sinapse-ai 5.0.8 → 6.0.1

package/.sinapse-ai/development/tasks/qa-fix-issues.md

@@ -82,13 +82,13 @@ autoClaude:
 
 ---
 
-## Command Integration (@dev)
+## Command Integration (@developer)
 
 ```yaml
 command:
   name: '*fix-qa-issues'
   syntax: '*fix-qa-issues {story-id}'
-  agent: dev
+  agent: developer
 
   examples:
     - '*fix-qa-issues 6.4'
@@ -496,7 +496,7 @@ phase_7:
 
         ---
 
-        **Next Step:** @qa re-review with `*review-story {storyId}`
+        **Next Step:** @quality-gate re-review with `*review-story {storyId}`
 
   validation:
     check: 'All updates completed, signal file created'
@@ -534,7 +534,7 @@ summary:
       {end for}
 
       ### Next Steps
-      1. QA agent should re-review: `@qa *review-story {storyId}`
+      1. QA agent should re-review: `@quality-gate *review-story {storyId}`
       2. If all issues verified, story moves to "Ready for Review"
 
       ---
@@ -587,11 +587,11 @@ qa_loop_integration:
   triggered_by:
     - QA review identifies issues
     - QA_FIX_REQUEST.md created
-    - @qa signals @dev
+    - @quality-gate signals @dev
 
   triggers_next:
     - READY_FOR_REREVIEW.md signals @qa
-    - @qa runs re-review
+    - @quality-gate runs re-review
     - Loop continues until PASS or WAIVED
 
   handoff_format:
@@ -633,7 +633,7 @@ qa_loop_integration:
 - ✅ Check null input returns proper error
 
 ### Next Steps
-1. QA agent should re-review: `@qa *review-story 6.4`
+1. QA agent should re-review: `@quality-gate *review-story 6.4`
 2. If all issues verified, story moves to "Ready for Review"
 ```
 
@@ -662,7 +662,7 @@ MAJ-2 requires refactoring the data layer. This exceeds minimal fix scope.
 Recommend creating separate story for performance optimization.
 
 ### Next Steps
-1. Discuss MAJ-2 with @qa and @po
+1. Discuss MAJ-2 with @quality-gate and @po
 2. Either expand scope or create follow-up story
 ```
 
@@ -675,7 +675,7 @@ metadata:
   story: '6.4'
   epic: 'Epic 6 - QA Evolution'
   created: '2026-01-29'
-  author: '@dev (Dex)'
+  author: '@developer (Dex)'
   version: '1.0.0'
   tags:
     - qa-loop
@@ -689,4 +689,4 @@ next_agent: @qa
 next_command: *review {story-id}
 condition: All QA_FIX_REQUEST issues resolved
 alternatives:
-  - agent: @dev, command: *run-tests, condition: Verify fixes pass before re-review
+  - agent: @developer, command: *run-tests, condition: Verify fixes pass before re-review

package/.sinapse-ai/development/tasks/qa-gate.md

@@ -331,7 +331,7 @@ If blast radius returned HIGH risk:
 
 1. The `suggestGateInfluence('HIGH')` advisory is **informational only**
 2. It suggests CONCERNS but does NOT automatically change the gate verdict
-3. @qa makes the final decision — the advisory is logged in the gate file under `code_intel_advisory`
+3. @quality-gate makes the final decision — the advisory is logged in the gate file under `code_intel_advisory`
 
 > **Fallback guarantee:** If code intelligence is unavailable or any call returns null, the gate process continues exactly as before — no sections are added, no errors are raised.
 
@@ -425,6 +425,6 @@ next_agent: @devops
 next_command: *push
 condition: QA gate verdict is PASS
 alternatives:
-  - agent: @dev, command: *apply-qa-fixes, condition: QA gate verdict is FAIL or CONCERNS
-  - agent: @po, command: *close-story {story-id}, condition: QA gate verdict is WAIVED
+  - agent: @developer, command: *apply-qa-fixes, condition: QA gate verdict is FAIL or CONCERNS
+  - agent: @product-lead, command: *close-story {story-id}, condition: QA gate verdict is WAIVED
  

package/.sinapse-ai/development/tasks/qa-review-build.md

@@ -971,7 +971,7 @@ template: |
 
   ---
 
-  *Generated by Quinn (@qa) via qa-review-build task*
+  *Generated by Quinn (@quality-gate) via qa-review-build task*
 
 output:
   report:
@@ -1102,7 +1102,7 @@ signal_rules:
       - Unit tests fail OR
       - Subtasks incomplete
     meaning: 'Build requires fixes before approval'
-    next_action: 'Return to @dev with fix requests'
+    next_action: 'Return to @developer with fix requests'
 ```
 
