diff --git a/src/bmm-skills/4-implementation/bmad-create-story/workflow.md b/src/bmm-skills/4-implementation/bmad-create-story/workflow.md
index 0acd8666b5..93516d97ee 100644
--- a/src/bmm-skills/4-implementation/bmad-create-story/workflow.md
+++ b/src/bmm-skills/4-implementation/bmad-create-story/workflow.md
@@ -34,6 +34,7 @@ Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
- `ux_file` = `{planning_artifacts}/*ux*.md`
- `story_title` = "" (will be elicited if not derivable)
- `project_context` = `**/project-context.md` (load if exists)
+- `deferred_work_file` = `{implementation_artifacts}/deferred-work.md`
- `default_output_file` = `{implementation_artifacts}/{{story_key}}.md`
### Input Files
@@ -44,6 +45,7 @@ Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
| architecture | Architecture (fallback - epics file should have relevant sections) | whole: `{planning_artifacts}/*architecture*.md`, sharded: `{planning_artifacts}/*architecture*/*.md` | SELECTIVE_LOAD |
| ux | UX design (fallback - epics file should have relevant sections) | whole: `{planning_artifacts}/*ux*.md`, sharded: `{planning_artifacts}/*ux*/*.md` | SELECTIVE_LOAD |
| epics | Enhanced epics+stories file with BDD and source hints | whole: `{planning_artifacts}/*epic*.md`, sharded: `{planning_artifacts}/*epic*/*.md` | SELECTIVE_LOAD |
+| deferred_work | Deferred items from code reviews (optional) | `{deferred_work_file}` | FULL_LOAD (optional) |
---
@@ -232,6 +234,54 @@ Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
all learnings that could impact current story implementation
+
+
+ Load {deferred_work_file} completely
+ Parse all deferred items. The file uses level-2 headings produced by bmad-code-review:
+ `## Deferred from: code review of story-X.Y (YYYY-MM-DD)`
+ Each heading is followed by bullet items (one per deferred finding).
+
+ For each bullet item extract:
+ - File paths mentioned (e.g., [src/foo.ts:42])
+ - Originating review: the heading text above the bullet (e.g., "code review of story-2.3 (2026-03-18)")
+ - Description text: the bullet content
+ - Category: if the producer included an explicit category, use it; otherwise derive heuristically from keywords in the description:
+ - "security" / "auth" / "injection" / "XSS" / "CSRF" → security
+ - "bug" / "crash" / "error" / "null" / "undefined" / "NaN" → bug
+ - "performance" / "slow" / "N+1" / "cache" → performance
+ - "style" / "lint" / "formatting" / "naming" → style
+ - otherwise → tech-debt
+ - Set `inferred_category = true` when the category was derived heuristically
+
+
+ From epics content and architecture analysis, build a list of files this story will likely touch:
+ - Files explicitly mentioned in story requirements
+ - Files in modules/directories related to the story's feature area
+ - Files that share dependencies with story components
+
+
+ Match deferred items against the story's file list:
+ - EXACT match: deferred item references a file the story will modify
+ - DIRECTORY match: deferred item is in the same directory/module
+ - COMPONENT match: deferred item affects a component the story depends on
+
+
+
+ Store {{matched_deferred_items}} for inclusion in the story file
+ Set {{matched_count}} = number of items in {{matched_deferred_items}}
+ Classify matches by priority:
+ - HIGH: security fixes, bugs in files this story will modify
+ - MEDIUM: tech-debt in the same module, performance issues in touched code
+ - LOW: style issues, minor refactors in adjacent files
+
+
+
+
+
+ Set {{matched_deferred_items}} = empty
+
+
+
@@ -324,6 +374,24 @@ Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
git_intelligence_summary
+
+
+ In the Dev Notes section, add a subsection:
+
+### Deferred Items to Address
+
+The following items were deferred from previous code reviews and overlap with files/modules this story will touch. Address these during implementation where practical.
