@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.
Files changed (133) hide show
  1. package/.agents/rules/git-push-protocol.md +2 -2
  2. package/.agents/skills/01-web-automation/auth-session-and-cookie-manager/SKILL.md +52 -3
  3. package/.agents/skills/01-web-automation/bats-testing-patterns/SKILL.md +55 -5
  4. package/.agents/skills/01-web-automation/clean-pom-crafter/SKILL.md +62 -67
  5. package/.agents/skills/01-web-automation/e2e-testing-patterns/SKILL.md +54 -4
  6. package/.agents/skills/01-web-automation/katalon-cli-runner/SKILL.md +62 -12
  7. package/.agents/skills/01-web-automation/lam-script-generator/SKILL.md +55 -8
  8. package/.agents/skills/01-web-automation/mobile-appium-som/SKILL.md +60 -12
  9. package/.agents/skills/01-web-automation/mobile-appium-som/examples/BaseScreen.java +2 -2
  10. package/.agents/skills/01-web-automation/mobile-appium-som/examples/LoginScreen.java +2 -2
  11. package/.agents/skills/01-web-automation/mobile-appium-som/examples/TC_MobileLogin.java +2 -2
  12. package/.agents/skills/01-web-automation/playwright-live-interaction/SKILL.md +54 -91
  13. package/.agents/skills/01-web-automation/playwright-webapp-testing/SKILL.md +59 -11
  14. package/.agents/skills/01-web-automation/web-agent-gym-benchmarking/SKILL.md +50 -4
  15. package/.agents/skills/02-test-design/architecture-decision-records/SKILL.md +55 -9
  16. package/.agents/skills/02-test-design/gherkin-to-suite/SKILL.md +55 -9
  17. package/.agents/skills/02-test-design/rbt-manual-testing/SKILL.md +55 -8
  18. package/.agents/skills/02-test-design/review-spec/SKILL.md +50 -6
  19. package/.agents/skills/02-test-design/tot-exploratory-testing/SKILL.md +50 -4
  20. package/.agents/skills/03-api-and-contracts/api-network-mocking-interception/SKILL.md +56 -5
  21. package/.agents/skills/03-api-and-contracts/api-spec-to-e2e-matrix/SKILL.md +53 -7
  22. package/.agents/skills/03-api-and-contracts/consumer-driven-contract-testing/SKILL.md +86 -36
  23. package/.agents/skills/04-performance-and-load/backend-load-and-stress-patterns/SKILL.md +54 -6
  24. package/.agents/skills/04-performance-and-load/lean-impact-scoreboard/SKILL.md +50 -6
  25. package/.agents/skills/04-performance-and-load/web-vitals-and-performance-profiler/SKILL.md +50 -3
  26. package/.agents/skills/05-security-and-compliance/security-dast-sentinel/SKILL.md +63 -14
  27. package/.agents/skills/05-security-and-compliance/skillspector-security-guard/SKILL.md +51 -5
  28. package/.agents/skills/05-security-and-compliance/wcag-audit-patterns/SKILL.md +54 -4
  29. package/.agents/skills/06-healing-and-resilience/agentless-qa-repair/SKILL.md +51 -5
  30. package/.agents/skills/06-healing-and-resilience/antigravity-test-sentinel/SKILL.md +53 -6
  31. package/.agents/skills/06-healing-and-resilience/failure-autopsy-and-healing/SKILL.md +54 -8
  32. package/.agents/skills/06-healing-and-resilience/flaky-test-sentinel-and-quarantine/SKILL.md +60 -24
  33. package/.agents/skills/06-healing-and-resilience/self-healing-locator/SKILL.md +52 -6
  34. package/.agents/skills/06-healing-and-resilience/systematic-debugging/SKILL.md +56 -10
  35. package/.agents/skills/06-healing-and-resilience/test-driven-development/SKILL.md +58 -12
  36. package/.agents/skills/06-healing-and-resilience/verification-before-completion/SKILL.md +58 -12
  37. package/.agents/skills/06-healing-and-resilience/visual-regression-sentinel/SKILL.md +53 -5
  38. package/.agents/skills/07-data-and-state/db-state-verifier-and-seeder/SKILL.md +56 -5
