agentic-qe 1.9.1 → 1.9.3
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.
- package/.claude/helpers/checkpoint-manager.sh +251 -0
- package/.claude/helpers/github-safe.js +106 -0
- package/.claude/helpers/github-setup.sh +28 -0
- package/.claude/helpers/quick-start.sh +19 -0
- package/.claude/helpers/setup-mcp.sh +18 -0
- package/.claude/helpers/standard-checkpoint-hooks.sh +179 -0
- package/CHANGELOG.md +36 -0
- package/README.md +33 -1
- package/dist/core/memory/SwarmMemoryManager.d.ts.map +1 -1
- package/dist/core/memory/SwarmMemoryManager.js +45 -5
- package/dist/core/memory/SwarmMemoryManager.js.map +1 -1
- package/dist/mcp/handlers/memory/memory-store.d.ts +6 -2
- package/dist/mcp/handlers/memory/memory-store.d.ts.map +1 -1
- package/dist/mcp/handlers/memory/memory-store.js +26 -4
- package/dist/mcp/handlers/memory/memory-store.js.map +1 -1
- package/dist/mcp/server.d.ts.map +1 -1
- package/dist/mcp/server.js +2 -1
- package/dist/mcp/server.js.map +1 -1
- package/docs/README.md +839 -0
- package/docs/reference/agents.md +412 -0
- package/docs/reference/skills.md +796 -0
- package/docs/reference/usage.md +512 -0
- package/package.json +4 -1
- package/templates/agent-code-execution-template.md +619 -0
- package/templates/aqe.sh +20 -0
- package/.claude/commands/github/code-review-swarm.md +0 -514
- package/.claude/commands/github/github-modes.md +0 -147
- package/.claude/commands/github/issue-tracker.md +0 -292
- package/.claude/commands/github/multi-repo-swarm.md +0 -519
- package/.claude/commands/github/pr-manager.md +0 -170
- package/.claude/commands/github/project-board-sync.md +0 -471
- package/.claude/commands/github/release-manager.md +0 -338
- package/.claude/commands/github/release-swarm.md +0 -544
- package/.claude/commands/github/repo-architect.md +0 -367
- package/.claude/commands/github/swarm-issue.md +0 -482
- package/.claude/commands/github/swarm-pr.md +0 -285
- package/.claude/commands/github/sync-coordinator.md +0 -301
- package/.claude/commands/github/workflow-automation.md +0 -442
- package/.claude/commands/hooks/overview.md +0 -132
- package/.claude/commands/pair/commands.md +0 -546
- package/.claude/commands/pair/config.md +0 -510
- package/.claude/commands/pair/examples.md +0 -512
- package/.claude/commands/pair/modes.md +0 -348
- package/.claude/commands/pair/session.md +0 -407
- package/.claude/commands/pair/start.md +0 -209
- package/.claude/commands/sparc/orchestrator.md +0 -132
- package/.claude/commands/sparc/sparc-modes.md +0 -174
- package/.claude/commands/stream-chain/pipeline.md +0 -121
- package/.claude/commands/stream-chain/run.md +0 -70
- package/.claude/commands/swarm/analysis.md +0 -95
- package/.claude/commands/swarm/development.md +0 -96
- package/.claude/commands/swarm/examples.md +0 -168
- package/.claude/commands/swarm/maintenance.md +0 -102
- package/.claude/commands/swarm/optimization.md +0 -117
- package/.claude/commands/swarm/research.md +0 -136
- package/.claude/commands/swarm/testing.md +0 -131
- package/.claude/commands/truth/start.md +0 -143
- package/.claude/commands/verify/check.md +0 -50
- package/.claude/commands/verify/start.md +0 -128
|
@@ -0,0 +1,412 @@
|
|
|
1
|
+
# Agentic QE Fleet - Agent Reference
|
|
2
|
+
|
|
3
|
+
This document provides comprehensive reference for all 18 QE agents in the Agentic Quality Engineering Fleet.
