@teevee98/synapse-hub 4.1.4 → 4.2.1
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/.agents/rules/git-push-protocol.md +2 -2
- package/.agents/skills/01-web-automation/auth-session-and-cookie-manager/SKILL.md +52 -3
- package/.agents/skills/01-web-automation/bats-testing-patterns/SKILL.md +55 -5
- package/.agents/skills/01-web-automation/clean-pom-crafter/SKILL.md +62 -67
- package/.agents/skills/01-web-automation/e2e-testing-patterns/SKILL.md +54 -4
- package/.agents/skills/01-web-automation/katalon-cli-runner/SKILL.md +62 -12
- package/.agents/skills/01-web-automation/lam-script-generator/SKILL.md +55 -8
- package/.agents/skills/01-web-automation/mobile-appium-som/SKILL.md +60 -12
- package/.agents/skills/01-web-automation/mobile-appium-som/examples/BaseScreen.java +2 -2
- package/.agents/skills/01-web-automation/mobile-appium-som/examples/LoginScreen.java +2 -2
- package/.agents/skills/01-web-automation/mobile-appium-som/examples/TC_MobileLogin.java +2 -2
- package/.agents/skills/01-web-automation/playwright-live-interaction/SKILL.md +54 -91
- package/.agents/skills/01-web-automation/playwright-webapp-testing/SKILL.md +59 -11
- package/.agents/skills/01-web-automation/web-agent-gym-benchmarking/SKILL.md +50 -4
- package/.agents/skills/02-test-design/architecture-decision-records/SKILL.md +55 -9
- package/.agents/skills/02-test-design/gherkin-to-suite/SKILL.md +55 -9
- package/.agents/skills/02-test-design/rbt-manual-testing/SKILL.md +55 -8
- package/.agents/skills/02-test-design/review-spec/SKILL.md +50 -6
- package/.agents/skills/02-test-design/tot-exploratory-testing/SKILL.md +50 -4
- package/.agents/skills/03-api-and-contracts/api-network-mocking-interception/SKILL.md +56 -5
- package/.agents/skills/03-api-and-contracts/api-spec-to-e2e-matrix/SKILL.md +53 -7
- package/.agents/skills/03-api-and-contracts/consumer-driven-contract-testing/SKILL.md +86 -36
- package/.agents/skills/04-performance-and-load/backend-load-and-stress-patterns/SKILL.md +54 -6
- package/.agents/skills/04-performance-and-load/lean-impact-scoreboard/SKILL.md +50 -6
- package/.agents/skills/04-performance-and-load/web-vitals-and-performance-profiler/SKILL.md +50 -3
- package/.agents/skills/05-security-and-compliance/security-dast-sentinel/SKILL.md +63 -14
- package/.agents/skills/05-security-and-compliance/skillspector-security-guard/SKILL.md +51 -5
- package/.agents/skills/05-security-and-compliance/wcag-audit-patterns/SKILL.md +54 -4
- package/.agents/skills/06-healing-and-resilience/agentless-qa-repair/SKILL.md +51 -5
- package/.agents/skills/06-healing-and-resilience/antigravity-test-sentinel/SKILL.md +53 -6
- package/.agents/skills/06-healing-and-resilience/failure-autopsy-and-healing/SKILL.md +54 -8
- package/.agents/skills/06-healing-and-resilience/flaky-test-sentinel-and-quarantine/SKILL.md +60 -24
- package/.agents/skills/06-healing-and-resilience/self-healing-locator/SKILL.md +52 -6
- package/.agents/skills/06-healing-and-resilience/systematic-debugging/SKILL.md +56 -10
- package/.agents/skills/06-healing-and-resilience/test-driven-development/SKILL.md +58 -12
- package/.agents/skills/06-healing-and-resilience/verification-before-completion/SKILL.md +58 -12
- package/.agents/skills/06-healing-and-resilience/visual-regression-sentinel/SKILL.md +53 -5
- package/.agents/skills/07-data-and-state/db-state-verifier-and-seeder/SKILL.md +56 -5
- package/.agents/skills/07-data-and-state/file-and-report-validator/SKILL.md +53 -4
- package/.agents/skills/07-data-and-state/synthetic-test-data-generator/SKILL.md +58 -5
- package/.agents/skills/08-code-quality/code-refactoring-refactor-clean/SKILL.md +57 -11
- package/.agents/skills/08-code-quality/graphify-impact-analyzer/SKILL.md +83 -34
- package/.agents/skills/08-code-quality/graphify-impact-analyzer/examples/dependency_blast_radius.json +3 -4
- package/.agents/skills/08-code-quality/lean-code-ladder/SKILL.md +55 -10
- package/.agents/skills/08-code-quality/repo-quality-audit/SKILL.md +49 -6
- package/.agents/skills/08-code-quality/senior-code-review/SKILL.md +52 -7
- package/.agents/skills/08-code-quality/surgical-coding-principles/SKILL.md +55 -10
- package/.agents/skills/08-code-quality/technical-debt-harvester/SKILL.md +51 -5
- package/.agents/skills/09-ci-and-devops/github-actions-templates/SKILL.md +54 -17
- package/.agents/skills/09-ci-and-devops/github-actions-templates/examples/matrix_test_pipeline.yml +2 -1
- package/.agents/skills/10-agent-orchestration/actor-qa-swarm/SKILL.md +50 -4
- package/.agents/skills/10-agent-orchestration/agent-orchestration-multi-agent-optimize/SKILL.md +53 -7
- package/.agents/skills/10-agent-orchestration/event-stream-qa-orchestrator/SKILL.md +50 -4
- package/.agents/skills/10-agent-orchestration/persistent-planning-files/SKILL.md +58 -13
- package/.agents/skills/10-agent-orchestration/qa-memory-os/SKILL.md +51 -5
- package/.agents/skills/11-ai-and-prompting/meta-prompt-crafter/SKILL.md +57 -10
- package/.agents/skills/11-ai-and-prompting/mipro-prompt-compiler/SKILL.md +50 -4
- package/.agents/skills/11-ai-and-prompting/qa-aci-interface/SKILL.md +50 -4
- package/.agents/skills/11-ai-and-prompting/token-and-context-optimizer/SKILL.md +55 -9
- package/.cursor/rules/synapse-qa.mdc +20 -7