  39. package/.agents/skills/07-data-and-state/file-and-report-validator/SKILL.md +53 -4
  40. package/.agents/skills/07-data-and-state/synthetic-test-data-generator/SKILL.md +58 -5
  41. package/.agents/skills/08-code-quality/code-refactoring-refactor-clean/SKILL.md +57 -11
  42. package/.agents/skills/08-code-quality/graphify-impact-analyzer/SKILL.md +83 -34
  43. package/.agents/skills/08-code-quality/graphify-impact-analyzer/examples/dependency_blast_radius.json +3 -4
  44. package/.agents/skills/08-code-quality/lean-code-ladder/SKILL.md +55 -10
  45. package/.agents/skills/08-code-quality/repo-quality-audit/SKILL.md +49 -6
  46. package/.agents/skills/08-code-quality/senior-code-review/SKILL.md +52 -7
  47. package/.agents/skills/08-code-quality/surgical-coding-principles/SKILL.md +55 -10
  48. package/.agents/skills/08-code-quality/technical-debt-harvester/SKILL.md +51 -5
  49. package/.agents/skills/09-ci-and-devops/github-actions-templates/SKILL.md +54 -17
  50. package/.agents/skills/09-ci-and-devops/github-actions-templates/examples/matrix_test_pipeline.yml +2 -1
  51. package/.agents/skills/10-agent-orchestration/actor-qa-swarm/SKILL.md +50 -4
  52. package/.agents/skills/10-agent-orchestration/agent-orchestration-multi-agent-optimize/SKILL.md +53 -7
  53. package/.agents/skills/10-agent-orchestration/event-stream-qa-orchestrator/SKILL.md +50 -4
  54. package/.agents/skills/10-agent-orchestration/persistent-planning-files/SKILL.md +58 -13
  55. package/.agents/skills/10-agent-orchestration/qa-memory-os/SKILL.md +51 -5
  56. package/.agents/skills/11-ai-and-prompting/meta-prompt-crafter/SKILL.md +57 -10
  57. package/.agents/skills/11-ai-and-prompting/mipro-prompt-compiler/SKILL.md +50 -4
  58. package/.agents/skills/11-ai-and-prompting/qa-aci-interface/SKILL.md +50 -4
  59. package/.agents/skills/11-ai-and-prompting/token-and-context-optimizer/SKILL.md +55 -9
  60. package/.cursor/rules/synapse-qa.mdc +20 -7
  61. package/.cursorrules +19 -5
  62. package/.windsurfrules +18 -3
  63. package/AGENTS.md +51 -59
  64. package/CLAUDE.md +38 -24
  65. package/LICENSE +5 -5
  66. package/NOTICE +1 -1
  67. package/README.en.md +4 -4
  68. package/README.md +4 -4
  69. package/agentskills.json +1 -1
  70. package/docs/ARCHITECTURE.en.md +2 -2
  71. package/docs/ARCHITECTURE.md +11 -2
  72. package/docs/CLIENT_SUPPORT_MATRIX.md +44 -0
  73. package/docs/CLI_REFERENCE.en.md +6 -4
  74. package/docs/CLI_REFERENCE.md +1 -1
  75. package/docs/CONTRIBUTING.en.md +1 -1
  76. package/docs/CONTRIBUTING.md +2 -2
  77. package/docs/SIDE_EFFECTING_TOOLS_INVENTORY.md +233 -0
  78. package/docs/TOOL_CATALOG.md +6 -2
  79. package/docs/research/agent_skill_training_analysis.md +1 -1
  80. package/package.json +1 -1
  81. package/plugin.json +1 -1
  82. package/skills_manifest.json +320 -55
  83. package/synapse.config.json +1 -1
  84. package/templates/ai_bridges/CLAUDE.md +29 -26
  85. package/templates/ai_bridges/copilot-instructions.md +14 -5
  86. package/templates/ai_bridges/cursor_synapse_qa.mdc +16 -7
  87. package/templates/ai_bridges/windsurfrules +14 -3
  88. package/templates/ui/index.html +2 -2
  89. package/tools/TOOLS_RUNBOOK.md +1 -1
  90. package/tools/TOOL_CATALOG.json +63 -3
  91. package/tools/__init__.py +1 -1
  92. package/tools/api_fuzzer.py +447 -132
  93. package/tools/author_integrity.py +121 -11
  94. package/tools/benchmark_swarm_context.py +130 -22
  95. package/tools/break_ui_generator.py +233 -0