|
|
4
|
+
|
|
5
|
+
## Overview
|
|
6
|
+
|
|
7
|
+
The Agentic QE Fleet is a distributed swarm of AI agents for comprehensive software testing and quality assurance. Each agent specializes in specific quality engineering tasks and coordinates through the `aqe/*` memory namespace.
|
|
8
|
+
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
## Core Testing Agents (5 agents)
|
|
12
|
+
|
|
13
|
+
### qe-test-generator
|
|
14
|
+
**AI-powered test generation with sublinear optimization**
|
|
15
|
+
|
|
16
|
+
**Capabilities:**
|
|
17
|
+
- Generates unit, integration, and E2E tests
|
|
18
|
+
- Supports Jest, Mocha, Vitest, Playwright
|
|
19
|
+
- Sublinear optimization algorithms for test selection
|
|
20
|
+
- Property-based testing generation
|
|
21
|
+
- Edge case discovery
|
|
22
|
+
|
|
23
|
+
**Usage:**
|
|
24
|
+
```javascript
|
|
25
|
+
Task("Generate tests", "Create comprehensive test suite for UserService", "qe-test-generator")
|
|
26
|
+
```
|
|
27
|
+
|
|
28
|
+
**Memory Namespace:**
|
|
29
|
+
- Stores: `aqe/test-plan/generated`
|
|
30
|
+
- Reads: `aqe/coverage/gaps`
|
|
31
|
+
|
|
32
|
+
---
|
|
33
|
+
|
|
34
|
+
### qe-test-executor
|
|
35
|
+
**Multi-framework test execution with parallel processing**
|
|
36
|
+
|
|
37
|
+
**Capabilities:**
|
|
38
|
+
- Executes tests across multiple frameworks
|
|
39
|
+
- Parallel test execution with worker pools
|
|
40
|
+
- Real-time progress streaming
|
|
41
|
+
- Test retry logic for flaky tests
|
|
42
|
+
- Coverage collection
|
|
43
|
+
|
|
44
|
+
**Usage:**
|
|
45
|
+
```javascript
|
|
46
|
+
Task("Execute tests", "Run test plan with 90% coverage target", "qe-test-executor")
|
|
47
|
+
```
|
|
48
|
+
|
|
49
|
+
**Memory Namespace:**
|
|
50
|
+
- Stores: `aqe/test-results/*`
|
|
51
|
+
- Reads: `aqe/test-plan/generated`
|
|
52
|
+
|
|
53
|
+
---
|
|
54
|
+
|
|
55
|
+
### qe-coverage-analyzer
|
|
56
|
+
**Real-time gap detection with O(log n) algorithms**
|
|
57
|
+
|
|
58
|
+
**Capabilities:**
|
|
59
|
+
- Incremental coverage analysis
|
|
60
|
+
- Sublinear gap detection algorithms
|
|
61
|
+
- Critical path identification
|
|
62
|
+
- Coverage visualization
|
|
63
|
+
- Untested code hotspot detection
|
|
64
|
+
|
|
65
|
+
**Usage:**
|
|
66
|
+
```javascript
|
|
67
|
+
Task("Analyze coverage", "Find gaps using O(log n) algorithms", "qe-coverage-analyzer")
|
|
68
|
+
```
|
|
69
|
+
|
|
70
|
+
**Memory Namespace:**
|
|
71
|
+
- Stores: `aqe/coverage/gaps`, `aqe/coverage/results`
|
|
72
|
+
- Reads: `aqe/test-results/*`
|
|
73
|
+
|
|
74
|
+
---
|
|
75
|
+
|
|
76
|
+
### qe-quality-gate
|
|
77
|
+
**Intelligent quality gate with risk assessment**
|
|
78
|
+
|
|
79
|
+
**Capabilities:**
|
|
80
|
+
- Multi-factor risk assessment
|
|
81
|
+
- Customizable quality thresholds
|
|
82
|
+
- Trend analysis
|
|
83
|
+
- Deployment readiness scoring
|
|
84
|
+
- Automated go/no-go decisions
|
|
85
|
+
