'step-t-03-score'
+description: 'Propose RICE scores for confirmed findings, validate at Gate 2, calculate composite scores'
+nextStepFile: '{project-root}/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-t/step-t-04-update.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: RICE Scoring & Gate 2 Validation
+
+## STEP GOAL:
+
+Propose RICE scores for each confirmed finding from Gate 1, present the scored batch for user validation at Gate 2, and calculate composite scores with proper sorting.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+- 🛑 NEVER generate content without user input at Gate 2
+- 📖 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 at Gate 2 — you propose, they decide
+- ✅ Compare proposed scores against existing backlog items for calibration consistency
+
+### Step-Specific Rules:
+- 🎯 Focus on scoring, rationale, and composite calculation
+- 🚫 FORBIDDEN to write to the backlog file (that is step-t-04's job)
+- 🚫 FORBIDDEN to re-extract or re-classify findings (that was step-t-02's job)
+- 🚫 FORBIDDEN to add new findings at Gate 2 (that was Gate 1's job — only drops allowed here)
+- 💬 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 Gate 2 adjustment
+
+## CONTEXT BOUNDARIES:
+- Available context: Confirmed findings from Gate 1, existing backlog (if loaded), RICE scoring guide template
+- Focus: Scoring and Gate 2 validation only
+- Limits: Do NOT write to backlog or modify extraction results
+- Dependencies: step-t-02-extract.md (confirmed findings from Gate 1)
+
+## 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** from the existing backlog (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 for All Findings
+
+For each confirmed finding from Gate 1, 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?"
+
+For each score, write a **one-line rationale** explaining the scoring basis (FR12). Example:
+
+> **#1: Add output examples for Noah agent** — R:5 I:1 C:70% E:2 = 1.8
+> *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.*
+
+**Calibration check:** Mentally compare each proposed score against 2-3 existing backlog items at similar scale. If the score would rank the item significantly above or below where it "feels" relative to those items, revisit the component scores.
+
+### 3. Calculate Composite Scores and Sort
+
+For each finding:
+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; existing backlog ranges ~0.2 to ~10.0)
+
+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 (Gate 2)
+
+Display the scored results:
+
+> **Gate 2 — Review Proposed RICE Scores**
+>
+> **Scored findings: [N]**
+>
+> | # | Finding | R | I | C | E | Score | Rationale |
+> |---|---------|---|---|---|---|-------|-----------|
+> | 1 | [title] | 5 | 2 | 80% | 3 | 2.7 | [one-line rationale] |
+> | 2 | [title] | 3 | 1 | 60% | 2 | 0.9 | [one-line rationale] |
+> | 3 | [title] | 7 | 0.5 | 50% | 1 | 1.8 | [one-line rationale] |
+>
+> *Sorted by composite score (descending). Formula: (R x I x C) / E*
+
+### 5. Present GATE 2 MENU OPTIONS
+
+Display:
+
+> **Gate 2 — 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)
+>
+> **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 update
+
+#### 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 `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-t/step-t-04-update.md`
+- IF any other input: Display "Unknown command. Use `#N R/I/CF/E [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 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-t-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 findings scored with calibrated RICE components and rationale, composites calculated correctly, batch sorted by score, user validated at Gate 2, finalized scores passed to step-t-04
+### ❌ SYSTEM FAILURE: Scores proposed without rationale, composite formula wrong, scores outside valid ranges, user not given Gate 2 validation, findings written to backlog prematurely
+**Master Rule:** Skipping steps is FORBIDDEN.

package/_bmad/bme/_enhance/workflows/initiatives-backlog/steps-t/step-t-04-update.md

@@ -0,0 +1,155 @@
+---
+name: 'step-t-04-update'
+description: 'Validate backlog structure, append scored items safely, regenerate prioritized view, and present completion summary'
+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 4: Backlog Update, Safety & Completion
+
+## STEP GOAL:
+
+Validate backlog structure, safely append scored items from Gate 2, regenerate the prioritized view, and present a completion summary before returning to the T/R/C menu.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+- 🛑 NEVER generate content without user input at validation mismatch prompt
+- 📖 CRITICAL: Read this complete step file before taking action
+- 🔄 CRITICAL: When returning to menu, read the entire workflow file
+- 📋 YOU ARE A BACKLOG OPERATIONS SPECIALIST performing safe, structured writes
+
+### Role Reinforcement:
+- ✅ You are a **backlog operations specialist** — precise, non-destructive, append-only
+- ✅ Preserve all existing content — never delete, overwrite, or reorder existing rows
+- ✅ The Prioritized View is the ONLY section regenerated from scratch
+- ✅ All output must be standard markdown — no HTML, no proprietary syntax
+
+### Step-Specific Rules:
+- 🎯 Focus on validation, safe writes, and completion reporting
+- 🚫 FORBIDDEN to delete or reorder existing backlog items (FR18, NFR1)
+- 🚫 FORBIDDEN to re-score items (scoring was finalized at Gate 2)
+- 🚫 FORBIDDEN to modify step-t-01, step-t-02, or step-t-03
+- 💬 Approach: validate first, write safely, summarize clearly
+
+## EXECUTION PROTOCOLS:
+- 🎯 Follow the MANDATORY SEQUENCE exactly
+- 📖 Load `{templateFile}` (backlog-format-spec.md) for structural validation rules and table formats
+- 💾 Write to `{outputFile}` only after validation passes (or user overrides)
+
+## CONTEXT BOUNDARIES:
+- Available context: Scored findings from Gate 2, existing backlog file, backlog format spec template
+- Focus: Structural validation, safe append, prioritized view regeneration, completion summary
+- Limits: Do NOT re-score, re-extract, or re-classify items
+- Dependencies: step-t-03-score.md (scored findings from Gate 2)
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise.
