fix(review): address PR #1791 review feedback

- Remove "Task tool" reference per maintainer; use generic "subagents"
- Fix nested triple-backtick fencing with four-tick outer fence
- Widen location format to support multi-line ranges and hunk refs
- Add JSON-safety constraint to guard_snippet field
- Tighten input loading to "strictly from provided input"
- Replace vague "unreadable" with "cannot be decoded as text"
- Replace vague "increased scrutiny" with concrete re-analysis checklist
- Resolve HALT-immediately vs re-analysis conflict in LLM instructions

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.claude/skills/bmad-os-review-pr/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: bmad-os-review-pr
-description: Adversarial PR review tool (Raven's Verdict). Cynical deep review transformed into professional engineering findings. Use when user asks to 'review a PR' and provides a PR url or id.
+description: Dual-layer PR review tool (Raven's Verdict). Runs adversarial cynical review and edge case hunter in parallel, merges and deduplicates findings into professional engineering output. Use when user asks to 'review a PR' and provides a PR url or id.
 ---
 
 Read `prompts/instructions.md` and execute.

.claude/skills/bmad-os-review-pr/prompts/instructions.md

@@ -93,13 +93,17 @@ gh pr diff {PR_NUMBER} [--repo {REPO}] --name-only | grep -E '\.(png|jpg|jpeg|gi
 
 Store list of binary files to skip. Note them in final output.
 
-## Adversarial Review
+## Review Layers
 
-### 1.1 Run Cynical Review
+**Launch steps 1.1 and 1.2 as parallel subagents.** Both receive the same PR diff and run concurrently. Wait for both to complete before proceeding to step 1.3.
+
+### 1.1 Run Cynical Review (subagent)
+
+Spawn a subagent with the following prompt. Pass the full PR diff as context.
 
 **INTERNAL PERSONA - Never post this directly:**
 
-Task: You are a cynical, jaded code reviewer with zero patience for sloppy work. This PR was submitted by a clueless weasel and you expect to find problems. Find at least five issues to fix or improve in it. Number them. Be skeptical of everything. Ultrathink.
+Task: You are a cynical, jaded code reviewer with zero patience for sloppy work. This PR was submitted by a clueless weasel and you expect to find problems. Find at least five issues to fix or improve in it. Number them. Be skeptical of everything.
 
 Output format:
 
@@ -124,14 +128,64 @@ Likely tag:
 - Add `[likely]` to findings with high confidence, e.g. with direct evidence
 - Sort findings by severity (Critical → Moderate → Minor), not by confidence
 
+### 1.2 Run Edge Case Hunter (subagent)
+
+Spawn a subagent that executes the task defined in `_bmad/core/tasks/review-edge-case-hunter.xml`. Pass the full PR diff as the `content` input. Omit `also_consider` unless the user specified extra focus areas.
+
+The task returns a JSON array of objects, each with: `location`, `trigger_condition`, `guard_snippet`, `potential_consequence`.
+
+**Map each JSON finding to the standard finding format:**
+
+````markdown
+### [NUMBER]. [trigger_condition] [likely]
+
+**Severity:** [INFERRED_EMOJI] [INFERRED_LEVEL]
+
+**`[location]`** — [trigger_condition]. [potential_consequence].
+
+**Suggested fix:**
+```
+[guard_snippet]
+```
+````
+
+Severity inference rules for edge case findings:
+
+- **Critical** — data loss, security, or crash conditions (null deref, unhandled throw, auth bypass)
+- **Moderate** — logic errors, silent wrong results, race conditions
+- **Minor** — cosmetic edge cases, unlikely boundary conditions
+
+Add `[likely]` to all edge case findings — they are derived from mechanical path tracing, so confidence is inherently high.
+
+If the edge case hunter returns zero findings or halts, note it internally and proceed — step 1.1 findings still stand.
+
+### 1.3 Merge and Deduplicate
+
+Combine the findings from step 1.1 (adversarial) and step 1.2 (edge case hunter) into a single list.
+
+**Deduplication rules:**
+
+1. Compare each edge case finding against each adversarial finding
+2. Two findings are duplicates if they reference the same file location AND describe the same gap (use description similarity — same function/variable/condition mentioned)
+3. When a duplicate is found, keep the version with more specificity (usually the edge case hunter's, since it includes `guard_snippet`)
+4. Mark the kept finding with the source that produced it
+
+**After dedup, renumber all findings sequentially and sort by severity (Critical → Moderate → Minor).**
+
+Tag each finding with its source:
+
+- `[Adversarial]` — from step 1.1 only
+- `[Edge Case]` — from step 1.2 only
+- `[Both]` — flagged by both layers (deduped)
+
 ## Tone Transformation
 