 ---
@@ -1185,7 +1185,7 @@ errors:
 
 ## Integration with QA Agent
 
-This task is automatically triggered by the `*review-build` command in the @qa agent:
+This task is automatically triggered by the `*review-build` command in the @quality-gate agent:
 
 ```yaml
 agent_integration:

package/.sinapse-ai/development/tasks/qa-review-story.md

@@ -243,7 +243,7 @@ Execute CodeRabbit self-healing **FIRST** before manual review:
 ```
 ┌───────────────────────────────────────────────────────────────────┐
 │                   CODERABBIT SELF-HEALING                         │
-│                    (Full Mode - @qa)                              │
+│                    (Full Mode - @quality-gate)                              │
 ├───────────────────────────────────────────────────────────────────┤
 │                                                                   │
 │  iteration = 0                                                    │
@@ -709,6 +709,6 @@ next_command: *apply-qa-fixes
 condition: QA verdict is REJECT
 alternatives:
   - agent: @devops, command: *push, condition: QA verdict is APPROVE
-  - agent: @dev, command: *fix-qa-issues, condition: Structured fix from QA_FIX_REQUEST.md
+  - agent: @developer, command: *fix-qa-issues, condition: Structured fix from QA_FIX_REQUEST.md
 
 - **Manual Sync**: If needed, use: `npm run sync-story -- --story {epic}.{story}` 

package/.sinapse-ai/development/tasks/qa-run-tests.md

@@ -260,7 +260,7 @@ If failures:
 
 ## Integration with CodeRabbit
 
-**CodeRabbit helps @qa agent**:
+**CodeRabbit helps @quality-gate agent**:
 - Catch issues tests might miss (logic errors, race conditions)
 - Validate security patterns (SQL injection, hardcoded secrets)
 - Enforce coding standards automatically

package/.sinapse-ai/development/tasks/run-workflow-engine.md

@@ -821,7 +821,7 @@ engine_state:
 The state file persists on disk. To resume in a new Claude Code session:
 
 ```
-@sinapse-master
+@sinapse-orqx
 *run-workflow {name} continue --mode=engine
 ```
 

package/.sinapse-ai/development/tasks/run-workflow.md

@@ -369,7 +369,7 @@ Abort workflow execution.
 The state file persists between sessions. To continue a workflow:
 
 1. User starts new Claude Code session
-2. Activates @sinapse-master
+2. Activates @sinapse-orqx
 3. Runs `*run-workflow {name} continue`
 4. System loads state, shows current step
 5. User executes step (possibly in new agent session)

package/.sinapse-ai/development/tasks/security-scan.md

@@ -719,12 +719,12 @@ Cria arquivo em: `qa.qaLocation/security/{epic}.{story}-sast-{YYYYMMDD}.md`
 - semgrep: v{version} (if used)
 
 **Report Generated**: {timestamp}
-**Report Generator**: @qa (Quinn - Test Architect)
+**Report Generator**: @quality-gate (Quinn - Test Architect)
 ```
 
 ## Integration with review-story.md
 
-Quando `@qa *review {story}` é executado, **automaticamente** chama `security-scan`:
+Quando `@quality-gate *review {story}` é executado, **automaticamente** chama `security-scan`:
 
