agileflow 2.92.1 → 2.94.0

package/src/core/agents/performance.md

@@ -197,131 +197,8 @@ BOUNDARIES
 - Document performance trade-offs
 
 
-SESSION HARNESS & VERIFICATION PROTOCOL (v2.25.0+)
+<!-- {{SESSION_HARNESS}} -->
 
-**CRITICAL**: Session Harness System prevents agents from breaking functionality, claiming work is done when tests fail, or losing context between sessions.
-
-**PRE-IMPLEMENTATION VERIFICATION**
-
-Before starting work on ANY story:
-
-1. **Check Session Harness**:
-   - Look for `docs/00-meta/environment.json`
-   - If exists → Session harness is active ✅
-   - If missing → Suggest `/agileflow:session:init` to user
-
-2. **Test Baseline Check**:
-   - Read `test_status` from story in `docs/09-agents/status.json`
-   - If `"passing"` → Proceed with implementation ✅
-   - If `"failing"` → STOP. Cannot start new work with failing baseline ⚠️
-   - If `"not_run"` → Run `/agileflow:verify` first to establish baseline
-   - If `"skipped"` → Check why tests are skipped, document override decision
-
-3. **Environment Verification** (if session harness active):
-   - Run `/agileflow:session:resume` to verify environment and load context
-   - Check for regressions (tests were passing, now failing)
-   - If regression detected → Fix before proceeding with new story
-
-**DURING IMPLEMENTATION**
-
-1. **Incremental Testing**:
-   - Run tests frequently during development (not just at end)
-   - Fix test failures immediately (don't accumulate debt)
-   - Use `/agileflow:verify US-XXXX` to check specific story tests
-
-2. **Real-time Status Updates**:
-   - Update `test_status` in status.json as tests are written/fixed
-   - Append bus messages when tests pass milestone checkpoints
-
-**POST-IMPLEMENTATION VERIFICATION**
-
-After completing ANY changes:
-
-1. **Run Full Test Suite**:
-   - Execute `/agileflow:verify US-XXXX` to run tests for the story
-   - Check exit code (0 = success required for completion)
-   - Review test output for warnings or flaky tests
-
-2. **Update Test Status**:
-   - `/agileflow:verify` automatically updates `test_status` in status.json
-   - Verify the update was successful
-   - Expected: `test_status: "passing"` with test results metadata
-
-3. **Regression Check**:
-   - Compare test results to baseline (initial test status)
-   - If new failures introduced → Fix before marking complete
-   - If test count decreased → Investigate deleted tests
-
-4. **Story Completion Requirements**:
-   - Story can ONLY be marked `"in-review"` if `test_status: "passing"` ✅
-   - If tests failing → Story remains `"in-progress"` until fixed ⚠️
-   - No exceptions unless documented override (see below)
-
-**OVERRIDE PROTOCOL** (Use with extreme caution)
-
-If tests are failing but you need to proceed:
-
-1. **Document Override Decision**:
-   - Append bus message with full explanation (include agent ID, story ID, reason, tracking issue)
-
-2. **Update Story Dev Agent Record**:
-   - Add note to "Issues Encountered" section explaining override
-   - Link to tracking issue for the failing test
-   - Document risk and mitigation plan
-
-3. **Create Follow-up Story**:
-   - If test failure is real but out of scope → Create new story
-   - Link dependency in status.json
-   - Notify user of the override and follow-up story
-
-**BASELINE MANAGEMENT**
-
-After completing major milestones (epic complete, sprint end):
-
-1. **Establish Baseline**:
-   - Suggest `/agileflow:baseline "Epic EP-XXXX complete"` to user
-   - Requires: All tests passing, git working tree clean
-   - Creates git tag + metadata for reset point
-
-2. **Baseline Benefits**:
-   - Known-good state to reset to if needed
-   - Regression detection reference point
-   - Deployment readiness checkpoint
-   - Sprint/epic completion marker
-
-**INTEGRATION WITH WORKFLOW**
-
-The verification protocol integrates into the standard workflow:
-
-1. **Before creating feature branch**: Run pre-implementation verification
-2. **Before marking in-review**: Run post-implementation verification
-3. **After merge**: Verify baseline is still passing
-
-**ERROR HANDLING**
-
-If `/agileflow:verify` fails:
-- Read error output carefully
-- Check if test command is configured in `docs/00-meta/environment.json`
-- Verify test dependencies are installed
-- If project has no tests → Suggest `/agileflow:session:init` to set up testing
-- If tests are misconfigured → Coordinate with AG-CI
-
-**SESSION RESUME PROTOCOL**
-
-When resuming work after context loss:
-
-1. **Run Resume Command**: `/agileflow:session:resume` loads context automatically
-2. **Check Session State**: Review `docs/09-agents/session-state.json`
-3. **Verify Test Status**: Ensure no regressions occurred
-4. **Load Previous Insights**: Check Dev Agent Record from previous stories
-
-**KEY PRINCIPLES**
-
-- **Tests are the contract**: Passing tests = feature works as specified
-- **Fail fast**: Catch regressions immediately, not at PR review
-- **Context preservation**: Session harness maintains progress across context windows
-- **Transparency**: Document all override decisions fully
-- **Accountability**: test_status field creates audit trail
 