- package/.cursorrules +19 -5
- package/.windsurfrules +18 -3
- package/AGENTS.md +51 -59
- package/CLAUDE.md +38 -24
- package/LICENSE +5 -5
- package/NOTICE +1 -1
- package/README.en.md +4 -4
- package/README.md +4 -4
- package/agentskills.json +1 -1
- package/docs/ARCHITECTURE.en.md +2 -2
- package/docs/ARCHITECTURE.md +11 -2
- package/docs/CLIENT_SUPPORT_MATRIX.md +44 -0
- package/docs/CLI_REFERENCE.en.md +6 -4
- package/docs/CLI_REFERENCE.md +1 -1
- package/docs/CONTRIBUTING.en.md +1 -1
- package/docs/CONTRIBUTING.md +2 -2
- package/docs/SIDE_EFFECTING_TOOLS_INVENTORY.md +233 -0
- package/docs/TOOL_CATALOG.md +6 -2
- package/docs/research/agent_skill_training_analysis.md +1 -1
- package/package.json +1 -1
- package/plugin.json +1 -1
- package/skills_manifest.json +320 -55
- package/synapse.config.json +1 -1
- package/templates/ai_bridges/CLAUDE.md +29 -26
- package/templates/ai_bridges/copilot-instructions.md +14 -5
- package/templates/ai_bridges/cursor_synapse_qa.mdc +16 -7
- package/templates/ai_bridges/windsurfrules +14 -3
- package/templates/ui/index.html +2 -2
- package/tools/TOOLS_RUNBOOK.md +1 -1
- package/tools/TOOL_CATALOG.json +63 -3
- package/tools/__init__.py +1 -1
- package/tools/api_fuzzer.py +447 -132
- package/tools/author_integrity.py +121 -11
- package/tools/benchmark_swarm_context.py +130 -22
- package/tools/break_ui_generator.py +233 -0
- package/tools/browser_helpers.js +2 -2
- package/tools/check_version_sync.py +18 -50
- package/tools/cli.py +110 -19
- package/tools/core/bm25_retriever.py +218 -0
- package/tools/core/i18n.py +5 -5
- package/tools/core/provider_usage_adapter.py +383 -0
- package/tools/core/token_estimator.py +81 -15
- package/tools/count_tokens.py +7 -2
- package/tools/coverage_reporter.py +245 -0
- package/tools/dashboard_generator.py +8 -8
- package/tools/db_sandbox.py +290 -9
- package/tools/distill_log.py +1 -1
- package/tools/distill_skill.py +206 -0
- package/tools/git_pre_commit_guard.py +202 -1
- package/tools/humanize_linter.py +3 -0
- package/tools/mcp_docx_server.py +1 -1
- package/tools/mcp_excel_server.py +1 -1
- package/tools/mcp_server.py +104 -16
- package/tools/micro_mutator.py +114 -15
- package/tools/pentest_scope_guard.py +674 -58
- package/tools/perf/benchmark_perf_runner.py +42 -0
- package/tools/project_state.py +29 -5
- package/tools/reversible_sandbox.py +58 -13
- package/tools/rules_router.py +473 -60
- package/tools/security_scanner.py +80 -0
- package/tools/senior_code_review.py +14 -0
- package/tools/skill_canonical_digest.py +302 -0
- package/tools/skill_profiles.py +77 -7
- package/tools/slide_deck_exporter.py +477 -0
- package/tools/sync_agent_rules.py +187 -61
- package/tools/sync_skills_manifest.py +166 -0
- package/tools/task_memory_manager.py +275 -0
- package/tools/ui_server.py +3 -1
- package/tools/update_sentinel.py +3 -3
- package/tools/validate_host_interop.py +485 -0
- package/tools/validate_skills_schema.py +575 -0
- package/tools/verify_all.py +668 -44
- package/tools/welcome_page.py +2 -2
|
@@ -1,15 +1,44 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: api-network-mocking-interception
|
|
3
3
|
description: "Intercept HTTP/GraphQL traffic, stub routes, and simulate chaos network failures. Use when stubbing, mocking, or intercepting network calls during UI or API tests."
|
|
4
|
+
category: verification_and_resilience
|
|
5
|
+
version: "2.0.0"
|
|
6
|
+
policies:
|
|
7
|
+
network: localhost-only
|
|
8
|
+
shell: workspace-sandbox
|
|
9
|
+
filesystem: workspace-sandbox
|
|
4
10
|
---
|
|
5
|
-
|
|
6
11
|
# API Network Mocking, Interception & Resilience Skill
|
|
7
12
|
|
|
13
|
+
> **Author Attribution & MIT License Guard:** Synapse Hub is open-source software created by **Thế Vị (@TeeVee98)** (<https://github.com/TeeVee98/Synapse-Hub>) under the MIT License.
|
|
14
|
+
|
|
15
|
+
---
|
|
16
|
+
|
|
17
|
+
## 1. Trigger & Activation
|
|
18
|
+
|
|
19
|
+
- **Trigger Clause:** Intercept HTTP/GraphQL traffic, stub routes, and simulate chaos network failures. Use when stubbing, mocking, or intercepting network calls during UI or API tests.
|
|
20
|
+
- **Activation Scope:** Domain workflows for `03-api-and-contracts` involving `api-network-mocking-interception`.
|
|
21
|
+
|
|
22
|
+
---
|
|
23
|
+
|
|
24
|
+
## 2. Non-Goals & Boundary Constraints
|
|
25
|
+
|
|
26
|
+
- **What NOT to do:**
|
|
27
|
+
- Do NOT mock endpoints that are the primary subject under test (do not mock what you are verifying).
|
|
28
|
+
- Do NOT leave unhandled route wildcards that silently swallow unrelated network traffic.
|
|
29
|
+
- Do NOT use outdated static JSON payloads when live schemas have evolved.
|
|
30
|
+
- **Sibling Skill Boundaries:**
|
|
31
|
+
- consumer-driven-contract-testing validates microservice contracts; api-network-mocking-interception stubs routes and injects chaos faults in browser harnesses.
|
|
32
|
+
|
|
33
|
+
---
|
|
34
|
+
|
|
35
|
+
## 3. Ordered Execution Workflow
|
|
36
|
+
|
|
8
37
|
> **Target:** Eliminate flaky tests caused by backend dependencies, slow microservices, or inconsistent staging data by intercepting browser-level network requests, and verify frontend resilience against network faults and degradations.