+
+{{#each matched_deferred_items}}
+- **[{{priority}}]** {{description}} `[{{file_ref}}]` — _from {{origin_review}}_
+{{/each}}
+
+
+ In the Tasks/Subtasks section, add corresponding subtasks for HIGH-priority deferred items:
+ - [ ] [Deferred] {{description}} [{{file_ref}}] (from previous review)
+
+
+
latest_tech_information
diff --git a/src/bmm-skills/4-implementation/bmad-retrospective/workflow.md b/src/bmm-skills/4-implementation/bmad-retrospective/workflow.md
index 3f56f728c9..cab9a8d3a3 100644
--- a/src/bmm-skills/4-implementation/bmad-retrospective/workflow.md
+++ b/src/bmm-skills/4-implementation/bmad-retrospective/workflow.md
@@ -38,6 +38,7 @@ Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
### Paths
- `sprint_status_file` = `{implementation_artifacts}/sprint-status.yaml`
+- `deferred_work_file` = `{implementation_artifacts}/deferred-work.md`
### Input Files
@@ -48,6 +49,7 @@ Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
| architecture | System architecture for context | whole: `{planning_artifacts}/*architecture*.md`, sharded: `{planning_artifacts}/*architecture*/*.md` | FULL_LOAD |
| prd | Product requirements for context | whole: `{planning_artifacts}/*prd*.md`, sharded: `{planning_artifacts}/*prd*/*.md` | FULL_LOAD |
| document_project | Brownfield project documentation (optional) | sharded: `{planning_artifacts}/*.md` | INDEX_GUIDED |
+| deferred_work | Deferred items from code reviews | `{deferred_work_file}` | FULL_LOAD (optional) |
### Required Inputs
@@ -247,6 +249,41 @@ Charlie (Senior Dev): "Good idea - those dev notes always have gold in them."
- Track bug patterns or regression issues
- Document test coverage gaps
+**Deferred Work Backlog Analysis:**
+
+
+ Load {deferred_work_file} completely
+ Parse all deferred items and compute:
+
+ - Total items deferred across all reviews
+ - Items originating from this epic's stories (match by level-2 headings: `## Deferred from: code review of story-{{epic_number}}.* (YYYY-MM-DD)`)
+ - Items originating from previous epics (carried forward — headings referencing other epic numbers)
+ - Items that were addressed during this epic (cross-reference with story file lists and git history)
+ - Items still outstanding
+
+ Classify outstanding items by severity. If the producer included an explicit category use it; otherwise derive heuristically from description keywords (security/auth/injection → security; bug/crash/error/null → bug; performance/slow/cache → performance; style/lint/naming → style; default → tech-debt):
+
+ - Security issues: count and list
+ - Bugs: count and list
+ - Tech-debt: count and list
+ - Style/minor: count and list
+
+ Store deferred work stats:
+
+ - {{deferred_created_this_epic}}: items deferred during this epic's reviews
+ - {{deferred_resolved_this_epic}}: items addressed during this epic
+ - {{deferred_carried_forward}}: items still outstanding
+ - {{deferred_high_priority}}: security + bug items still outstanding
+
+ IF {{deferred_carried_forward}} > 0: flag for discussion in retrospective as a quality concern
+ IF {{deferred_high_priority}} > 0: flag as critical — high-priority items are aging without resolution
+
+
+
+ Set {{deferred_created_this_epic}} = 0, {{deferred_resolved_this_epic}} = 0, {{deferred_carried_forward}} = 0
+ Note: no deferred work file found — either no code reviews ran or all findings were resolved inline
+
+
Synthesize patterns across all stories:
**Common Struggles:**
@@ -507,6 +544,13 @@ Quality and Technical:
- Test coverage: {{coverage_info}}
- Production incidents: {{incident_count}}
+Deferred Work (from code reviews):
+
+- Created this epic: {{deferred_created_this_epic}}
+- Resolved this epic: {{deferred_resolved_this_epic}}
+- Carried forward: {{deferred_carried_forward}}{{#if deferred_high_priority}}
+- ⚠️ High-priority outstanding: {{deferred_high_priority}} (security/bugs){{/if}}
+
Business Outcomes:
- Goals achieved: {{goals_met}}/{{total_goals}}
@@ -1352,6 +1396,7 @@ Bob (Scrum Master): "See you all when prep work is done. Meeting adjourned!"