-**Transform the cynical output into cold engineering professionalism.**
+**Transform the merged findings into cold engineering professionalism.**
 
 **Transformation rules:**
 
 1. Remove all inflammatory language, insults, assumptions about the author
-2. Keep all technical substance, file references, severity ratings and likely tag
+2. Keep all technical substance, file references, severity ratings, likely tag, and **source tags**
 3. Replace accusatory phrasing with neutral observations:
    - ❌ "The author clearly didn't think about..."
    - ✅ "This implementation may not account for..."
@@ -140,6 +194,7 @@ Likely tag:
    - ✅ "This pattern has historically caused issues in production environments"
 5. Add the suggested fixes.
 6. Keep suggestions actionable and specific
+7. Edge case hunter findings need no persona cleanup, but still apply professional formatting consistently
 
 Output format after transformation:
 
@@ -149,18 +204,20 @@ Output format after transformation:
 **Title:** {PR_TITLE}
 **Author:** @{AUTHOR}
 **Branch:** {HEAD} → {BASE}
+**Review layers:** Adversarial + Edge Case Hunter
 
 ---
 
 ### Findings
 
-[TRANSFORMED FINDINGS HERE]
+[TRANSFORMED FINDINGS HERE — each tagged with source]
 
 ---
 
 ### Summary
 
 **Critical:** {COUNT} | **Moderate:** {COUNT} | **Minor:** {COUNT}
+**Sources:** {ADVERSARIAL_COUNT} adversarial | {EDGE_CASE_COUNT} edge case | {BOTH_COUNT} both
 
 [BINARY_FILES_NOTE if any]
 

CHANGELOG.md

@@ -1,5 +1,20 @@
 # Changelog
 
+## [6.0.4]
+
+### 🎁 Features
+
+* Add edge case hunter review task - new reusable review task that exhaustively traces branching paths and boundary conditions in code, reporting only unhandled gaps. Method-driven analysis complementary to adversarial review (#1790)
+
+### 🐛 Bug Fixes
+
+* Fix brainstorming to not overwrite previous sessions; now prompts to continue existing brainstorming or start a new one when older brainstorming sessions are found
+* Fix installer templates - replace legacy `@` path prefixes with explicit `{project-root}` syntax for consistency (#1769)
+* Fix edge case hunter - remove zero-findings halt condition that was pressuring the LLM to hallucinate findings when none legitimately exist (#1797)
+* Fix broken docs domain references in README and GitHub issue templates (#1777)
+
+---
+
 ## [6.0.3]
 
 ### 🎁 Features

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "bmad-method",
-  "version": "6.0.3",
+  "version": "6.0.4",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "bmad-method",
-      "version": "6.0.3",
+      "version": "6.0.4",
       "license": "MIT",
       "dependencies": {
         "@clack/core": "^1.0.0",

package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "bmad-method",
-  "version": "6.0.3",
+  "version": "6.0.4",
   "description": "Breakthrough Method of Agile AI-driven Development",
   "keywords": [
     "agile",

src/core/module.yaml

@@ -2,7 +2,7 @@ code: core
 name: "BMad Core Module"
 
 header: "BMad Core Configuration"
-subheader: "Configure the core settings for your BMad installation.\nThese settings will be used across all modules and agents."
+subheader: "Configure the core settings for your BMad installation.\nThese settings will be used across all installed bmad skills, workflows, and agents."
 
 user_name:
   prompt: "What should agents call you? (Use your name or a team name)"
@@ -23,3 +23,13 @@ output_folder:
   prompt: "Where should output files be saved?"
   default: "_bmad-output"
   result: "{project-root}/{value}"
+
+tool_supports_subagents:
+  prompt: "Subagents are supported by the LLM or Tool I will be using?"
+  default: true
+  result: "{value}"
+
+tool_supports_agent_teams:
+  prompt: "Agent Teams are supported by the LLM or Tool I will be using?"
+  default: false
+  result: "{value}"

src/core/tasks/review-edge-case-hunter.xml

@@ -15,18 +15,18 @@ Ignore the rest of the codebase unless the provided content explicitly reference
   </inputs>
 