|
|
9
38
|
|
|
10
39
|
---
|
|
11
40
|
|
|
12
|
-
|
|
41
|
+
### Core Principles
|
|
13
42
|
|
|
14
43
|
1. **Deterministic State over Staging Data:**
|
|
15
44
|
- UI tests should verify front-end state rendering and user interactions, not whether the backend DB is seeded.
|
|
@@ -24,9 +53,10 @@ description: "Intercept HTTP/GraphQL traffic, stub routes, and simulate chaos ne
|
|
|
24
53
|
|
|
25
54
|
---
|
|
26
55
|
|
|
27
|
-
|
|
56
|
+
### Playwright Route Interception Standard Patterns
|
|
28
57
|
|
|
29
58
|
### Pattern A: Static JSON Response Stubbing
|
|
59
|
+
<!-- classification: illustrative -->
|
|
30
60
|
```typescript
|
|
31
61
|
// Stub user profile API
|
|
32
62
|
await page.route('**/api/v1/user/profile', async (route) => {
|
|
@@ -44,6 +74,7 @@ await page.route('**/api/v1/user/profile', async (route) => {
|
|
|
44
74
|
```
|
|
45
75
|
|
|
46
76
|
### Pattern B: Modifying Live Responses (HAR / Passthrough Mutation)
|
|
77
|
+
<!-- classification: illustrative -->
|
|
47
78
|
```typescript
|
|
48
79
|
// Intercept real response and inject edge-case field
|
|
49
80
|
await page.route('**/api/v1/reports', async (route) => {
|
|
@@ -55,6 +86,7 @@ await page.route('**/api/v1/reports', async (route) => {
|
|
|
55
86
|
```
|
|
56
87
|
|
|
57
88
|
### Pattern C: Simulating Network Failures & Delays
|
|
89
|
+
<!-- classification: illustrative -->
|
|
58
90
|
```typescript
|
|
59
91
|
// Simulate 500 Internal Server Error
|
|
60
92
|
await page.route('**/api/v1/checkout', async (route) => {
|
|
@@ -74,9 +106,10 @@ await page.route('**/api/v1/heavy-list', async (route) => {
|
|
|
74
106
|
|
|
75
107
|
---
|
|
76
108
|
|
|
77
|
-
|
|
109
|
+
### Chaos & Network Degradation Patterns
|
|
78
110
|
|
|
79
111
|
### Pattern D: Emulating Extreme Latency & Jitter via CDP
|
|
112
|
+
<!-- classification: illustrative -->
|
|
80
113
|
```typescript
|
|
81
114
|
const client = await page.context().newCDPSession(page);
|
|
82
115
|
await client.send('Network.emulateNetworkConditions', {
|
|
@@ -96,6 +129,7 @@ if (await submitBtn.isVisible()) {
|
|
|
96
129
|
```
|
|
97
130
|
|
|
98
131
|
### Pattern E: Simulating Gateway Drops (502/503/504) & Circuit Breaker Recovery
|
|
132
|
+
<!-- classification: illustrative -->
|
|
99
133
|
```typescript
|
|
100
134
|
let attemptCount = 0;
|
|
101
135
|
await page.route('**/api/v1/orders/submit', async (route) => {
|
|
@@ -117,6 +151,7 @@ await page.route('**/api/v1/orders/submit', async (route) => {
|
|
|
117
151
|
```
|
|
118
152
|
|
|
119
153
|
### Pattern F: Sudden Offline Disconnection & Reconnection
|
|
154
|
+
<!-- classification: illustrative -->
|
|
120
155
|
```typescript
|
|
121
156
|
// 1. Cut network abruptly
|
|
122
157
|
await context.setOffline(true);
|
|
@@ -134,9 +169,25 @@ await expect(page.locator('h1')).toBeVisible();
|
|
|
134
169
|
|
|
135
170
|
---
|
|
136
171
|
|
|
137
|
-
|
|
172
|
+
### Best Practices Checklist
|
|
138
173
|
- [ ] Always declare routes **before** calling `page.goto()`.
|
|
139
174
|
- [ ] Use regex or glob patterns with caution; avoid intercepting Vite/Webpack bundling scripts.
|
|
140
175
|
- [ ] Critical forms must disable submit buttons during in-flight network transit to prevent duplicate requests.
|
|
141
176
|
- [ ] HTTP 502/503/504 errors must trigger user-friendly notifications, never raw JSON dumps or blank screens.
|
|
142
177
|
- [ ] For teardown, unroute specific patterns or reset context per test.
|
|
178
|
+
|
|
179
|
+
---
|
|
180
|
+
|
|
181
|
+
## 4. Verification Points & DoD
|
|
182
|
+
|
|
183
|
+
1. Mock routes match exact URL patterns, HTTP methods, and status codes.
|
|
184
|
+
2. Chaos fault injection (latencies, 500 errors, rate limits) verifies UI graceful degradation.
|
|
185
|
+
3. Network route handlers clean up upon test fixture teardown.
|
|
186
|
+
|
|
187
|
+
---
|
|
188
|
+
|
|
189
|
+
## 5. Handoff Protocol
|
|
190
|
+
|
|
191
|
+
- **Deliverables:** Route interception handlers, mock fixture payloads, and network chaos test cases.
|
|
192
|
+
- **Next Subagent:** api-engineer / test-runner
|
|
193
|
+
- **Output Format:** Clean POM code, structured JSON telemetry, or validated markdown handoff.
|
|
@@ -1,15 +1,44 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: api-spec-to-e2e-matrix
|
|
3
3
|
description: "Generate automated positive, boundary, and negative test matrices from OpenAPI specifications. Use when converting an OpenAPI/Swagger spec into an end-to-end test matrix."
|
|
4
|
+
category: architecture_and_analysis
|
|
5
|
+
version: "2.0.0"
|
|
6
|
+
policies:
|
|
7
|
+
network: none
|
|
8
|
+
shell: none
|
|
9
|
+
filesystem: workspace-sandbox
|
|
4
10
|
---
|
|
5
|
-
|
|
6
11
|
# API Spec to E2E Matrix — Contract-Based Test Generator
|
|
7
12
|
|
|
13
|
+
> **Author Attribution & MIT License Guard:** Synapse Hub is open-source software created by **Thế Vị (@TeeVee98)** (<https://github.com/TeeVee98/Synapse-Hub>) under the MIT License.