 ```markdown
 # review-story.md (atualizar)

package/.sinapse-ai/development/tasks/setup-llm-routing.md

@@ -4,7 +4,7 @@
 **Version:** 1.1.0
 **Created:** 2025-12-12
 **Updated:** 2025-12-14
-**Agent:** @dev (Dex)
+**Agent:** @developer (Dex)
 **Location:** .sinapse-ai/development/tasks/setup-llm-routing.md
 
 ---

package/.sinapse-ai/development/tasks/spec-critique.md

@@ -360,7 +360,7 @@ generate_output:
     {
       "storyId": "{storyId}",
       "critiquedAt": "{timestamp}",
-      "critiquedBy": "@qa",
+      "critiquedBy": "@quality-gate",
       "specVersion": 1,
 
       "verdict": "APPROVED|NEEDS_REVISION|BLOCKED",
@@ -419,7 +419,7 @@ generate_output:
   "properties": {
     "storyId": { "type": "string" },
     "critiquedAt": { "type": "string", "format": "date-time" },
-    "critiquedBy": { "type": "string", "default": "@qa" },
+    "critiquedBy": { "type": "string", "default": "@quality-gate" },
     "specVersion": { "type": "integer", "minimum": 1 },
     "verdict": { "enum": ["APPROVED", "NEEDS_REVISION", "BLOCKED"] },
     "verdictReason": { "type": "string" },
@@ -471,7 +471,7 @@ generate_output:
 
 ## Integration
 
-### Command Integration (@qa)
+### Command Integration (@quality-gate)
 
 ```yaml
 command:
@@ -599,5 +599,5 @@ next_agent: @architect
 next_command: *plan
 condition: Critique verdict is APPROVED
 alternatives:
-  - agent: @pm, command: *write-spec, condition: Critique verdict is NEEDS_REVISION
+  - agent: @project-lead, command: *write-spec, condition: Critique verdict is NEEDS_REVISION
   - agent: @architect, command: *analyze-impact, condition: Critique verdict is BLOCKED

package/.sinapse-ai/development/tasks/spec-gather-requirements.md

@@ -204,7 +204,7 @@ structuring:
       "storyId": "{storyId}",
       "gatheredAt": "{timestamp}",
       "source": "{source}",
-      "gatheredBy": "@pm",
+      "gatheredBy": "@project-lead",
       "elicitationVersion": "2.0",
 
       "functional": [
@@ -313,7 +313,7 @@ structuring:
     "storyId": { "type": "string" },
     "gatheredAt": { "type": "string", "format": "date-time" },
     "source": { "enum": ["prd", "user", "existing"] },
-    "gatheredBy": { "type": "string", "default": "@pm" },
+    "gatheredBy": { "type": "string", "default": "@project-lead" },
     "elicitationVersion": { "type": "string", "default": "2.0" },
     "functional": {
       "type": "array",
@@ -438,7 +438,7 @@ structuring:
 
 ## Integration
 
-### Command Integration (@pm)
+### Command Integration (@project-lead)
 
 ```yaml
 command:
@@ -549,4 +549,4 @@ next_agent: @architect
 next_command: *analyze-impact
 condition: Requirements gathered (requirements.json created)
 alternatives:
-  - agent: @pm, command: *write-spec, condition: SIMPLE complexity, skip assessment
+  - agent: @project-lead, command: *write-spec, condition: SIMPLE complexity, skip assessment

package/.sinapse-ai/development/tasks/spec-write-spec.md

@@ -271,7 +271,7 @@ Feature: {feature name}
 
 ## Metadata
 
-- **Generated by:** @pm via spec-write-spec
+- **Generated by:** @project-lead via spec-write-spec
 - **Inputs:** requirements.json, complexity.json, research.json
 - **Iteration:** 1
 