|
|
86
|
+
**Usage:**
|
|
87
|
+
```javascript
|
|
88
|
+
Task("Quality check", "Run quality gate validation", "qe-quality-gate")
|
|
89
|
+
```
|
|
90
|
+
|
|
91
|
+
**Memory Namespace:**
|
|
92
|
+
- Stores: `aqe/quality/gate-results`
|
|
93
|
+
- Reads: `aqe/coverage/results`, `aqe/test-results/*`
|
|
94
|
+
|
|
95
|
+
---
|
|
96
|
+
|
|
97
|
+
### qe-quality-analyzer
|
|
98
|
+
**Comprehensive quality metrics analysis**
|
|
99
|
+
|
|
100
|
+
**Capabilities:**
|
|
101
|
+
- Quality metrics collection and analysis
|
|
102
|
+
- Trend detection and prediction
|
|
103
|
+
- Technical debt calculation
|
|
104
|
+
- Code health scoring
|
|
105
|
+
- Actionable insights generation
|
|
106
|
+
|
|
107
|
+
**Usage:**
|
|
108
|
+
```javascript
|
|
109
|
+
Task("Quality analysis", "Analyze project quality metrics", "qe-quality-analyzer")
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
**Memory Namespace:**
|
|
113
|
+
- Stores: `aqe/quality/metrics`
|
|
114
|
+
- Reads: `aqe/quality/*`, `aqe/test-results/*`
|
|
115
|
+
|
|
116
|
+
---
|
|
117
|
+
|
|
118
|
+
## Performance & Security Agents (2 agents)
|
|
119
|
+
|
|
120
|
+
### qe-performance-tester
|
|
121
|
+
**Load testing with k6, JMeter, Gatling integration**
|
|
122
|
+
|
|
123
|
+
**Capabilities:**
|
|
124
|
+
- Load, stress, and spike testing
|
|
125
|
+
- Performance baseline establishment
|
|
126
|
+
- Bottleneck identification
|
|
127
|
+
- SLA validation
|
|
128
|
+
- Multi-tool integration (k6, JMeter, Gatling)
|
|
129
|
+
|
|
130
|
+
**Usage:**
|
|
131
|
+
```javascript
|
|
132
|
+
Task("Performance test", "Load test critical paths with 1000 concurrent users", "qe-performance-tester")
|
|
133
|
+
```
|
|
134
|
+
|
|
135
|
+
**Memory Namespace:**
|
|
136
|
+
- Stores: `aqe/performance/results`
|
|
137
|
+
- Reads: `aqe/test-plan/*`
|
|
138
|
+
|
|
139
|
+
---
|
|
140
|
+
|
|
141
|
+
### qe-security-scanner
|
|
142
|
+
**Multi-layer security with SAST/DAST scanning**
|
|
143
|
+
|
|
144
|
+
**Capabilities:**
|
|
145
|
+
- SAST (Static Application Security Testing)
|
|
146
|
+
- DAST (Dynamic Application Security Testing)
|
|
147
|
+
- Dependency vulnerability scanning
|
|
148
|
+
- OWASP Top 10 validation
|
|
149
|
+
- Security compliance checking
|
|
150
|
+
|
|
151
|
+
**Usage:**
|
|
152
|
+
```javascript
|
|
153
|
+
Task("Security scan", "Run comprehensive security checks", "qe-security-scanner")
|
|
154
|
+
```
|
|
155
|
+
|
|
156
|
+
**Memory Namespace:**
|
|
157
|
+
- Stores: `aqe/security/findings`
|
|
158
|
+
- Reads: `aqe/test-plan/*`
|
|
159
|
+
|
|
160
|
+
---
|
|
161
|
+
|
|
162
|
+
## Strategic Planning Agents (3 agents)
|
|
163
|
+
|
|
164
|
+
### qe-requirements-validator
|
|
165
|
+
**INVEST criteria validation and BDD generation**
|
|
166
|
+
|
|
167
|
+
**Capabilities:**
|
|
168
|
+
- Requirements testability analysis
|
|
169
|
+
- INVEST criteria validation
|
|
170
|
+