|
|
14
|
+
|
|
15
|
+
---
|
|
16
|
+
|
|
17
|
+
## 1. Trigger & Activation
|
|
18
|
+
|
|
19
|
+
- **Trigger Clause:** Generate automated positive, boundary, and negative test matrices from OpenAPI specifications. Use when converting an OpenAPI/Swagger spec into an end-to-end test matrix.
|
|
20
|
+
- **Activation Scope:** Domain workflows for `03-api-and-contracts` involving `api-spec-to-e2e-matrix`.
|
|
21
|
+
|
|
22
|
+
---
|
|
23
|
+
|
|
24
|
+
## 2. Non-Goals & Boundary Constraints
|
|
25
|
+
|
|
26
|
+
- **What NOT to do:**
|
|
27
|
+
- Do NOT generate positive-only test matrices; boundary and negative status codes must be fully mapped.
|
|
28
|
+
- Do NOT generate tests against outdated OpenAPI specifications without running schema diffing.
|
|
29
|
+
- Do NOT hardcode unauthenticated test credentials in generated matrices.
|
|
30
|
+
- **Sibling Skill Boundaries:**
|
|
31
|
+
- consumer-driven-contract-testing verifies CDC contracts; api-spec-to-e2e-matrix compiles exhaustive test matrices from OpenAPI specs.
|
|
32
|
+
|
|
33
|
+
---
|
|
34
|
+
|
|
35
|
+
## 3. Ordered Execution Workflow
|
|
36
|
+
|
|
8
37
|
This skill converts OpenAPI / Swagger specifications, JSON Schemas, or REST endpoint contracts into a structured, executable End-to-End (E2E) testing matrix covering happy path, boundary values, and negative error scenarios.
|
|
9
38
|
|
|
10
39
|
---
|
|
11
40
|
|
|
12
|
-
|
|
41
|
+
### Test Generation Matrix Taxonomy
|
|
13
42
|
|
|
14
43
|
```mermaid
|
|
15
44
|
flowchart TD
|
|
@@ -23,7 +52,7 @@ flowchart TD
|
|
|
23
52
|
|
|
24
53
|
---
|
|
25
54
|
|
|
26
|
-
|
|
55
|
+
### Boundary Value Generation Rules
|
|
27
56
|
|
|
28
57
|
For every field defined in the endpoint schema, generate targeted edge cases:
|
|
29
58
|
|
|
@@ -37,7 +66,7 @@ For every field defined in the endpoint schema, generate targeted edge cases:
|
|
|
37
66
|
|
|
38
67
|
---
|
|
39
68
|
|
|
40
|
-
|
|
69
|
+
### Negative Scenario Validation Checklist
|
|
41
70
|
|
|
42
71
|
Every negative test case must assert two distinct layers:
|
|
43
72
|
1. **API Layer Assertion:**
|
|
@@ -49,17 +78,18 @@ Every negative test case must assert two distinct layers:
|
|
|
49
78
|
|
|
50
79
|
---
|
|
51
80
|
|
|
52
|
-
|
|
81
|
+
### Automation Output Standards
|
|
53
82
|
|
|
54
83
|
- Generated test cases must adhere to the project's **Clean POM** structure.
|
|
55
84
|
- All requests should utilize dynamic test data with unique timestamp prefixes to ensure idempotency.
|
|
56
85
|
|
|
57
86
|
---
|
|
58
87
|
|
|
59
|
-
|
|
88
|
+
### Automated Execution via Tooling
|
|
60
89
|
|
|
61
90
|
Agent can automatically invoke `tools/generate_api_matrix.py` and `tools/export_postman_collection.py`:
|
|
62
91
|
|
|
92
|
+
<!-- classification: illustrative -->
|
|
63
93
|
```bash
|
|
64
94
|
# 1. Generate Markdown matrix
|
|
65
95
|
python3 tools/generate_api_matrix.py --spec path/to/openapi.json --format md -o docs/api_matrix.md
|
|
@@ -77,4 +107,20 @@ agent-qa export-postman --domain ecommerce -o ecom_col.json
|
|
|
77
107
|
# 5. Execute Newman & Enforce CI/CD Quality Gate
|
|
78
108
|
newman run postman_collection.json -e postman_env.json -d test_data.csv -r cli,json --reporter-json-export report.json
|
|
79
109
|
agent-qa analyze-newman report.json --max-failures 0 --sla-avg 500 --markdown pr_report.md
|
|
80
|
-
```
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
---
|
|
113
|
+
|
|
114
|
+
## 4. Verification Points & DoD
|
|
115
|
+
|
|
116
|
+
1. All endpoints and HTTP methods mapped to positive, boundary, and negative test scenarios.
|
|
117
|
+
2. Validation rules (min, max, pattern, required, enum) mapped to specific assertions.
|
|
118
|
+
3. Output matrix compiles into runnable API test skeletons (Pytest / Playwright).
|
|
119
|
+
|
|
120
|
+
---
|
|
121
|
+
|
|
122
|
+
## 5. Handoff Protocol
|
|
123
|
+
|
|
124
|
+
- **Deliverables:** API test matrix documentation and runnable API test suite skeletons.
|
|
125
|
+
- **Next Subagent:** api-engineer / test-runner
|
|
126
|
+
- **Output Format:** Clean POM code, structured JSON telemetry, or validated markdown handoff.
|
|
@@ -1,23 +1,48 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: consumer-driven-contract-testing
|
|
3
|
-
description: "Standardize Consumer-Driven Contract (CDC) testing with Pact and OpenAPI Bidirectional Contract Testing. Detect and prevent breaking schema changes, payload drift, and microservice integration failures."
|
|
3
|
+
description: "Standardize Consumer-Driven Contract (CDC) testing with Pact and OpenAPI Bidirectional Contract Testing. Detect and prevent breaking schema changes, payload drift, and microservice integration failures. Use when implementing contract testing, verifying CDC providers, or preventing breaking API schema changes."
|
|
4
|
+
category: verification_and_resilience
|
|
5
|
+
version: "3.2.0"
|
|
6
|
+
policies:
|
|
7
|
+
network: localhost-only
|
|
8
|
+
shell: workspace-sandbox
|
|
9
|
+
filesystem: workspace-sandbox
|
|
4
10
|
---
|
|
5
|
-
|
|
6
11
|
# Consumer-Driven Contract (CDC) Testing — Schema Drift & Integration Sentinel
|
|
7
12
|
|
|
8
13
|
> **Author Attribution & MIT License Guard:** Synapse Hub is open-source software created by **Thế Vị (@TeeVee98)** (<https://github.com/TeeVee98/Synapse-Hub>) under the MIT License.