   <output-format>Return ONLY a valid JSON array of objects. Each object must contain exactly these four fields and nothing else:
-{
-  "location": "file:line",
+[{
+  "location": "file:start-end (or file:line when single line, or file:hunk when exact line unavailable)",
   "trigger_condition": "one-line description (max 15 words)",
-  "guard_snippet": "minimal code sketch that closes the gap",
+  "guard_snippet": "minimal code sketch that closes the gap (single-line escaped string, no raw newlines or unescaped quotes)",
   "potential_consequence": "what could actually go wrong (max 15 words)"
-}
-No extra text, no explanations, no markdown wrapping.</output-format>
+}]
+No extra text, no explanations, no markdown wrapping. An empty array [] is valid when no unhandled paths are found.</output-format>
 
   <llm critical="true">
-    <i>MANDATORY: Execute ALL steps in the flow section IN EXACT ORDER</i>
+    <i>MANDATORY: Execute steps in the flow section IN EXACT ORDER</i>
     <i>DO NOT skip steps or change the sequence</i>
-    <i>HALT immediately when halt-conditions are met</i>
+    <i>When a halt-condition triggers, follow its specific instruction exactly</i>
     <i>Each action xml tag within step xml tag is a REQUIRED action to complete that step</i>
 
     <i>Your method is exhaustive path enumeration — mechanically walk every branch, not hunt by intuition</i>
@@ -38,8 +38,8 @@ No extra text, no explanations, no markdown wrapping.</output-format>
 
   <flow>
     <step n="1" title="Receive Content">
-      <action>Load the content to review from provided input or context</action>
-      <action>If content to review is empty, ask for clarification and abort task</action>
+      <action>Load the content to review strictly from provided input</action>
+      <action>If content is empty, or cannot be decoded as text, return empty array [] and stop</action>
       <action>Identify content type (diff, full file, or function) to determine scope rules</action>
     </step>
 
@@ -51,14 +51,20 @@ No extra text, no explanations, no markdown wrapping.</output-format>
       <action>Collect only the unhandled paths as findings - discard handled ones silently</action>
     </step>
 
-    <step n="3" title="Present Findings">
+    <step n="3" title="Validate Completeness">
+      <action>Recheck every conditional for missing else/default</action>
+      <action>Recheck every input for null/empty/wrong-type</action>
+      <action>Recheck loop bounds for off-by-one and empty-collection</action>
+      <action>Add any newly found unhandled paths to findings; discard confirmed-handled ones</action>
+    </step>
+
+    <step n="4" title="Present Findings">
       <action>Output findings as a JSON array following the output-format specification exactly</action>
     </step>
   </flow>
 
   <halt-conditions>
-    <condition>HALT if zero findings - this is suspicious, re-analyze or ask for guidance</condition>
-    <condition>HALT if content is empty or unreadable</condition>
+    <condition>If content is empty or cannot be decoded as text, return empty array [] and stop</condition>
   </halt-conditions>
 
 </task>

src/core/workflows/brainstorming/steps/step-01-session-setup.md

@@ -29,23 +29,30 @@ Initialize the brainstorming workflow by detecting continuation state and settin
 
 ## INITIALIZATION SEQUENCE:
 
-### 1. Check for Existing Workflow
+### 1. Check for Existing Sessions
 
-First, check if the output document already exists:
+First, check the brainstorming sessions folder for existing sessions:
 
-- Look for file at `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`
-- If exists, read the complete file including frontmatter
-- If not exists, this is a fresh workflow
+- List all files in `{output_folder}/brainstorming/`
+- **DO NOT read any file contents** - only list filenames
+- If files exist, identify the most recent by date/time in the filename
+- If no files exist, this is a fresh workflow
 
-### 2. Handle Continuation (If Document Exists)
+### 2. Handle Existing Sessions (If Files Found)
 
-If the document exists and has frontmatter with `stepsCompleted`:
+If existing session files are found:
 
-- **STOP here** and load `./step-01b-continue.md` immediately
-- Do not proceed with any initialization tasks
-- Let step-01b handle the continuation logic
+- Display the most recent session filename (do NOT read its content)
+- Ask the user: "Found existing session: `[filename]`. Would you like to:
+  **[1]** Continue this session
+  **[2]** Start a new session
+  **[3]** See all existing sessions"
 
-### 3. Fresh Workflow Setup (If No Document)
+- If user selects **[1]** (continue): Set `{brainstorming_session_output_file}` to that file path and load `./step-01b-continue.md`
+- If user selects **[2]** (new): Generate new filename with current date/time and proceed to step 3
+- If user selects **[3]** (see all): List all session filenames and ask which to continue or if new
+
+### 3. Fresh Workflow Setup (If No Files or User Chooses New)
 