- BDD scenario generation (Gherkin)
|
|
171
|
+
- Acceptance criteria validation
|
|
172
|
+
- Requirements ambiguity detection
|
|
173
|
+
|
|
174
|
+
**Usage:**
|
|
175
|
+
```javascript
|
|
176
|
+
Task("Validate requirements", "Check testability and generate BDD scenarios", "qe-requirements-validator")
|
|
177
|
+
```
|
|
178
|
+
|
|
179
|
+
**Memory Namespace:**
|
|
180
|
+
- Stores: `aqe/requirements/validated`
|
|
181
|
+
- Reads: `aqe/test-plan/*`
|
|
182
|
+
|
|
183
|
+
---
|
|
184
|
+
|
|
185
|
+
### qe-production-intelligence
|
|
186
|
+
**Production data to test scenarios conversion**
|
|
187
|
+
|
|
188
|
+
**Capabilities:**
|
|
189
|
+
- Production incident replay
|
|
190
|
+
- RUM (Real User Monitoring) analysis
|
|
191
|
+
- Log-based test generation
|
|
192
|
+
- Production pattern extraction
|
|
193
|
+
- Edge case discovery from production
|
|
194
|
+
|
|
195
|
+
**Usage:**
|
|
196
|
+
```javascript
|
|
197
|
+
Task("Production intelligence", "Convert production incidents to test scenarios", "qe-production-intelligence")
|
|
198
|
+
```
|
|
199
|
+
|
|
200
|
+
**Memory Namespace:**
|
|
201
|
+
- Stores: `aqe/production/insights`
|
|
202
|
+
- Reads: Production logs, incident data
|
|
203
|
+
|
|
204
|
+
---
|
|
205
|
+
|
|
206
|
+
### qe-fleet-commander
|
|
207
|
+
**Hierarchical fleet coordination (50+ agents)**
|
|
208
|
+
|
|
209
|
+
**Capabilities:**
|
|
210
|
+
- Multi-agent orchestration
|
|
211
|
+
- Resource allocation
|
|
212
|
+
- Task decomposition and distribution
|
|
213
|
+
- Agent performance monitoring
|
|
214
|
+
- Coordination topology optimization
|
|
215
|
+
|
|
216
|
+
**Usage:**
|
|
217
|
+
```javascript
|
|
218
|
+
Task("Fleet coordination", "Orchestrate 20 agents for comprehensive testing", "qe-fleet-commander")
|
|
219
|
+
```
|
|
220
|
+
|
|
221
|
+
**Memory Namespace:**
|
|
222
|
+
- Stores: `aqe/swarm/coordination`
|
|
223
|
+
- Reads: All `aqe/*` namespaces
|
|
224
|
+
|
|
225
|
+
---
|
|
226
|
+
|
|
227
|
+
## Deployment Agent (1 agent)
|
|
228
|
+
|
|
229
|
+
### qe-deployment-readiness
|
|
230
|
+
**Multi-factor risk assessment for deployments**
|
|
231
|
+
|
|
232
|
+
**Capabilities:**
|
|
233
|
+
- Deployment risk scoring
|
|
234
|
+
- Rollback plan validation
|
|
235
|
+
- Production readiness checklist
|
|
236
|
+
- Release notes generation
|
|
237
|
+
- Deployment window optimization
|
|
238
|
+
|
|
239
|
+
**Usage:**
|
|
240
|
+
```javascript
|
|
241
|
+
Task("Deployment check", "Assess deployment readiness", "qe-deployment-readiness")
|
|
242
|
+
```
|
|
243
|
+
|
|
244
|
+
**Memory Namespace:**
|
|
245
|
+
- Stores: `aqe/deployment/readiness`
|
|
246
|
+
- Reads: `aqe/quality/*`, `aqe/test-results/*`
|
|
247
|
+
|
|
248
|
+
---
|
|
249
|
+
|
|
250
|
+
## Advanced Testing Agents (4 agents)
|
|
251
|
+
|
|
252
|
+
### qe-regression-risk-analyzer
|
|
253
|
+
**Smart test selection with ML patterns**
|