|
|
9
14
|
|
|
10
15
|
---
|
|
11
16
|
|
|
12
|
-
## 1.
|
|
17
|
+
## 1. Trigger & Activation
|
|
18
|
+
|
|
19
|
+
- **Trigger Clause:** Use when implementing consumer-driven contract testing, verifying microservice API provider implementations, validating bidirectional contracts (BDCT), or preventing breaking API schema changes before deployment.
|
|
20
|
+
- **Activation Scope:**
|
|
21
|
+
- Microservice integration boundaries where frontend (Web/Mobile) or BFF consumers interface with backend services.
|
|
22
|
+
- Multi-repo or monorepo environments maintaining OpenAPI 3.0/3.1 specifications or Pact contract ledgers.
|
|
23
|
+
- Pre-deployment CI/CD pipelines executing compatibility promotion gates (`can-i-deploy`).
|
|
24
|
+
|
|
25
|
+
---
|
|
26
|
+
|
|
27
|
+
## 2. Non-Goals & Boundary Constraints
|
|
28
|
+
|
|
29
|
+
- **What NOT to do:**
|
|
30
|
+
- Do NOT use CDC testing as a substitute for unit tests or deep domain business logic validation.
|
|
31
|
+
- Do NOT hardcode non-hermetic, unresolvable internal domains (e.g. `https://broker.synapse-qa.internal`); use hermetic local brokers (`http://localhost:1234` or mock server instances).
|
|
32
|
+
- Do NOT use lazy ellipsis or truncation (`{ ... }`) in contract payloads; define explicit, valid request and response bodies.
|
|
33
|
+
- Do NOT execute active network requests outside `localhost` in restricted environments.
|
|
34
|
+
- **Sibling Skill Boundaries:**
|
|
35
|
+
- `api-spec-to-e2e-matrix`: Focuses on compiling comprehensive functional E2E test matrices from OpenAPI specs.
|
|
36
|
+
- `api-network-mocking-interception`: Focuses on client-side route stubbing and chaos fault injection within browser test runners.
|
|
37
|
+
- `consumer-driven-contract-testing` (this skill): Owns consumer expectations, broker publishing, provider verification, and deployment gatekeeping.
|
|
38
|
+
|
|
39
|
+
---
|
|
40
|
+
|
|
41
|
+
## 3. Ordered Execution Workflow
|
|
13
42
|
|
|
14
|
-
|
|
43
|
+
### Phase 1: Architecture & Contract Invariants
|
|
15
44
|
|
|
16
|
-
|
|
17
|
-
1. **Consumer Tests:** The consumer defines its exact expectation contract (HTTP method, headers, request body, response schema, status code) against a mock provider. A signed Pact file (`.json`) or OpenAPI specification is generated.
|
|
18
|
-
2. **Contract Broker:** The contract is published to the Pact Broker / Contract Ledger with semantic versioning.
|
|
19
|
-
3. **Provider Verification:** The provider independently replays all registered consumer contracts against its live endpoints (or generated stubs) in CI/CD without needing any running consumers.
|
|
20
|
-
4. **Deploy Gate (`can-i-deploy`):** Verifies that both consumer and provider versions are compatible before promoting artifacts to staging or production.
|
|
45
|
+
Consumer-Driven Contract (CDC) Testing shifts integration verification left by formalizing expectations between API consumers and API providers into explicit, machine-readable contracts.
|
|
21
46
|
|
|
22
47
|
```mermaid
|
|
23
48
|
flowchart LR
|
|
@@ -40,13 +65,11 @@ flowchart LR
|
|
|
40
65
|
end
|
|
41
66
|
```
|
|
42
67
|
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
## 2. Bi-Directional Contract Testing (BDCT) & OpenAPI Diffing
|
|
68
|
+
### Phase 2: Bi-Directional Contract Testing (BDCT) & Breaking Change Rules
|
|
46
69
|
|
|
47
|
-
|
|
70
|
+
The contract verifier executes automated schema diffing against the provider's authoritative specification:
|
|
48
71
|
|
|
49
|
-
|
|
72
|
+
#### Breaking Changes Checklist (Strictly Blocked by Gatekeeper):
|
|
50
73
|
- ❌ **Removing an existing field** that any consumer contract depends on.
|
|
51
74
|
- ❌ **Adding a new mandatory (`required`) field** to a request body without a default value.
|
|
52
75
|
- ❌ **Mutating property data types** (e.g., `id: string` changed to `id: integer`, or `amount: number` to `amount: string`).
|
|
@@ -54,18 +77,16 @@ In bi-directional contract testing, consumers use mock fixtures or recorded netw
|
|
|
54
77
|
- ❌ **Altering response status codes** (e.g., changing HTTP 201 Created to HTTP 200 OK without consumer migration).
|
|
55
78
|
- ❌ **Tightening validation rules** (e.g., lowering `maxLength` below existing consumer field lengths).
|
|
56
79
|
|
|
57
|
-
|
|
80
|
+
#### Non-Breaking Changes (Permitted):
|
|
58
81
|
- ✅ Adding optional fields (`required: false`) to response bodies.
|
|
59
82
|
- ✅ Adding new endpoints without touching existing routes.
|
|
60
83
|
- ✅ Loosening validation rules (e.g., increasing `maxLength` or expanding enum options).