@@ -391,7 +391,7 @@ write_output:
 
 ## Integration
 
-### Command Integration (@pm)
+### Command Integration (@project-lead)
 
 ```yaml
 command:

package/.sinapse-ai/development/tasks/story-checkpoint.md

@@ -12,7 +12,7 @@ Requer decisão humana para continuar, pausar, revisar ou abortar.
 ```yaml
 task_id: story-checkpoint
 version: "1.0.0"
-agent: "@po"
+agent: "@product-lead"
 elicit: true  # REQUIRES human interaction
 epic: "11 - Projeto Bob"
 story: "11.3"
@@ -207,7 +207,7 @@ steps:
       To resume later, run:
         *workflow resume development-cycle
 
-      Or activate @po and run:
+      Or activate @product-lead and run:
         *validate-story-draft ${next_story}
 
   3_exit:
@@ -357,4 +357,4 @@ output:
 
 ---
 
-*Task created by @dev (Dex) for Story 11.3*
+*Task created by @developer (Dex) for Story 11.3*

package/.sinapse-ai/development/tasks/sync-registry-intel.md

@@ -2,7 +2,7 @@
 
 ## Metadata
 - **Task ID:** sync-registry-intel
-- **Agent:** @sinapse-master
+- **Agent:** @sinapse-orqx
 - **Story:** NOG-2
 - **Type:** Command Task
 - **Elicit:** false

package/.sinapse-ai/development/tasks/validate-agents.md

@@ -26,7 +26,7 @@ Story ACT-6: Framework integrity checking via `*validate-agents` command.
 ### Step 1: Discover Agent Files
 
 Scan `.sinapse-ai/development/agents/` for all `.md` files.
-Expected agents: dev, qa, architect, pm, po, sm, analyst, data-engineer, ux-design-expert, devops, sinapse-master, squad-creator
+Expected agents: dev, qa, architect, pm, po, sm, analyst, data-engineer, ux-design-expert, devops, sinapse-orqx, squad-creator
 
 ### Step 2: Parse YAML Block
 

package/.sinapse-ai/development/tasks/validate-next-story.md

@@ -246,18 +246,18 @@ To comprehensively validate a story draft before implementation begins, ensuring
 
 **Constraint Validation:**
 - [ ] **executor != quality_gate** (CRITICAL - must be different)
-- [ ] **executor** is a known agent: @dev, @data-engineer, @devops, @ux-design-expert, @analyst, @architect
-- [ ] **quality_gate** is a known agent: @architect, @dev, @pm
+- [ ] **executor** is a known agent: @developer, @data-engineer, @devops, @ux-design-expert, @analyst, @architect
+- [ ] **quality_gate** is a known agent: @architect, @developer, @pm
 
 **Type-to-Executor Consistency:**
 | Work Type | Expected Executor | Expected Quality Gate |
 |-----------|-------------------|----------------------|
-| Code/Features/Logic | @dev | @architect |
-| Schema/DB/RLS/Migrations | @data-engineer | @dev |
+| Code/Features/Logic | @developer | @architect |
+| Schema/DB/RLS/Migrations | @data-engineer | @developer |
 | Infra/CI/CD/Deploy | @devops | @architect |
-| Design/UI Components | @ux-design-expert | @dev |
-| Research/Investigation | @analyst | @pm |
-| Architecture Decisions | @architect | @pm |
+| Design/UI Components | @ux-design-expert | @developer |
+| Research/Investigation | @analyst | @project-lead |
+| Architecture Decisions | @architect | @project-lead |
 
 - [ ] Story content keywords match assigned executor type
 - [ ] Quality gate tools are appropriate for the executor type
@@ -340,7 +340,7 @@ To comprehensively validate a story draft before implementation begins, ensuring
 - Are secondary types listed if applicable?
 