- Action items with owners and timelines
- Preparation tasks for next epic
- Critical path items
+- Deferred work summary (items created, resolved, carried forward, high-priority outstanding)
- Significant discoveries and epic update recommendations (if any)
- Readiness assessment
- Commitments and next steps
diff --git a/src/bmm-skills/4-implementation/bmad-sprint-status/workflow.md b/src/bmm-skills/4-implementation/bmad-sprint-status/workflow.md
index 1def1c8f3f..f69ee29101 100644
--- a/src/bmm-skills/4-implementation/bmad-sprint-status/workflow.md
+++ b/src/bmm-skills/4-implementation/bmad-sprint-status/workflow.md
@@ -21,12 +21,14 @@ Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
### Paths
- `sprint_status_file` = `{implementation_artifacts}/sprint-status.yaml`
+- `deferred_work_file` = `{implementation_artifacts}/deferred-work.md`
### Input Files
| Input | Path | Load Strategy |
|-------|------|---------------|
| Sprint status | `{sprint_status_file}` | FULL_LOAD |
+| Deferred work | `{deferred_work_file}` | FULL_LOAD (optional) |
### Context
@@ -118,6 +120,25 @@ Enter corrections (e.g., "1=in-progress, 2=backlog") or "skip" to continue witho
- IF `last_updated` timestamp is more than 7 days old (or `last_updated` is missing, fall back to `generated`): warn "sprint-status.yaml may be stale"
- IF any story key doesn't match an epic pattern (e.g., story "5-1-..." but no "epic-5"): warn "orphaned story detected"
- IF any epic has status in-progress but has no associated stories: warn "in-progress epic has no stories"
+
+Analyze deferred work backlog (if {deferred_work_file} exists):
+
+
+ Parse all deferred items from {deferred_work_file}. The file uses level-2 headings produced by bmad-code-review:
+ `## Deferred from: code review of story-X.Y (YYYY-MM-DD)`
+ Each heading is followed by bullet items (one per deferred finding).
+
+ Count total deferred items (bullet items, not headings)
+ Group items by originating review/story (derived from the heading above each group)
+ Classify items by severity: if the item includes an explicit category use it; otherwise derive heuristically from description keywords (security/auth/injection → security; bug/crash/error/null → bug; performance/slow/cache → performance; style/lint/naming → style; default → tech-debt)
+ Store counts: {{deferred_total}}, {{deferred_high}} (security/bug), {{deferred_medium}} (tech-debt/performance), {{deferred_low}} (style/minor)
+ IF {{deferred_total}} > 20: add risk "Deferred work backlog is large ({{deferred_total}} items) — consider triaging with SM agent"
+ IF {{deferred_high}} > 0: add risk "{{deferred_high}} high-priority deferred items (security/bugs) need attention"
+
+
+
+ Set {{deferred_total}} = 0, {{deferred_high}} = 0, {{deferred_medium}} = 0, {{deferred_low}} = 0
+
@@ -144,6 +165,10 @@ Enter corrections (e.g., "1=in-progress, 2=backlog") or "skip" to continue witho
**Epics:** backlog {{epic_backlog}}, in-progress {{epic_in_progress}}, done {{epic_done}}
+{{#if deferred_total}}
+**Deferred Work:** {{deferred_total}} items ({{deferred_high}} high, {{deferred_medium}} medium, {{deferred_low}} low)
+{{/if}}
+
**Next Recommendation:** /bmad:bmm:workflows:{{next_workflow_id}} ({{next_story_id}})
{{#if risks}}
@@ -195,7 +220,7 @@ If the command targets a story, set `story_key={{next_story_id}}` when prompted.
- Load and parse {sprint_status_file} same as Step 2
+ Load and parse {sprint_status_file} same as Step 2 (including deferred work analysis — set deferred counts to 0 when file is missing/empty)
Compute recommendation same as Step 3
next_workflow_id = {{next_workflow_id}}
next_story_id = {{next_story_id}}
@@ -208,6 +233,10 @@ If the command targets a story, set `story_key={{next_story_id}}` when prompted.
epic_in_progress = {{epic_in_progress}}
epic_done = {{epic_done}}
risks = {{risks}}
+ deferred_total = {{deferred_total}}
+ deferred_high = {{deferred_high}}
+ deferred_medium = {{deferred_medium}}
+ deferred_low = {{deferred_low}}
Return to caller