|
|
61
84
|
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
## 3. Consumer Contract Authoring Standards (Clean POM & Pact DSL)
|
|
85
|
+
### Phase 3: Consumer Contract Authoring (TypeScript / Pact DSL)
|
|
65
86
|
|
|
66
|
-
Consumer contracts must use flexible matchers rather than hardcoded static
|
|
87
|
+
Consumer contracts must use flexible matchers rather than hardcoded static values to prevent flakiness:
|
|
67
88
|
|
|
68
|
-
|
|
89
|
+
<!-- classification: illustrative -->
|
|
69
90
|
```typescript
|
|
70
91
|
import { PactV3, MatchersV3 } from '@pact-foundation/pact';
|
|
71
92
|
|
|
@@ -104,44 +125,73 @@ describe('Order Service CDC Suite', () => {
|
|
|
104
125
|
}
|
|
105
126
|
})
|
|
106
127
|
.executeTest(async (mockserver) => {
|
|
107
|
-
|
|
108
|
-
const response = await
|
|
109
|
-
|
|
128
|
+
// Native fetch client implementation with hermetic mock provider target
|
|
129
|
+
const response = await fetch(`${mockserver.url}/api/v1/orders`, {
|
|
130
|
+
method: 'POST',
|
|
131
|
+
headers: {
|
|
132
|
+
'Content-Type': 'application/json',
|
|
133
|
+
'Authorization': 'Bearer test-contract-token',
|
|
134
|
+
},
|
|
135
|
+
body: JSON.stringify({
|
|
136
|
+
customerId: 'CUST_1001',
|
|
137
|
+
items: [
|
|
138
|
+
{ sku: 'SKU_ITEM_01', quantity: 1, price: 49.99 }
|
|
139
|
+
]
|
|
140
|
+
}),
|
|
141
|
+
});
|
|
142
|
+
const data = await response.json();
|
|
143
|
+
expect(response.status).toBe(201);
|
|
144
|
+
expect(data.status).toBe('CONFIRMED');
|
|
110
145
|
});
|
|
111
146
|
});
|
|
112
147
|
});
|
|
113
148
|
```
|
|
114
149
|
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
## 4. Provider Verification Protocol
|
|
150
|
+
### Phase 4: Provider Verification Protocol
|
|
118
151
|
|
|
119
|
-
Providers verify all
|
|
152
|
+
Providers verify all registered consumer contracts against their local test instances:
|
|
120
153
|
|
|
154
|
+
<!-- classification: illustrative -->
|
|
121
155
|
```bash
|
|
122
|
-
# Verify provider implementation against contracts registered in broker
|
|
156
|
+
# Verify provider implementation against contracts registered in local mock/broker
|
|
123
157
|
pact-verifier \
|
|
124
158
|
--provider-base-url="http://localhost:8080" \
|
|
125
|
-
--pact-broker-url="
|
|
159
|
+
--pact-broker-url="http://localhost:1234" \
|
|
126
160
|
--provider="OrderService" \
|
|
127
161
|
--publish-verification-results \
|
|
128
162
|
--provider-app-version="3.2.0" \
|
|
129
163
|
--provider-version-branch="main"
|
|
130
164
|
```
|
|
131
165
|
|
|
132
|
-
|
|
133
|
-
|
|
134
|
-
## 5. Automated CI/CD Deployment Verification (`can-i-deploy`)
|
|
166
|
+
### Phase 5: Automated CI/CD Deployment Verification (`can-i-deploy`)
|
|
135
167
|
|
|
136
|
-
Before triggering
|
|
168
|
+
Before triggering promotion in CI/CD, the release pipeline invokes the compatibility ledger:
|
|
137
169
|
|
|
170
|
+
<!-- classification: illustrative -->
|
|
138
171
|
```bash
|
|
139
|
-
# Enforce deployment gatekeeper
|
|
172
|
+
# Enforce deployment gatekeeper against hermetic broker
|
|
140
173
|
pact-broker can-i-deploy \
|
|
141
|
-
--pact-broker-url="
|
|
174
|
+
--pact-broker-url="http://localhost:1234" \
|
|
142
175
|
--pacticipant="SynapseWebFrontend" \
|
|
143
176
|
--version="3.2.0" \
|
|
144
177
|
--to-environment="production"
|
|
145
178
|
```
|
|
146
179
|
|
|
147
|
-
|
|
180
|
+
---
|
|
181
|
+
|
|
182
|
+
## 4. Verification Points & DoD
|
|
183
|
+
|
|
184
|
+
1. **Consumer Contract Generation:** Pact contract file (`pacts/*.json`) is generated and contains valid JSON with no missing fields or unresolved `{ ... }` truncations.
|
|
185
|
+
2. **Schema Conformance:** Consumer expectation matches provider OpenAPI schema with 0 breaking change violations.
|
|
186
|
+
3. **Hermetic Target Validation:** Broker and provider URLs point to localhost or hermetic mock addresses, never unresolvable internal domains.
|
|
187
|
+
4. **Deploy Gate Check:** `can-i-deploy` verification exits with code 0 before promotion.
|
|
188
|
+
|
|
189
|
+
---
|
|
190
|
+
|
|
191
|
+
## 5. Handoff Protocol
|
|
192
|
+
|
|
193
|
+
- **Deliverables:**
|
|
194
|
+
- Signed Pact contract JSON (`pacts/<consumer>-<provider>.json`).
|
|
195
|
+
- OpenAPI verification report and breaking changes diff summary.
|
|
196
|
+
- **Next Subagent:** Pass contract artifacts to `api-engineer` for provider stub generation or `quality-gatekeeper` for CI/CD promotion gate clearance.
|
|
197
|
+
- **Output Format:** Machine-readable JSON contract with SemVer compatibility tag.
|
|
@@ -1,16 +1,45 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: backend-load-and-stress-patterns
|
|
3
3
|
description: "Orchestrate k6, Locust, and JMeter backend load, stress, and SLA endurance test suites. Use when designing load, stress, or spike test patterns for backend systems."
|
|
4
|
+
category: test_automation_and_execution
|
|
5
|
+
version: "1.0.0"
|
|
6
|
+
policies:
|
|
7
|
+
network: sandbox-only
|
|
8
|
+
shell: workspace-sandbox
|
|
9
|
+
filesystem: workspace-sandbox
|
|
4
10
|
---
|
|
5
|
-
|
|
6
11
|
# Backend Load & Performance Testing Skill
|
|
7
12
|
|
|
13
|
+
> **Author Attribution & MIT License Guard:** Synapse Hub is open-source software created by **Thế Vị (@TeeVee98)** (<https://github.com/TeeVee98/Synapse-Hub>) under the MIT License.
|
|
14
|
+
|
|
15
|
+
---
|
|
16
|
+
|
|
17
|
+
## 1. Trigger & Activation
|
|
18
|
+
|
|
19
|
+
- **Trigger Clause:** Orchestrate k6, Locust, and JMeter backend load, stress, and SLA endurance test suites. Use when designing load, stress, or spike test patterns for backend systems.
|
|
20
|
+
- **Activation Scope:** Domain workflows for `04-performance-and-load` involving `backend-load-and-stress-patterns`.