 **Specialized Agent Assignment:**
-- Is @dev listed as primary agent (required for all stories)?
+- Is @developer listed as primary agent (required for all stories)?
 - Are type-specific agents assigned appropriately?
   - Database stories → @db-sage
   - Frontend stories → @ux-expert
@@ -349,7 +349,7 @@ To comprehensively validate a story draft before implementation begins, ensuring
 
 **Quality Gate Tasks:**
 - Are all applicable quality gates defined as checkboxes?
-- Pre-Commit (@dev) - REQUIRED for all stories
+- Pre-Commit (@developer) - REQUIRED for all stories
 - Pre-PR (@github-devops) - Required if PR will be created
 - Pre-Deployment (@github-devops) - Required for production stories
 
@@ -468,5 +468,5 @@ next_agent: @dev
 next_command: *develop {story-id}
 condition: Story status is Approved (GO decision)
 alternatives:
-  - agent: @sm, command: *draft, condition: Story rejected (NO-GO), needs rework
+  - agent: @sprint-lead, command: *draft, condition: Story rejected (NO-GO), needs rework
  

package/.sinapse-ai/development/tasks/validate-workflow.md

@@ -316,6 +316,6 @@ Invalid: 0
 
 ## Integration
 
-- Called by `*validate-workflow` command in sinapse-master
+- Called by `*validate-workflow` command in sinapse-orqx
 - Called by `SquadValidator.validateWorkflows()` during squad validation
 - Can be called by `FrameworkAnalyzer.validateWorkflow()` for analysis

package/.sinapse-ai/development/tasks/verify-subtask.md

@@ -59,13 +59,13 @@ autoClaude:
 