  96. package/tools/browser_helpers.js +2 -2
  97. package/tools/check_version_sync.py +18 -50
  98. package/tools/cli.py +110 -19
  99. package/tools/core/bm25_retriever.py +218 -0
  100. package/tools/core/i18n.py +5 -5
  101. package/tools/core/provider_usage_adapter.py +383 -0
  102. package/tools/core/token_estimator.py +81 -15
  103. package/tools/count_tokens.py +7 -2
  104. package/tools/coverage_reporter.py +245 -0
  105. package/tools/dashboard_generator.py +8 -8
  106. package/tools/db_sandbox.py +290 -9
  107. package/tools/distill_log.py +1 -1
  108. package/tools/distill_skill.py +206 -0
  109. package/tools/git_pre_commit_guard.py +202 -1
  110. package/tools/humanize_linter.py +3 -0
  111. package/tools/mcp_docx_server.py +1 -1
  112. package/tools/mcp_excel_server.py +1 -1
  113. package/tools/mcp_server.py +104 -16
  114. package/tools/micro_mutator.py +114 -15
  115. package/tools/pentest_scope_guard.py +674 -58
  116. package/tools/perf/benchmark_perf_runner.py +42 -0
  117. package/tools/project_state.py +29 -5
  118. package/tools/reversible_sandbox.py +58 -13
  119. package/tools/rules_router.py +473 -60
  120. package/tools/security_scanner.py +80 -0
  121. package/tools/senior_code_review.py +14 -0
  122. package/tools/skill_canonical_digest.py +302 -0
  123. package/tools/skill_profiles.py +77 -7
  124. package/tools/slide_deck_exporter.py +477 -0
  125. package/tools/sync_agent_rules.py +187 -61
  126. package/tools/sync_skills_manifest.py +166 -0
  127. package/tools/task_memory_manager.py +275 -0
  128. package/tools/ui_server.py +3 -1
  129. package/tools/update_sentinel.py +3 -3
  130. package/tools/validate_host_interop.py +485 -0
  131. package/tools/validate_skills_schema.py +575 -0
  132. package/tools/verify_all.py +668 -44
  133. package/tools/welcome_page.py +2 -2
@@ -1,15 +1,44 @@
1
1
  ---
2
2
  name: web-vitals-and-performance-profiler
3
3
  description: "Measure Core Web Vitals (LCP, CLS, INP) and network waterfalls via CDP. Use when the user asks why a page is slow or needs CWV budgets enforced in CI."
4
+ category: architecture_and_analysis
5
+ version: "2.0.0"
6
+ policies:
7
+ network: localhost-only
8
+ shell: workspace-sandbox
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Web Vitals & Performance Profiler 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:** Measure Core Web Vitals (LCP, CLS, INP) and network waterfalls via CDP. Use when the user asks why a page is slow or needs CWV budgets enforced in CI.
20
+ - **Activation Scope:** Domain workflows for `04-performance-and-load` involving `web-vitals-and-performance-profiler`.
21
+
22
+ ---
23
+
24
+ ## 2. Non-Goals & Boundary Constraints
25
+
26
+ - **What NOT to do:**
27
+ - Do NOT measure performance with browser DevTools open or under unconstrained CPU/network conditions.
28
+ - Do NOT report Web Vitals metrics from a single test execution; collect median values over multiple runs.
29
+ - Do NOT focus exclusively on page load; track runtime responsiveness and visual stability.
30
+ - **Sibling Skill Boundaries:**
31
+ - backend-load-and-stress-patterns tests server saturation; web-vitals-and-performance-profiler measures client browser Core Web Vitals (LCP, FID/INP, CLS).
32
+
33
+ ---
34
+
35
+ ## 3. Ordered Execution Workflow
36
+
8
37
  > **Target:** Detect user-experience bottlenecks, layout shifts, sluggish API responses, and render-blocking assets automatically during headless test execution.
9
38
 