|
|
21
|
+
|
|
22
|
+
---
|
|
23
|
+
|
|
24
|
+
## 2. Non-Goals & Boundary Constraints
|
|
25
|
+
|
|
26
|
+
- **What NOT to do:**
|
|
27
|
+
- Do NOT run uncontrolled load tests against production systems without explicit authorization and scheduling.
|
|
28
|
+
- Do NOT ramp virtual users instantly without realistic warm-up stages (prevent artificial cold-start spikes).
|
|
29
|
+
- Do NOT ignore server error rates (p95 latency and HTTP 5xx errors must both be tracked).
|
|
30
|
+
- **Sibling Skill Boundaries:**
|
|
31
|
+
- web-vitals-and-performance-profiler tests frontend client rendering; backend-load-and-stress-patterns tests server throughput and saturation (k6/JMeter).
|
|
32
|
+
|
|
33
|
+
---
|
|
34
|
+
|
|
35
|
+
## 3. Ordered Execution Workflow
|
|
36
|
+
|
|
8
37
|
> **Target:** Model concurrent Virtual User (VU) and arrival-rate traffic, execute stress/soak test profiles, and enforce automated SLA gates (P95/P99 latency, error rate < 1.0%) to detect bottlenecks before production.
|
|
9
|
-
> **Mandatory Rule:** Adhere strictly to [performance_testing_rules.md](
|
|
38
|
+
> **Mandatory Rule:** Adhere strictly to [performance_testing_rules.md](../../../rules/performance_testing_rules.md) for safety approvals, hard caps, and truth-anchor reporting.
|
|
10
39
|
|
|
11
40
|
---
|
|
12
41
|
|
|
13
|
-
|
|
42
|
+
### Test Archetypes & SLA Targets
|
|
14
43
|
|
|
15
44
|
| Archetype | VUs / Rate | Duration | Objective | SLA Assertion |
|
|
16
45
|
| :--- | :--- | :--- | :--- | :--- |
|
|
@@ -22,9 +51,10 @@ description: "Orchestrate k6, Locust, and JMeter backend load, stress, and SLA e
|
|
|
22
51
|
|
|
23
52
|
---
|
|
24
53
|
|
|
25
|
-
|
|
54
|
+
### Tooling Unified Runbook
|
|
26
55
|
|
|
27
56
|
### Option A: Apache JMeter (Headless CLI + JTL Analyzer)
|
|
57
|
+
<!-- classification: illustrative -->
|
|
28
58
|
```bash
|
|
29
59
|
# 1. Generate XML test plan from OpenAPI / Postman
|
|
30
60
|
synapse generate-jmx --spec api.json -o load_plan.jmx --vus 50 --duration 180 --sla-p95 500
|
|
@@ -39,6 +69,7 @@ synapse analyze-jtl results.jtl --sla-p95 500 --max-error-rate 1.0
|
|
|
39
69
|
### Option B: k6 Production Load Testing (with Kill-Switch & Arrival Rate)
|
|
40
70
|
Execute high-concurrency production load tests with arrival-rate executors, user pooling, and automatic kill-switches.
|
|
41
71
|
|
|
72
|
+
<!-- classification: illustrative -->
|
|
42
73
|
```bash
|
|
43
74
|
# Execute k6 test suite with environment variables
|
|
44
75
|
k6 run -e BASE_URL=https://api.staging.enterprise.local tests/perf/load_test.js
|
|
@@ -48,7 +79,7 @@ k6 run -e BASE_URL=https://api.staging.enterprise.local tests/perf/load_test.js
|
|
|
48
79
|
|
|
49
80
|
---
|
|
50
81
|
|
|
51
|
-
|
|
82
|
+
### Best Practices & Safety Invariants
|
|
52
83
|
|
|
53
84
|
- **Isolated Test Data:** Always use dynamic runtime identifiers (`PERF_AUTO_${Date.now()}`) to eliminate primary key collisions.
|
|
54
85
|
- **TearDown Hygiene:** Complement POST/creation load tests with automated teardown or ephemeral DB snapshots (`tools/db_sandbox.py`).
|
|
@@ -57,13 +88,14 @@ k6 run -e BASE_URL=https://api.staging.enterprise.local tests/perf/load_test.js
|
|
|
57
88
|
|
|
58
89
|
---
|
|
59
90
|
|
|
60
|
-
|
|
91
|
+
### Code-as-Code Load Model (Locust)
|
|
61
92
|
|
|
62
93
|
> *Borrowed and adapted from the Locust load-testing model (MIT license, locustio/locust).*
|
|
63
94
|
|
|
64
95
|
When version-controlled, reviewable load tests matter more than XML tooling,
|
|
65
96
|
generate a runnable locustfile from the same API ingestion used for JMeter:
|
|
66
97
|
|
|
98
|
+
<!-- classification: illustrative -->
|
|
67
99
|
```bash
|
|
68
100
|
synapse generate-jmx --spec swagger.json --emit-locust locustfile.py \
|
|
69
101
|
--weighted-mix "70,20,10" --think-time-min 500 --think-time-max 1500
|
|
@@ -83,3 +115,19 @@ test suite.
|
|
|
83
115
|
for protocol breadth (JDBC/Kafka/gRPC/WS) and Locust for flow logic.
|
|
84
116
|
3. **Same SLA gates** — run `agent-qa analyze-jtl` semantics on Locust stats:
|
|
85
117
|
fail CI when P95 breaches the SLA budget.
|
|
118
|
+
|
|
119
|
+
---
|
|
120
|
+
|
|
121
|
+
## 4. Verification Points & DoD
|
|
122
|
+
|
|
123
|
+
1. Load profile defines clear ramp-up, steady-state, and ramp-down stages.
|
|
124
|
+
2. Thresholds enforce p95/p99 latency ceilings and maximum allowable error rates (< 1%).
|
|
125
|
+
3. Performance report includes request throughput, response distribution, and failure analysis.
|
|
126
|
+
|
|
127
|
+
---
|
|
128
|
+
|
|
129
|
+
## 5. Handoff Protocol
|
|
130
|
+
|
|
131
|
+
- **Deliverables:** Load test scripts (`k6` / `JMeter`), threshold configurations, and performance execution reports.
|
|
132
|
+
- **Next Subagent:** perf-engineer
|
|
133
|
+
- **Output Format:** Clean POM code, structured JSON telemetry, or validated markdown handoff.