 ---
 
-## Command Integration (@dev)
+## Command Integration (@developer)
 
 ```yaml
 command:
   name: '*verify-subtask'
   syntax: '*verify-subtask {subtask-id}'
-  agent: dev
+  agent: developer
 
   examples:
     - '*verify-subtask 1.1'

package/.sinapse-ai/development/templates/code-intel-integration-pattern.md

@@ -187,10 +187,10 @@ function createMockClient(overrides = {}) {
 
 | Helper | Agent | Functions | Story |
 |--------|-------|-----------|-------|
-| `dev-helper.js` | @dev | checkBeforeWriting, suggestReuse, getConventionsForPath, assessRefactoringImpact | NOG-3 |
-| `qa-helper.js` | @qa | validateTestCoverage, detectRegressionRisk | NOG-4 |
+| `dev-helper.js` | @developer | checkBeforeWriting, suggestReuse, getConventionsForPath, assessRefactoringImpact | NOG-3 |
+| `qa-helper.js` | @quality-gate | validateTestCoverage, detectRegressionRisk | NOG-4 |
 | `planning-helper.js` | @architect | analyzeComplexity, suggestArchitecture | NOG-5 |
-| `story-helper.js` | @sm/@po | detectDuplicateStory, suggestRelevantFiles, validateNoDuplicates | NOG-6 |
+| `story-helper.js` | @sm/@product-lead | detectDuplicateStory, suggestRelevantFiles, validateNoDuplicates | NOG-6 |
 | `devops-helper.js` | @devops | assessDeploymentRisk, validatePipelineImpact | NOG-7 |
 | `creation-helper.js` | squad-creator | getCodebaseContext, checkDuplicateArtefact, enrichRegistryEntry | NOG-8 |
 

package/.sinapse-ai/development/templates/subagent-step-prompt.md

@@ -1,7 +1,7 @@
 # Subagent Step Prompt Template
 
 > **Purpose:** Reusable template for constructing subagent prompts in the Workflow Runtime Engine.
-> Each variable is replaced at runtime by the orchestrator (sinapse-master) before spawning the subagent via the Task tool.
+> Each variable is replaced at runtime by the orchestrator (sinapse-orqx) before spawning the subagent via the Task tool.
 
 ---
 
@@ -114,7 +114,7 @@ The `{{TASK_CONTENT}}` variable should contain the full task file content, from
 ## Notes
 
 - This template is referenced by `run-workflow-engine.md` task
-- The orchestrator (sinapse-master) builds the prompt by reading files and replacing variables
+- The orchestrator (sinapse-orqx) builds the prompt by reading files and replacing variables
 - Subagents receive the complete prompt and execute autonomously
 - The orchestrator parses the `step_output` YAML block from the subagent's response
 - If the subagent fails to produce a valid YAML block, the orchestrator retries or requests manual intervention

package/.sinapse-ai/development/workflows/README.md

@@ -27,9 +27,9 @@ The `setup-environment` workflow helps developers configure their IDE for optima
 
 ### Usage
 
-From the sinapse-master agent:
+From the sinapse-orqx agent:
 ```
-@sinapse-master
+@sinapse-orqx
 *setup-environment
 ```
 

package/.sinapse-ai/development/workflows/auto-worktree.yaml

@@ -4,7 +4,7 @@ workflow:
   version: "1.0"
   description: >-
     Automatically creates and manages isolated worktrees for story development.
-    Triggered when @dev starts working on a story, ensuring parallel development
+    Triggered when @developer starts working on a story, ensuring parallel development
     capability and clean isolation between different development tasks.
 
     Part of the Auto-Claude ADE (Autonomous Development Engine) infrastructure.
@@ -20,13 +20,13 @@ workflow:
   # ═══════════════════════════════════════════════════════════════════════════════════
 
   triggers:
-    # Primary trigger: When @dev starts a story
+    # Primary trigger: When @developer starts a story
     - event: story_started
-      agent: dev
+      agent: developer
       condition: projectConfig.autoWorktree.enabled === true
       action: create_worktree
 
-    # Secondary trigger: When @po assigns a story
+    # Secondary trigger: When @product-lead assigns a story
     - event: story_assigned
       agent: po
       condition: projectConfig.autoWorktree.createOnAssign === true
@@ -386,7 +386,7 @@ workflow:
   # ═══════════════════════════════════════════════════════════════════════════════════
 
   integration:
-    # Integration with @dev agent
+    # Integration with @developer agent
     dev_agent:
       hook: on_story_start
       action: trigger_workflow

package/.sinapse-ai/development/workflows/brownfield-discovery.yaml

@@ -349,7 +349,7 @@ workflow:
       elicit: true
       duration_estimate: "30-45 min"
       notes: |
-        @qa faz review geral de qualidade do assessment:
+        @quality-gate faz review geral de qualidade do assessment:
 
         RESPONSABILIDADES:
         1. IDENTIFICAR GAPS
@@ -376,7 +376,7 @@ workflow:
            - O assessment está completo?
