@sleighmaster/bmad 1.5.12 → 1.5.13
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -66,9 +66,15 @@
|
|
|
66
66
|
<!-- Review loop tracking -->
|
|
67
67
|
<action>Set {{review_round}} = {{review_round}} + 1</action>
|
|
68
68
|
<check if="{{review_round}} gt 1">
|
|
69
|
-
<
|
|
70
|
-
|
|
69
|
+
<critical>⚠️ THIS IS NOT A VERIFICATION PASS — THIS IS A FULL ADVERSARIAL RE-REVIEW FROM SCRATCH.
|
|
70
|
+
You MUST NOT assume your fixes are correct. You have confirmation bias — fight it.
|
|
71
|
+
Treat this round as if a DIFFERENT reviewer is seeing the code for the first time.
|
|
72
|
+
Execute ALL checks below (AC Validation, Task Audit, Code Quality) with the SAME rigor as Round 1.
|
|
73
|
+
"Re-read modified files" means read EVERY file in the comprehensive review list, not just the ones you touched.</critical>
|
|
74
|
+
<output>🔄 **Re-review Round {{review_round}}** — FULL adversarial re-review (not just fix verification)...</output>
|
|
75
|
+
<action>Re-read ALL files in the comprehensive review list (not just files modified in the previous round)</action>
|
|
71
76
|
<action>Re-run git status/diff to capture latest changes</action>
|
|
77
|
+
<action>Re-extract ALL Acceptance Criteria and Tasks from the story file (do NOT rely on memory from previous rounds)</action>
|
|
72
78
|
</check>
|
|
73
79
|
|
|
74
80
|
<!-- Git vs Story Discrepancies -->
|
|
@@ -118,6 +124,30 @@
|
|
|
118
124
|
</action>
|
|
119
125
|
<action>Find at least 3 more specific, actionable issues</action>
|
|
120
126
|
</check>
|
|
127
|
+
|
|
128
|
+
<!-- Mandatory review evidence output — required EVERY round before proceeding to Step 4 -->
|
|
129
|
+
<critical>You MUST output the following structured evidence checklist BEFORE proceeding to Step 4.
|
|
130
|
+
If you cannot fill in specific evidence for each section, you have NOT completed the review.
|
|
131
|
+
Do NOT proceed to Step 4 until every section has concrete evidence.</critical>
|
|
132
|
+
<output>### 📋 Review Evidence (Round {{review_round}})
|
|
133
|
+
|
|
134
|
+
**Files Actually Read This Round:** [list every file path you read]
|
|
135
|
+
|
|
136
|
+
**AC Verification:**
|
|
137
|
+
{{for each AC}}
|
|
138
|
+
- AC#{{n}}: {{IMPLEMENTED|PARTIAL|MISSING}} — Evidence: {{file:line or specific code reference}}
|
|
139
|
+
{{/for}}
|
|
140
|
+
|
|
141
|
+
**Task Audit:**
|
|
142
|
+
{{for each [x] task}}
|
|
143
|
+
- Task {{n}}: {{VERIFIED|NOT DONE}} — Evidence: {{file:line or specific code reference}}
|
|
144
|
+
{{/for}}
|
|
145
|
+
|
|
146
|
+
**Security/Performance Spot-Check:**
|
|
147
|
+
- Checked: {{list specific checks performed with file references}}
|
|
148
|
+
|
|
149
|
+
**Issues Found This Round:** {{count}} ({{high}} HIGH, {{medium}} MEDIUM, {{low}} LOW)
|
|
150
|
+
</output>
|
|
121
151
|
</step>
|
|
122
152
|
|
|
123
153
|
<step n="4" goal="Record findings, auto-fix, and loop until clean">
|
|
@@ -179,8 +209,8 @@
|
|
|
179
209
|
|
|
180
210
|
<output>🔧 **Round {{review_round}} fixes applied:** {{fixed_count}} issues fixed. Looping back for re-review...</output>
|
|
181
211
|
|
|
182
|
-
<!-- Loop back to Step 3 for re-review -->
|
|
183
|
-
<goto step="3">
|
|
212
|
+
<!-- Loop back to Step 3 for FULL re-review — not just verification of fixes -->
|
|
213
|
+
<goto step="3" scope="FULL" depth="adversarial">Full adversarial re-review — re-execute ALL checks from scratch, not just verify fixes</goto>
|
|
184
214
|
</check>
|
|
185
215
|
</step>
|
|
186
216
|
|