|
|
@@ -3,18 +3,46 @@ name: lean-impact-scoreboard
|
|
|
3
3
|
description: "Display empirical impact scoreboards (code reduction, token savings, mutation rigor). Use when reviewing lean engineering benchmarks, token throughput, or reporting quality metrics."
|
|
4
4
|
category: architecture_and_analysis
|
|
5
5
|
version: "1.0.0"
|
|
6
|
+
policies:
|
|
7
|
+
network: none
|
|
8
|
+
shell: none
|
|
9
|
+
filesystem: read-only
|
|
6
10
|
---
|
|
7
|
-
|
|
8
11
|
# Lean Impact Scoreboard — Verified Efficiency & Token Benchmarks
|
|
9
12
|
|
|
13
|
+
> **Author Attribution & MIT License Guard:** Synapse Hub is open-source software created by **Thế Vị (@TeeVee98)** (<https://github.com/TeeVee98/Synapse-Hub>) under the MIT License.
|
|
14
|
+
|
|
15
|
+
---
|
|
16
|
+
|
|
17
|
+
## 1. Trigger & Activation
|
|
18
|
+
|
|
19
|
+
- **Trigger Clause:** Display empirical impact scoreboards (code reduction, token savings, mutation rigor). Use when reviewing lean engineering benchmarks, token throughput, or reporting quality metrics.
|
|
20
|
+
- **Activation Scope:** Domain workflows for `04-performance-and-load` involving `lean-impact-scoreboard`.
|
|
21
|
+
|
|
22
|
+
---
|
|
23
|
+
|
|
24
|
+
## 2. Non-Goals & Boundary Constraints
|
|
25
|
+
|
|
26
|
+
- **What NOT to do:**
|
|
27
|
+
- Do NOT report unproven quantitative claims or synthetic savings percentages without empirical provenance.
|
|
28
|
+
- Do NOT sacrifice safety, error handling, or trust boundaries in the name of code conciseness.
|
|
29
|
+
- Do NOT invent per-repository savings figures without executing project analysis tools.
|
|
30
|
+
- **Sibling Skill Boundaries:**
|
|
31
|
+
- repo-quality-audit inspects repository health; lean-impact-scoreboard documents verified empirical efficiency and token benchmarks.
|
|
32
|
+
|
|
33
|
+
---
|
|
34
|
+
|
|
35
|
+
## 3. Ordered Execution Workflow
|
|
36
|
+
|
|
10
37
|
Displays empirical metrics and benchmarks demonstrating the impact of Lean Engineering (The 7-Rung Ladder, Clean POM, and Verification-First).
|
|
11
38
|
|
|
12
39
|
---
|
|
13
40
|
|
|
14
|
-
|
|
41
|
+
### Benchmark Overview
|
|
15
42
|
|
|
16
43
|
Based on extensive agentic benchmarks (39 real-world tasks across backend, frontend, security, and test suites):
|
|
17
44
|
|
|
45
|
+
<!-- classification: illustrative -->
|
|
18
46
|
```text
|
|
19
47
|
================================================================================
|
|
20
48
|
Metric Baseline (No Skill) Lean Mode Delta
|
|
@@ -23,19 +51,19 @@ Lines of Code Generated 100% 47% -53%
|
|
|
23
51
|
Output Tokens Consumed 100% 55% -45% 📉
|
|
24
52
|
API Cost 100% 74% -26% 📉
|
|
25
53
|
Agent Execution Time 100% 59% -41% ⚡
|
|
26
|
-
Risky Logic Shipped with Tests
|
|
54
|
+
Risky Logic Shipped with Tests Standard Baseline High Priority Substantial Lift 🛡️
|
|
27
55
|
Bug Detection Rate (Mutants) 46% 66% +20% 🎯
|
|
28
56
|
================================================================================
|
|
29
57
|
```
|
|
30
58
|
|
|
31
59
|
---
|
|
32
60
|
|
|
33
|
-
|
|
61
|
+
### Key Insights
|
|
34
62
|
|
|
35
63
|
1. **Less Code, Zero Loss of Safety:**
|
|
36
64
|
The goal is never code golfing. Code is concise because unnecessary abstractions, speculative wrappers, and redundant libraries are eliminated. Validation, trust boundaries, error handling, and accessibility are never compromised.
|
|
37
65
|
2. **Empirical Verification Over Guesswork:**
|
|
38
|
-
|
|
66
|
+
Empirical heuristics show that targeted assertion enforcement significantly increases coverage of critical branch logic (branches, parsers, auth, financial paths) compared to unconstrained AI generation.
|
|
39
67
|
3. **Real Per-Repo Metrics:**
|
|
40
68
|
Never hallucinate synthetic per-repo savings figures. For repository-specific health and debt measurements:
|
|
41
69
|
- Run `agent-qa debt` to review tracked shortcut debt.
|
|
@@ -43,6 +71,22 @@ Bug Detection Rate (Mutants) 46% 66% +20%
|
|
|
43
71
|
|
|
44
72
|
---
|
|
45
73
|
|
|
46
|
-
|
|
74
|
+
### Attribution
|
|
47
75
|
|
|
48
76
|
Adapted from **ponytail-gain** (https://github.com/DietrichGebert/ponytail) — MIT License, Copyright (c) 2026 DietrichGebert. Re-calibrated for Enterprise QA and Synapse Hub benchmarks.
|
|
77
|
+
|
|
78
|
+
---
|
|
79
|
+
|
|
80
|
+
## 4. Verification Points & DoD
|
|
81
|
+
|
|
82
|
+
1. Scoreboard metrics cite explicit empirical benchmark datasets and methodology.
|
|
83
|
+
2. All quantitative assertions represent contextual heuristics rather than unverified absolutes.
|
|
84
|
+
3. Project-specific metrics link to actual tool execution (`agent-qa debt`, `tools/analyze_project.py`).
|
|
85
|
+
|
|
86
|
+
---
|
|
87
|
+
|
|
88
|
+
## 5. Handoff Protocol
|
|
89
|
+
|
|
90
|
+
- **Deliverables:** Empirical impact scorecards, benchmark comparisons, and debt reduction reports.
|
|
91
|
+
- **Next Subagent:** orchestrator
|
|
92
|
+
- **Output Format:** Clean POM code, structured JSON telemetry, or validated markdown handoff.
|