            - Pode seguir para planning?
 
-        COMANDO: @qa (prompt manual)
+        COMANDO: @quality-gate (prompt manual)
 
         PROMPT:
         ```
@@ -659,7 +659,7 @@ workflow:
       elicit: true
       duration_estimate: "20-30 min"
       notes: |
-        @pm cria epic baseado no assessment validado:
+        @project-lead cria epic baseado no assessment validado:
 
         EPIC: "Resolução de Débitos Técnicos - [Nome do Projeto]"
 
@@ -671,7 +671,7 @@ workflow:
         - Budget aprovado
         - Lista de stories
 
-        COMANDO: @pm → *create-epic
+        COMANDO: @project-lead → *create-epic
 
         OUTPUT: docs/stories/epic-technical-debt.md
 
@@ -686,7 +686,7 @@ workflow:
       elicit: true
       duration_estimate: "15-20 min por story"
       notes: |
-        @pm cria stories para cada débito/grupo de débitos:
+        @project-lead cria stories para cada débito/grupo de débitos:
 
         Para cada item priorizado:
         - Story com tasks claras
@@ -695,7 +695,7 @@ workflow:
         - Estimativa validada pelos especialistas
         - Definition of Done
 
-        COMANDO: @pm → *create-story (repetir)
+        COMANDO: @project-lead → *create-story (repetir)
 
         OUTPUT:
         - docs/stories/story-1.1-fix-security-rls.md
@@ -742,7 +742,7 @@ workflow:
         PRÓXIMOS PASSOS:
         1. Apresentar TECHNICAL-DEBT-REPORT.md para stakeholders
         2. Obter aprovação de budget
-        3. Iniciar desenvolvimento: @dev → story-1.1
+        3. Iniciar desenvolvimento: @developer → story-1.1
 
         TEMPO TOTAL ESTIMADO: 4-6 horas
 
@@ -842,7 +842,7 @@ workflow:
       duration: "20-30 min"
     fase_7:
       name: "QA Review"
-      agent: "@qa"
+      agent: "@quality-gate"
       command: "(manual review)"
       output: "docs/reviews/qa-review.md"
       duration: "30-45 min"
@@ -860,7 +860,7 @@ workflow:
       duration: "30-45 min"
     fase_10:
       name: "Planning"
-      agent: "@pm"
+      agent: "@project-lead"
       command: "*brownfield-create-epic + *brownfield-create-story"
       output: "docs/stories/epic-*.md, story-*.md"
       duration: "30-60 min"
@@ -917,7 +917,7 @@ workflow:
     report_complete: |
       Relatório executivo: docs/reports/TECHNICAL-DEBT-REPORT.md
 
-      Próximo: @pm para criar epic e stories (FASE 10)
+      Próximo: @project-lead para criar epic e stories (FASE 10)
 
     workflow_complete: |
       ✅ DISCOVERY COMPLETO!
@@ -929,4 +929,4 @@ workflow:
       - docs/stories/epic-technical-debt.md
       - docs/stories/story-*.md
 
-      Pronto para: @dev implementar stories
+      Pronto para: @developer implementar stories

package/.sinapse-ai/development/workflows/brownfield-fullstack.yaml

@@ -146,7 +146,7 @@ workflow:
         - architecture.md
       notes: |
         Shard documents for IDE development:
-        - Option A: Use PO agent to shard: @po then ask to shard docs/prd.md
+        - Option A: Use PO agent to shard: @product-lead then ask to shard docs/prd.md
         - Option B: Manual: Drag shard-doc task + docs/prd.md into chat
         - Creates docs/prd/ and docs/architecture/ folders with sharded content
 
@@ -162,8 +162,8 @@ workflow:
       repeats: for_each_epic_or_enhancement
       notes: |
         Story creation cycle:
-        - For sharded PRD: @sm → *create (uses create-next-story)
-        - For brownfield docs: @sm → use create-brownfield-story task
+        - For sharded PRD: @sprint-lead → *create (uses create-next-story)
+        - For brownfield docs: @sprint-lead → use create-brownfield-story task
         - Creates story from available documentation
         - Story starts in "Draft" status
         - May require additional context gathering for brownfield
@@ -184,7 +184,7 @@ workflow:
         - Update story status: Draft → Approved
 
     - id: dev-implement-story
-      agent: dev
+      agent: developer
       action: implement_story
       creates: implementation_files
       duration_estimate: "1-4 hours"
@@ -203,14 +203,14 @@ workflow:
       requires: implementation_files
       optional: true
       notes: |
-        OPTIONAL: QA Agent (New Chat): @qa → review-story
+        OPTIONAL: QA Agent (New Chat): @quality-gate → review-story
         - Senior dev review with refactoring ability
         - Fixes small issues directly
         - Leaves checklist for remaining items
         - Updates story status (Review → Done or stays Review)
 
     - id: dev-address-qa-feedback
-      agent: dev
+      agent: developer
       action: address_qa_feedback
       updates: implementation_files
       requires: implementation_files