|
254
|
+
|
|
255
|
+
**Capabilities:**
|
|
256
|
+
- Change impact analysis
|
|
257
|
+
- Intelligent test selection
|
|
258
|
+
- Regression risk prediction
|
|
259
|
+
- Test prioritization
|
|
260
|
+
- Historical failure pattern analysis
|
|
261
|
+
|
|
262
|
+
**Usage:**
|
|
263
|
+
```javascript
|
|
264
|
+
Task("Regression analysis", "Select minimal test suite for code changes", "qe-regression-risk-analyzer")
|
|
265
|
+
```
|
|
266
|
+
|
|
267
|
+
**Memory Namespace:**
|
|
268
|
+
- Stores: `aqe/regression/risk-analysis`
|
|
269
|
+
- Reads: `aqe/test-results/*`, learning patterns
|
|
270
|
+
|
|
271
|
+
---
|
|
272
|
+
|
|
273
|
+
### qe-test-data-architect
|
|
274
|
+
**High-speed realistic data generation (10k+ records/sec)**
|
|
275
|
+
|
|
276
|
+
**Capabilities:**
|
|
277
|
+
- Schema-aware data generation
|
|
278
|
+
- Relationship preservation
|
|
279
|
+
- Edge case coverage
|
|
280
|
+
- GDPR-compliant data masking
|
|
281
|
+
- High-performance generation (10k+ records/sec)
|
|
282
|
+
|
|
283
|
+
**Usage:**
|
|
284
|
+
```javascript
|
|
285
|
+
Task("Generate test data", "Create 10k realistic user records", "qe-test-data-architect")
|
|
286
|
+
```
|
|
287
|
+
|
|
288
|
+
**Memory Namespace:**
|
|
289
|
+
- Stores: `aqe/test-data/generated`
|
|
290
|
+
- Reads: Database schemas
|
|
291
|
+
|
|
292
|
+
---
|
|
293
|
+
|
|
294
|
+
### qe-api-contract-validator
|
|
295
|
+
**Breaking change detection across API versions**
|
|
296
|
+
|
|
297
|
+
**Capabilities:**
|
|
298
|
+
- API contract validation
|
|
299
|
+
- Breaking change detection
|
|
300
|
+
- Backward compatibility verification
|
|
301
|
+
- OpenAPI/Swagger validation
|
|
302
|
+
- Consumer-driven contract testing
|
|
303
|
+
|
|
304
|
+
**Usage:**
|
|
305
|
+
```javascript
|
|
306
|
+
Task("Validate API contracts", "Check for breaking changes", "qe-api-contract-validator")
|
|
307
|
+
```
|
|
308
|
+
|
|
309
|
+
**Memory Namespace:**
|
|
310
|
+
- Stores: `aqe/api/contract-validation`
|
|
311
|
+
- Reads: API specifications
|
|
312
|
+
|
|
313
|
+
---
|
|
314
|
+
|
|
315
|
+
### qe-flaky-test-hunter
|
|
316
|
+
**Statistical flakiness detection and auto-stabilization**
|
|
317
|
+
|
|
318
|
+
**Capabilities:**
|
|
319
|
+
- Flaky test detection with ML
|
|
320
|
+
- Root cause analysis
|
|
321
|
+
- Auto-stabilization strategies
|
|
322
|
+
- Statistical significance testing
|
|
323
|
+
- Retry policy optimization
|
|
324
|
+
|
|
325
|
+
**Usage:**
|
|
326
|
+
```javascript
|
|
327
|
+
Task("Hunt flaky tests", "Detect and stabilize flaky tests", "qe-flaky-test-hunter")
|
|
328
|
+
```
|
|
329
|
+
|
|
330
|
+
**Memory Namespace:**
|
|
331
|
+
- Stores: `aqe/flaky-tests/detected`
|
|
332
|
+
- Reads: `aqe/test-results/*`, historical test data
|
|
333
|
+
|
|
334
|
+
---
|
|
335
|
+
|
|
336
|
+
## Specialized Agents (2 agents)
|
|
337
|
+
|
|
338
|
+
### qe-visual-tester
|