+
+### 1. Pre-Write Validation
+
+Load `{outputFile}` (existing backlog) and validate structural integrity:
+
+1. **Section heading anchors** — All 7 required H2 sections exist in correct order:
+   - `## RICE Scoring Guide`
+   - `## Backlog`
+   - `## Exploration Candidates`
+   - `## Epic Groupings`
+   - `## Prioritized View (by RICE Score)`
+   - `## Completed`
+   - `## Change Log`
+2. **Prioritized view table** — Has exactly 6 columns (Rank, #, Initiative, Score, Track, Category)
+3. **Category tables** — Each table under `## Backlog` has exactly 10 columns (#, Initiative, Source, R, I, C, E, Score, Track, Status)
+4. **Change Log section** — The `## Change Log` H2 section exists with a table
+
+If ALL checks pass, proceed directly to step 3 (Append Items).
+
+### 2. Mismatch Handling
+
+If ANY validation check fails, present the specific mismatch(es):
+
+> **Pre-Write Validation — Structural Mismatch Detected**
+>
+> [List each failed check with details]
+>
+> **[Y] Yes, proceed anyway**
+> **[X] Abort and return to menu**
+
+**ALWAYS halt and wait for user input.**
+
+- IF Y: Continue to step 3 (Append Items)
+- IF X: Display "Aborting backlog update." then load, read the entire file, and execute `{workflowFile}` to return to mode selection
+- IF any other input: Display "Please select **Y** or **X**." then redisplay the prompt
+
+### 3. Append Items
+
+For each scored item from Gate 2:
+
+1. **Find target category** — Locate the H3 section under `## Backlog` matching the item's category
+2. **Create category if needed** — If category doesn't exist, add a new H3 heading with a 10-column table at the end of `## Backlog` (before `## Exploration Candidates`)
+3. **Generate item ID** — Use category prefix letter (D/U/T/I/A/P) + next number (increment from highest existing in that category)
+4. **Append row** — Add new row to end of category table. NEVER delete, overwrite, or reorder existing rows
+5. **Add provenance** — Include in the Initiative description: `Added from [source], [date]` where source is the input origin from step-t-01 and date is the current session date
+
+**Column format** (10 columns per backlog-format-spec.md):
+```
+| [ID] | **[Title]** — [description]. Added from [source], [date] | [source ref] | [R] | [I] | [C]% | [E] | [score] | [track] | Backlog |
+```
+
+**Important:** Triage Gate 2 adjustments are the initial score — no rescore provenance is generated.
+
+### 4. Regenerate Prioritized View
+
+Rebuild the `## Prioritized View (by RICE Score)` table from scratch:
+
+1. Collect ALL active items from all category tables (existing + newly appended)
+2. Exclude items with Status "Done" or items in the `## Completed` section
+3. Sort by composite RICE score descending
+4. Tiebreak: (1) Higher Confidence first, (2) Newer insertion order first
+5. Generate sequential rank numbers starting at 1
+
+Table format (6 columns):
+```
+| Rank | # | Initiative | Score | Track | Category |
+|------|---|-----------|-------|-------|----------|
+```
+
+### 5. Add Changelog Entry
+
+Prepend a new row to the `## Change Log` table (newest first):
+
+```
+| YYYY-MM-DD | Triage: Added [N] items ([categories affected]). [Any merge notes if applicable] |
+```
+
+### 6. Update Last Updated Date
+
+Set the metadata header `Last Updated` field to the current date (YYYY-MM-DD format).
+
+### 7. Completion Summary & Return to Menu
+
+After successful write, display:
+
+> **Triage Complete**
+>
+> **Items added:** [N]
+> **Items merged:** [N] (absorbed into existing items at Gate 1)
+> **Categories affected:** [list]
+>
+> **New Top 3 Positions:**
+> 1. [#ID] [title] — Score: [X.X]
+> 2. [#ID] [title] — Score: [X.X]
+> 3. [#ID] [title] — Score: [X.X]
+
+Then return to the T/R/C menu:
+
+> Loading `{workflowFile}` to return to mode selection...
+
+Load, read the entire file, and execute `{workflowFile}`.
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS:
+### ✅ SUCCESS: Pre-write validation performed, existing content preserved, items appended with correct IDs and provenance, prioritized view regenerated with all items sorted correctly, changelog updated, completion summary displayed with top 3, T/R/C menu re-presented
+### ❌ SYSTEM FAILURE: Existing backlog content deleted/overwritten/reordered, items written without validation, wrong IDs or missing provenance, prioritized view not regenerated, no completion summary, no return to menu
+**Master Rule:** Skipping steps is FORBIDDEN.