 If no document exists or no `stepsCompleted` in frontmatter:
 
@@ -55,10 +62,10 @@ Create the brainstorming session document:
 
 ```bash
 # Create directory if needed
-mkdir -p "$(dirname "{output_folder}/brainstorming/brainstorming-session-{{date}}.md")"
+mkdir -p "$(dirname "{brainstorming_session_output_file}")"
 
 # Initialize from template
-cp "{template_path}" "{output_folder}/brainstorming/brainstorming-session-{{date}}.md"
+cp "{template_path}" "{brainstorming_session_output_file}"
 ```
 
 #### B. Context File Check and Loading
@@ -134,7 +141,7 @@ _[Content based on conversation about session parameters and facilitator approac
 
 ## APPEND TO DOCUMENT:
 
-When user selects approach, append the session overview content directly to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md` using the structure from above.
+When user selects approach, append the session overview content directly to `{brainstorming_session_output_file}` using the structure from above.
 
 ### E. Continue to Technique Selection
 
@@ -152,7 +159,7 @@ Which approach appeals to you most? (Enter 1-4)"
 
 #### When user selects approach number:
 
-- **Append initial session overview to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`**
+- **Append initial session overview to `{brainstorming_session_output_file}`**
 - **Update frontmatter:** `stepsCompleted: [1]`, `selected_approach: '[selected approach]'`
 - **Load the appropriate step-02 file** based on selection
 
@@ -167,7 +174,9 @@ After user selects approach number:
 
 ## SUCCESS METRICS:
 
-✅ Existing workflow detected and continuation handled properly
+✅ Existing sessions detected without reading file contents
+✅ User prompted to continue existing session or start new
+✅ Correct session file selected for continuation
 ✅ Fresh workflow initialized with correct document structure
 ✅ Session context gathered and understood clearly
 ✅ User's approach selection captured and routed correctly
@@ -176,7 +185,9 @@ After user selects approach number:
 
 ## FAILURE MODES:
 
-❌ Not checking for existing document before creating new one
+❌ Reading file contents during session detection (wastes context)
+❌ Not asking user before continuing existing session
+❌ Not properly routing user's continue/new session selection
 ❌ Missing continuation detection leading to duplicate work
 ❌ Insufficient session context gathering
 ❌ Not properly routing user's approach selection
@@ -184,7 +195,9 @@ After user selects approach number:
 
 ## SESSION SETUP PROTOCOLS:
 
-- Always verify document existence before initialization
+- Always list sessions folder WITHOUT reading file contents
+- Ask user before continuing any existing session
+- Only load continue step after user confirms
 - Load brain techniques CSV only when needed for technique presentation
 - Use collaborative facilitation language throughout
 - Maintain psychological safety for creative exploration

src/core/workflows/brainstorming/steps/step-01b-continue.md

@@ -35,7 +35,7 @@ Load existing document and analyze current state:
 
 **Document Analysis:**
 
-- Read existing `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`
+- Read existing `{brainstorming_session_output_file}`
 - Examine frontmatter for `stepsCompleted`, `session_topic`, `session_goals`
 - Review content to understand session progress and outcomes
 - Identify current stage and next logical steps

src/core/workflows/brainstorming/steps/step-03-technique-execution.md

@@ -296,7 +296,7 @@ After final technique element:
 
 #### If 'C' (Move to organization):
 
-- **Append the technique execution content to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`**
+- **Append the technique execution content to `{brainstorming_session_output_file}`**
 - **Update frontmatter:** `stepsCompleted: [1, 2, 3]`
 - **Load:** `./step-04-idea-organization.md`
 
@@ -356,7 +356,7 @@ _[Short narrative describing the user and AI collaboration journey - what made t
 
 ## APPEND TO DOCUMENT:
 
-When user selects 'C', append the content directly to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md` using the structure from above.
+When user selects 'C', append the content directly to `{brainstorming_session_output_file}` using the structure from above.
 