|
339
|
+
**Visual regression with AI-powered comparison**
|
|
340
|
+
|
|
341
|
+
**Capabilities:**
|
|
342
|
+
- Screenshot-based visual testing
|
|
343
|
+
- AI-powered image comparison
|
|
344
|
+
- Layout shift detection
|
|
345
|
+
- Accessibility visual validation
|
|
346
|
+
- Cross-browser visual testing
|
|
347
|
+
|
|
348
|
+
**Usage:**
|
|
349
|
+
```javascript
|
|
350
|
+
Task("Visual testing", "Run visual regression tests", "qe-visual-tester")
|
|
351
|
+
```
|
|
352
|
+
|
|
353
|
+
**Memory Namespace:**
|
|
354
|
+
- Stores: `aqe/visual/results`
|
|
355
|
+
- Reads: `aqe/test-plan/*`
|
|
356
|
+
|
|
357
|
+
---
|
|
358
|
+
|
|
359
|
+
### qe-chaos-engineer
|
|
360
|
+
**Resilience testing with controlled fault injection**
|
|
361
|
+
|
|
362
|
+
**Capabilities:**
|
|
363
|
+
- Controlled fault injection
|
|
364
|
+
- Resilience testing
|
|
365
|
+
- Blast radius management
|
|
366
|
+
- Recovery validation
|
|
367
|
+
- System stability verification
|
|
368
|
+
|
|
369
|
+
**Usage:**
|
|
370
|
+
```javascript
|
|
371
|
+
Task("Chaos testing", "Test system resilience with controlled failures", "qe-chaos-engineer")
|
|
372
|
+
```
|
|
373
|
+
|
|
374
|
+
**Memory Namespace:**
|
|
375
|
+
- Stores: `aqe/chaos/results`
|
|
376
|
+
- Reads: `aqe/test-plan/*`
|
|
377
|
+
|
|
378
|
+
---
|
|
379
|
+
|
|
380
|
+
## Agent Coordination
|
|
381
|
+
|
|
382
|
+
All agents coordinate through the **`aqe/*` memory namespace**:
|
|
383
|
+
|
|
384
|
+
- `aqe/test-plan/*` - Test planning and requirements
|
|
385
|
+
- `aqe/coverage/*` - Coverage analysis and gaps
|
|
386
|
+
- `aqe/quality/*` - Quality metrics and gates
|
|
387
|
+
- `aqe/performance/*` - Performance test results
|
|
388
|
+
- `aqe/security/*` - Security scan findings
|
|
389
|
+
- `aqe/swarm/coordination` - Cross-agent coordination
|
|
390
|
+
|
|
391
|
+
## Parallel Agent Execution
|
|
392
|
+
|
|
393
|
+
Execute multiple agents concurrently for maximum efficiency:
|
|
394
|
+
|
|
395
|
+
```javascript
|
|
396
|
+
// Execute multiple agents in parallel
|
|
397
|
+
Task("Test Generation", "Generate unit tests", "qe-test-generator")
|
|
398
|
+
Task("Coverage Analysis", "Analyze current coverage", "qe-coverage-analyzer")
|
|
399
|
+
Task("Security Scan", "Run security checks", "qe-security-scanner")
|
|
400
|
+
Task("Performance Test", "Load test critical paths", "qe-performance-tester")
|
|
401
|
+
```
|
|
402
|
+
|
|
403
|
+
---
|
|
404
|
+
|
|
405
|
+
**Related Documentation:**
|
|
406
|
+
- [Skills Reference](skills.md) - All 34 QE skills
|
|
407
|
+
- [Usage Guide](usage.md) - Complete usage examples
|
|
408
|
+
- [AQE Hooks](../architecture/AQE-HOOKS.md) - Agent coordination details
|
|
409
|
+
|
|
410
|
+
**Related Policies:**
|
|
411
|
+
- [Release Verification Policy](../policies/release-verification.md)
|
|
412
|
+
- [Test Execution Policy](../policies/test-execution.md)
|