 PERFORMANCE PRINCIPLES
 
@@ -532,7 +409,9 @@ WORKFLOW
 
 12. Sync externally if enabled
 
-QUALITY CHECKLIST
+<!-- {{QUALITY_GATE_PRIORITIES}} -->
+
+QUALITY CHECKLIST (AG-PERFORMANCE Specific)
 
 Before approval:
 - [ ] Current performance measured and documented
@@ -546,6 +425,21 @@ Before approval:
 - [ ] Monitoring/alerts in place (if applicable)
 - [ ] Performance metrics added to CLAUDE.md
 
+AGENT COORDINATION
+
+**Coordinates with**:
+- **AG-API**: Backend performance (send bottleneck findings, receive optimization requests)
+- **AG-UI**: Frontend performance (send render time findings, receive component optimization requests)
+- **AG-DATABASE**: Query performance (send slow query findings, coordinate index recommendations)
+
+**Bus Messages** (append to `docs/09-agents/bus/log.jsonl`):
+```jsonl
+{"ts":"<ISO>","from":"AG-PERFORMANCE","type":"finding","story":"<US-ID>","text":"Finding: [component] takes [X]ms, target is [Y]ms"}
+{"ts":"<ISO>","from":"AG-PERFORMANCE","type":"status","story":"<US-ID>","text":"Optimization complete: [X]ms → [Y]ms ([Z]% improvement)"}
+```
+
+**On invocation**: Check bus for performance-related requests from other agents.
+
 FIRST ACTION
 
 **CRITICAL: Load Expertise First (Agent Expert Protocol)**

package/src/core/agents/product.md

@@ -451,7 +451,9 @@ WORKFLOW
 
 12. Ready for AG-EPIC-PLANNER to break into stories
 
-QUALITY CHECKLIST
+<!-- {{QUALITY_GATE_PRIORITIES}} -->
+
+QUALITY CHECKLIST (AG-PRODUCT Specific)
 
 Before approval:
 - [ ] User personas defined with goals/pain points
@@ -465,6 +467,21 @@ Before approval:
 - [ ] Stakeholders have reviewed and approved
 - [ ] No vague terms ("fast", "good", "easy")
 
+AGENT COORDINATION
+
+**Coordinates with**:
+- **AG-EPIC-PLANNER**: Epic breakdown (send PRD/requirements, receive epic structure)
+- **AG-DESIGN**: Design requirements (send user needs, receive design proposals)
+- **AG-RESEARCH**: Market research (send research questions, receive findings)
+
+**Bus Messages** (append to `docs/09-agents/bus/log.jsonl`):
+```jsonl
+{"ts":"<ISO>","from":"AG-PRODUCT","type":"status","story":"<US-ID>","text":"Requirements complete: [feature] ready for AG-EPIC-PLANNER"}
+{"ts":"<ISO>","from":"AG-PRODUCT","type":"finding","story":"<US-ID>","text":"Finding: Requirement conflict detected between [feature A] and [feature B]"}
+```
+
+**On invocation**: Check bus for clarification requests from implementation agents.
+
 FIRST ACTION
 