 ## SUCCESS METRICS:
 

src/core/workflows/brainstorming/steps/step-04-idea-organization.md

@@ -253,14 +253,14 @@ Provide final session wrap-up and forward guidance:
 
 #### If [C] Complete:
 
-- **Append the final session content to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`**
+- **Append the final session content to `{brainstorming_session_output_file}`**
 - Update frontmatter: `stepsCompleted: [1, 2, 3, 4]`
 - Set `session_active: false` and `workflow_completed: true`
 - Complete workflow with positive closure message
 
 ## APPEND TO DOCUMENT:
 
-When user selects 'C', append the content directly to `{output_folder}/brainstorming/brainstorming-session-{{date}}.md` using the structure from step 7.
+When user selects 'C', append the content directly to `{brainstorming_session_output_file}` using the structure from step 7.
 
 ## SUCCESS METRICS:
 

src/core/workflows/brainstorming/workflow.md

@@ -45,7 +45,9 @@ Load config from `{project-root}/_bmad/core/config.yaml` and resolve:
 - `installed_path` = `{project-root}/_bmad/core/workflows/brainstorming`
 - `template_path` = `{installed_path}/template.md`
 - `brain_techniques_path` = `{installed_path}/brain-methods.csv`
-- `default_output_file` = `{output_folder}/brainstorming/brainstorming-session-{{date}}.md`
+- `brainstorming_session_output_file` = `{output_folder}/brainstorming/brainstorming-session-{{date}}-{{time}}.md` (evaluated once at workflow start)
+
+All steps MUST reference `{brainstorming_session_output_file}` instead of the full path pattern.
 - `context_file` = Optional context file path from workflow invocation for project-specific guidance
 - `advancedElicitationTask` = `{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.xml`
 

tools/cli/installers/lib/ide/templates/agent-command-template.md

@@ -6,7 +6,7 @@ description: '{{description}}'
 You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
 
 <agent-activation CRITICAL="TRUE">
-1. LOAD the FULL agent file from @_bmad/{{module}}/agents/{{path}}
+1. LOAD the FULL agent file from {project-root}/_bmad/{{module}}/agents/{{path}}
 2. READ its entire contents - this contains the complete agent persona, menu, and instructions
 3. Execute ALL activation steps exactly as written in the agent file
 4. Follow the agent's persona and menu system precisely

tools/cli/installers/lib/ide/templates/combined/default-workflow-yaml.md

@@ -6,9 +6,9 @@ description: '{{description}}'
 IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
 
 <steps CRITICAL="TRUE">
-1. Always LOAD the FULL @{project-root}/{{bmadFolderName}}/core/tasks/workflow.xml
-2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @{project-root}/{{bmadFolderName}}/{{path}}
-3. Pass the yaml path @{project-root}/{{bmadFolderName}}/{{path}} as 'workflow-config' parameter to the workflow.xml instructions
+1. Always LOAD the FULL {project-root}/{{bmadFolderName}}/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config {project-root}/{{bmadFolderName}}/{{path}}
+3. Pass the yaml path {project-root}/{{bmadFolderName}}/{{path}} as 'workflow-config' parameter to the workflow.xml instructions
 4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
 5. Save outputs after EACH section when generating any documents from templates
 </steps>

tools/cli/installers/lib/ide/templates/combined/default-workflow.md

@@ -3,4 +3,4 @@ name: '{{name}}'
 description: '{{description}}'
 ---
 
-IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL @{project-root}/{{bmadFolderName}}/{{path}}, READ its entire contents and follow its directions exactly!
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/{{bmadFolderName}}/{{path}}, READ its entire contents and follow its directions exactly!

tools/cli/installers/lib/ide/templates/workflow-command-template.md

@@ -5,8 +5,8 @@ description: '{{description}}'
 IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
 
 <steps CRITICAL="TRUE">
-1. Always LOAD the FULL @_bmad/core/tasks/workflow.xml
-2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config @{{workflow_path}}
+1. Always LOAD the FULL {project-root}/_bmad/core/tasks/workflow.xml
+2. READ its entire contents - this is the CORE OS for EXECUTING the specific workflow-config {project-root}/{{workflow_path}}
 3. Pass the yaml path {{workflow_path}} as 'workflow-config' parameter to the workflow.xml instructions
 4. Follow workflow.xml instructions EXACTLY as written to process and follow the specific workflow config and its instructions
 5. Save outputs after EACH section when generating any documents from templates

tools/cli/installers/lib/ide/templates/workflow-commander.md

@@ -2,4 +2,4 @@
 description: '{{description}}'
 ---
 
-IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL @{{workflow_path}}, READ its entire contents and follow its directions exactly!
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL {project-root}/{{workflow_path}}, READ its entire contents and follow its directions exactly!