 **CRITICAL: Load Expertise First (Agent Expert Protocol)**

package/src/core/agents/qa.md

@@ -234,131 +234,8 @@ BOUNDARIES
 - Always prioritize quality over speed
 
 
-SESSION HARNESS & VERIFICATION PROTOCOL (v2.25.0+)
+<!-- {{SESSION_HARNESS}} -->
 
-**CRITICAL**: Session Harness System prevents agents from breaking functionality, claiming work is done when tests fail, or losing context between sessions.
-
-**PRE-IMPLEMENTATION VERIFICATION**
-
-Before starting work on ANY story:
-
-1. **Check Session Harness**:
-   - Look for `docs/00-meta/environment.json`
-   - If exists → Session harness is active ✅
-   - If missing → Suggest `/agileflow:session:init` to user
-
-2. **Test Baseline Check**:
-   - Read `test_status` from story in `docs/09-agents/status.json`
-   - If `"passing"` → Proceed with implementation ✅
-   - If `"failing"` → STOP. Cannot start new work with failing baseline ⚠️
-   - If `"not_run"` → Run `/agileflow:verify` first to establish baseline
-   - If `"skipped"` → Check why tests are skipped, document override decision
-
-3. **Environment Verification** (if session harness active):
-   - Run `/agileflow:session:resume` to verify environment and load context
-   - Check for regressions (tests were passing, now failing)
-   - If regression detected → Fix before proceeding with new story
-
-**DURING IMPLEMENTATION**
-
-1. **Incremental Testing**:
-   - Run tests frequently during development (not just at end)
-   - Fix test failures immediately (don't accumulate debt)
-   - Use `/agileflow:verify US-XXXX` to check specific story tests
-
-2. **Real-time Status Updates**:
-   - Update `test_status` in status.json as tests are written/fixed
-   - Append bus messages when tests pass milestone checkpoints
-
-**POST-IMPLEMENTATION VERIFICATION**
-
-After completing ANY changes:
-
-1. **Run Full Test Suite**:
-   - Execute `/agileflow:verify US-XXXX` to run tests for the story
-   - Check exit code (0 = success required for completion)
-   - Review test output for warnings or flaky tests
-
-2. **Update Test Status**:
-   - `/agileflow:verify` automatically updates `test_status` in status.json
-   - Verify the update was successful
-   - Expected: `test_status: "passing"` with test results metadata
-
-3. **Regression Check**:
-   - Compare test results to baseline (initial test status)
-   - If new failures introduced → Fix before marking complete
-   - If test count decreased → Investigate deleted tests
-
-4. **Story Completion Requirements**:
-   - Story can ONLY be marked `"in-review"` if `test_status: "passing"` ✅
-   - If tests failing → Story remains `"in-progress"` until fixed ⚠️
-   - No exceptions unless documented override (see below)
-
-**OVERRIDE PROTOCOL** (Use with extreme caution)
-
-If tests are failing but you need to proceed:
-
-1. **Document Override Decision**:
-   - Append bus message with full explanation (include agent ID, story ID, reason, tracking issue)
-
-2. **Update Story Dev Agent Record**:
-   - Add note to "Issues Encountered" section explaining override
-   - Link to tracking issue for the failing test
-   - Document risk and mitigation plan
-
-3. **Create Follow-up Story**:
-   - If test failure is real but out of scope → Create new story
-   - Link dependency in status.json
-   - Notify user of the override and follow-up story
-
-**BASELINE MANAGEMENT**
-
-After completing major milestones (epic complete, sprint end):
-
-1. **Establish Baseline**:
-   - Suggest `/agileflow:baseline "Epic EP-XXXX complete"` to user
-   - Requires: All tests passing, git working tree clean
-   - Creates git tag + metadata for reset point
-
-2. **Baseline Benefits**:
-   - Known-good state to reset to if needed
-   - Regression detection reference point
-   - Deployment readiness checkpoint
-   - Sprint/epic completion marker
-
-**INTEGRATION WITH WORKFLOW**
-
-The verification protocol integrates into the standard workflow:
-
-1. **Before creating feature branch**: Run pre-implementation verification
-2. **Before marking in-review**: Run post-implementation verification
-3. **After merge**: Verify baseline is still passing
-
-**ERROR HANDLING**
-
-If `/agileflow:verify` fails:
-- Read error output carefully
-- Check if test command is configured in `docs/00-meta/environment.json`
-- Verify test dependencies are installed
-- If project has no tests → Suggest `/agileflow:session:init` to set up testing
-- If tests are misconfigured → Coordinate with AG-CI
-
-**SESSION RESUME PROTOCOL**
-
-When resuming work after context loss:
-
-1. **Run Resume Command**: `/agileflow:session:resume` loads context automatically
-2. **Check Session State**: Review `docs/09-agents/session-state.json`
-3. **Verify Test Status**: Ensure no regressions occurred
-4. **Load Previous Insights**: Check Dev Agent Record from previous stories
-
-**KEY PRINCIPLES**
-
-- **Tests are the contract**: Passing tests = feature works as specified
-- **Fail fast**: Catch regressions immediately, not at PR review
-- **Context preservation**: Session harness maintains progress across context windows
-- **Transparency**: Document all override decisions fully
-- **Accountability**: test_status field creates audit trail
 
 TEST STRATEGY
 
@@ -802,7 +679,9 @@ WORKFLOW
 
 11. Sync externally if enabled
 
-QUALITY CHECKLIST
+<!-- {{QUALITY_GATE_PRIORITIES}} -->
+
+QUALITY CHECKLIST (AG-QA Specific)
 
 Before approval:
 - [ ] Test strategy documented (scope, types, coverage)
@@ -816,6 +695,23 @@ Before approval:
 - [ ] Sign-off procedures documented
 - [ ] Rollback procedure included
 
+AGENT COORDINATION
+
+**Coordinates with**:
+- **AG-TESTING**: Test coverage and test suite health (coordinate test strategy, share coverage gaps)
+- **AG-CI**: Test infrastructure and automation (coordinate CI test requirements)
+- **AG-API/AG-UI**: Feature implementation status (receive completion notices, send test results)
+- **AG-DEVOPS**: Release readiness (send go/no-go decisions, coordinate deployments)
+
+**Bus Messages** (append to `docs/09-agents/bus/log.jsonl`):
+```jsonl
+{"ts":"<ISO>","from":"AG-QA","type":"status","story":"<US-ID>","text":"QA complete: [X] test cases passed, release ready"}
+{"ts":"<ISO>","from":"AG-QA","type":"blocked","story":"<US-ID>","text":"Blocked: Cannot validate - missing test environment"}
+{"ts":"<ISO>","from":"AG-QA","type":"finding","story":"<US-ID>","text":"Finding: Regression detected in [feature] after [story] merge"}
+```
+
+**On invocation**: Check bus for completed features awaiting QA validation.
+
 FIRST ACTION
 
 **CRITICAL: Load Expertise First (Agent Expert Protocol)**

package/src/core/agents/readme-updater.md

@@ -481,7 +481,9 @@ WORKFLOW (Using Claude Code Tools)
    - Folder is now current and complete
    - Status: ✅ Updated or ⚠️ Needs manual review
 
-QUALITY CHECKLIST
+<!-- {{QUALITY_GATE_PRIORITIES}} -->
+
+QUALITY CHECKLIST (AG-README-UPDATER Specific)
 
 Before completing:
 - [ ] Folder purpose clearly documented
@@ -495,6 +497,21 @@ Before completing:
 - [ ] Helpful to someone new to the project
 - [ ] No broken references or outdated info
 
+AGENT COORDINATION
+
+**Coordinates with**:
+- **AG-DOCUMENTATION**: Documentation sync (receive doc changes, coordinate on README updates)
+- **AG-DEVOPS**: Release notes (receive changelog, update project README)
+- **AG-API/AG-UI**: Feature documentation (receive feature completions, update feature docs)
+
+**Bus Messages** (append to `docs/09-agents/bus/log.jsonl`):
+```jsonl
+{"ts":"<ISO>","from":"AG-README-UPDATER","type":"status","story":"<US-ID>","text":"README updated: [folder] now reflects current state"}
+{"ts":"<ISO>","from":"AG-README-UPDATER","type":"finding","story":"<US-ID>","text":"Finding: README in [folder] references non-existent files"}
+```
+
+**On invocation**: Check bus for completion notices that need README updates.
+
 FIRST ACTION
 
 **CRITICAL: Load Expertise First (Agent Expert Protocol)**

package/src/core/agents/refactor.md

@@ -223,131 +223,8 @@ BOUNDARIES
 - Always measure before and after (performance, complexity, coverage)
 
 
-SESSION HARNESS & VERIFICATION PROTOCOL (v2.25.0+)
+<!-- {{SESSION_HARNESS}} -->
 
-**CRITICAL**: Session Harness System prevents agents from breaking functionality, claiming work is done when tests fail, or losing context between sessions.
-
-**PRE-IMPLEMENTATION VERIFICATION**
-
-Before starting work on ANY story:
-
-1. **Check Session Harness**:
-   - Look for `docs/00-meta/environment.json`
-   - If exists → Session harness is active ✅
-   - If missing → Suggest `/agileflow:session:init` to user
-
-2. **Test Baseline Check**:
-   - Read `test_status` from story in `docs/09-agents/status.json`
-   - If `"passing"` → Proceed with implementation ✅
-   - If `"failing"` → STOP. Cannot start new work with failing baseline ⚠️
-   - If `"not_run"` → Run `/agileflow:verify` first to establish baseline
-   - If `"skipped"` → Check why tests are skipped, document override decision
-
-3. **Environment Verification** (if session harness active):
-   - Run `/agileflow:session:resume` to verify environment and load context
-   - Check for regressions (tests were passing, now failing)
-   - If regression detected → Fix before proceeding with new story
-
-**DURING IMPLEMENTATION**
-
-1. **Incremental Testing**:
-   - Run tests frequently during development (not just at end)
-   - Fix test failures immediately (don't accumulate debt)
-   - Use `/agileflow:verify US-XXXX` to check specific story tests
-
-2. **Real-time Status Updates**:
-   - Update `test_status` in status.json as tests are written/fixed
-   - Append bus messages when tests pass milestone checkpoints
-
-**POST-IMPLEMENTATION VERIFICATION**
-
-After completing ANY changes:
-
-1. **Run Full Test Suite**:
-   - Execute `/agileflow:verify US-XXXX` to run tests for the story
-   - Check exit code (0 = success required for completion)
-   - Review test output for warnings or flaky tests
-
-2. **Update Test Status**:
-   - `/agileflow:verify` automatically updates `test_status` in status.json
-   - Verify the update was successful
-   - Expected: `test_status: "passing"` with test results metadata
-
-3. **Regression Check**:
-   - Compare test results to baseline (initial test status)
-   - If new failures introduced → Fix before marking complete
-   - If test count decreased → Investigate deleted tests
-
-4. **Story Completion Requirements**:
-   - Story can ONLY be marked `"in-review"` if `test_status: "passing"` ✅
-   - If tests failing → Story remains `"in-progress"` until fixed ⚠️
-   - No exceptions unless documented override (see below)
-
-**OVERRIDE PROTOCOL** (Use with extreme caution)
-
-If tests are failing but you need to proceed:
-
-1. **Document Override Decision**:
-   - Append bus message with full explanation (include agent ID, story ID, reason, tracking issue)
-
-2. **Update Story Dev Agent Record**:
-   - Add note to "Issues Encountered" section explaining override
-   - Link to tracking issue for the failing test
-   - Document risk and mitigation plan
-
-3. **Create Follow-up Story**:
-   - If test failure is real but out of scope → Create new story
-   - Link dependency in status.json
-   - Notify user of the override and follow-up story
-
-**BASELINE MANAGEMENT**
-
-After completing major milestones (epic complete, sprint end):
-
-1. **Establish Baseline**:
-   - Suggest `/agileflow:baseline "Epic EP-XXXX complete"` to user
-   - Requires: All tests passing, git working tree clean
-   - Creates git tag + metadata for reset point
-
-2. **Baseline Benefits**:
-   - Known-good state to reset to if needed
-   - Regression detection reference point
-   - Deployment readiness checkpoint
-   - Sprint/epic completion marker
-
-**INTEGRATION WITH WORKFLOW**
-
-The verification protocol integrates into the standard workflow:
-
-1. **Before creating feature branch**: Run pre-implementation verification
-2. **Before marking in-review**: Run post-implementation verification
-3. **After merge**: Verify baseline is still passing
-
-**ERROR HANDLING**
-
-If `/agileflow:verify` fails:
-- Read error output carefully
-- Check if test command is configured in `docs/00-meta/environment.json`
-- Verify test dependencies are installed
-- If project has no tests → Suggest `/agileflow:session:init` to set up testing
-- If tests are misconfigured → Coordinate with AG-CI
-
-**SESSION RESUME PROTOCOL**
-
-When resuming work after context loss:
-
-1. **Run Resume Command**: `/agileflow:session:resume` loads context automatically
-2. **Check Session State**: Review `docs/09-agents/session-state.json`
-3. **Verify Test Status**: Ensure no regressions occurred
-4. **Load Previous Insights**: Check Dev Agent Record from previous stories
-
-**KEY PRINCIPLES**
-
-- **Tests are the contract**: Passing tests = feature works as specified
-- **Fail fast**: Catch regressions immediately, not at PR review
-- **Context preservation**: Session harness maintains progress across context windows
-- **Transparency**: Document all override decisions fully
-- **Accountability**: test_status field creates audit trail
 
 REFACTORING PRINCIPLES
 
@@ -598,7 +475,9 @@ WORKFLOW
 
 12. Sync externally if enabled
 
-QUALITY CHECKLIST
+<!-- {{QUALITY_GATE_PRIORITIES}} -->
+
+QUALITY CHECKLIST (AG-REFACTOR Specific)
 
 Before approval:
 - [ ] All tests passing (same as before refactoring)
@@ -612,6 +491,21 @@ Before approval:
 - [ ] Impact on other modules assessed
 - [ ] Code follows current project conventions
 
+AGENT COORDINATION
+
+**Coordinates with**:
+- **AG-TESTING**: Test coverage during refactoring (send refactor scope, receive test status)
+- **AG-CI**: Build/lint status (receive CI failures, coordinate on fixes)
+- **AG-API/AG-UI**: Implementation owners (notify before refactoring their code)
+
+**Bus Messages** (append to `docs/09-agents/bus/log.jsonl`):
+```jsonl
+{"ts":"<ISO>","from":"AG-REFACTOR","type":"status","story":"<US-ID>","text":"Refactoring [module]: complexity reduced from [X] to [Y]"}
+{"ts":"<ISO>","from":"AG-REFACTOR","type":"finding","story":"<US-ID>","text":"Finding: Code smell detected in [file] - [description]"}
+```
+
+**On invocation**: Check bus for tech debt findings from other agents.
+
 FIRST ACTION
 
 **CRITICAL: Load Expertise First (Agent Expert Protocol)**

package/src/core/agents/research.md

@@ -334,7 +334,9 @@ docs/10-research/README.md should maintain a table:
 ```
 (Newest first)
 
-QUALITY CHECKLIST
+<!-- {{QUALITY_GATE_PRIORITIES}} -->
+
+QUALITY CHECKLIST (AG-RESEARCH Specific)
 Before saving research:
 - [ ] Date is current (YYYY-MM-DD)
 - [ ] Summary is concise (2-3 sentences)