10
39
  ---
11
40
 
12
- ## 1. Core Principles
41
+ ### Core Principles
13
42
 
14
43
  1. **Performance as an Assertion:**
15
44
  - Functional tests must double as non-functional guardrails. If a critical workflow takes > 10 seconds to load, it should fail performance budgets.
@@ -22,9 +51,10 @@ description: "Measure Core Web Vitals (LCP, CLS, INP) and network waterfalls via
22
51
 
23
52
  ---
24
53
 
25
- ## 2. Standard Playwright Performance Measurement
54
+ ### Standard Playwright Performance Measurement
26
55
 
27
56
  ### Pattern A: Extracting Core Web Vitals via JavaScript Evaluation
57
+ <!-- classification: illustrative -->
28
58
  ```typescript
29
59
  import { test, expect } from '@playwright/test';
30
60
 
@@ -45,6 +75,7 @@ test('audit core web vitals on dashboard', async ({ page }) => {
45
75
  ```
46
76
 
47
77
  ### Pattern B: Tracking Slow Network Endpoints
78
+ <!-- classification: illustrative -->
48
79
  ```typescript
49
80
  test('detect slow backend microservices', async ({ page }) => {
50
81
  const slowRequests: { url: string; duration: number }[] = [];
@@ -63,3 +94,19 @@ test('detect slow backend microservices', async ({ page }) => {
63
94
  expect(slowRequests).toHaveLength(0); // Fail if any endpoint took > 2s
64
95
  });
65
96
  ```
97
+
98
+ ---
99
+
100
+ ## 4. Verification Points & DoD
101
+
102
+ 1. Performance measurements capture LCP, CLS, and INP against standard thresholds (Good, Needs Work, Poor).
103
+ 2. Network and CPU throttling profiles simulate realistic target user conditions.
104
+ 3. Performance telemetry logs specific DOM element culprits for LCP and CLS.
105
+
106
+ ---
107
+
108
+ ## 5. Handoff Protocol
109
+
110
+ - **Deliverables:** Core Web Vitals telemetry reports, CDP trace profiles, and performance remediation recommendations.
111
+ - **Next Subagent:** perf-engineer
112
+ - **Output Format:** Clean POM code, structured JSON telemetry, or validated markdown handoff.
@@ -1,10 +1,39 @@
1
1
  ---
2
2
  name: security-dast-sentinel
3
3
  description: "Run dynamic security audits: OWASP Top 10, security headers, BOLA/IDOR, and token leakage. Use when running or planning DAST and security scans against a target app."
4
+ category: verification_and_resilience
5
+ version: "1.0.0"
6
+ policies:
7
+ network: sandbox-only
8
+ shell: workspace-sandbox
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Security DAST Sentinel & Enterprise Security Audit Harness
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:** Run dynamic security audits: OWASP Top 10, security headers, BOLA/IDOR, and token leakage. Use when running or planning DAST and security scans against a target app.
20
+ - **Activation Scope:** Domain workflows for `05-security-and-compliance` involving `security-dast-sentinel`.
21
+
22
+ ---
23
+
24
+ ## 2. Non-Goals & Boundary Constraints
25
+
26
+ - **What NOT to do:**
27
+ - Do NOT perform destructive DAST fuzzing or injection against unapproved production endpoints.
28
+ - Do NOT bypass the 5-layer authorization and consent guardrails.
29
+ - Do NOT report false-positive vulnerability warnings without verifying reproducible evidence.
30
+ - **Sibling Skill Boundaries:**
31
+ - skillspector-security-guard audits skill and script security; security-dast-sentinel conducts dynamic application security testing (OWASP Top 10).
32
+
33
+ ---
34
+
35
+ ## 3. Ordered Execution Workflow
36
+
8
37
  > **Purpose:** Automated Dynamic Application Security Testing (DAST), defensive runtime verification, and mathematical security audit orchestration across enterprise web applications, APIs, and AI agent swarms. Bridges functional automated testing with OWASP Top 10 compliance gates and Cloudflare 6-Phase audit rigor.
9
38
  >
10
39
  > [!IMPORTANT] Authorization & Scope of Engagement
@@ -12,8 +41,9 @@ description: "Run dynamic security audits: OWASP Top 10, security headers, BOLA/
12
41
 
13
42
  ---
14
43
 
15
- ## 0. 6-Phase Security Audit FSM (Cloudflare Enterprise Pattern)
44
+ ### 6-Phase Security Audit FSM (Cloudflare Enterprise Pattern)
16
45
 
46
+ <!-- classification: illustrative -->
17
47
  ```text
18
48
  Phase 1: Reconnaissance ──► Phase 2: Hunting Waves ──► Phase 3: Candidate Validation
19
49
  │ │ │
@@ -29,10 +59,11 @@ Phase 6: Reporting ◄── Phase 5: Verification ◄── Phase 4: Stru
29
59
  Enumerate attack surface boundaries, components, and subsystems:
30
60
  `Coverage Unit = Surface × Boundary × Subsystem × Attack Class [× Lifecycle]`
31
61
  Initialize and track mathematical coverage via `tools/security_coverage_ledger.py`:
32
- ```bash
62
+ <!-- classification: illustrative -->
63
+ ```bash
33
64
  python tools/security_coverage_ledger.py init -f coverage-ledger.json
34
65
  python tools/security_coverage_ledger.py add -f coverage-ledger.json -s "web_api" -b "auth" --subsystem "billing" -a "idor"
35
- ```
66
+ ```
36
67
  2. **Phase 2: Coverage-Led Hunting Waves**:
37
68
  Organize hunting into structured waves (Wave 1: core boundaries, Wave 2: integrations, Wave 3: edge cases). Refer to [**Attack Classes Taxonomy (`references/ATTACK-CLASSES.md`)**](references/ATTACK-CLASSES.md).
38
69
  3. **Phase 3: Candidate Validation**:
@@ -41,18 +72,20 @@ Phase 6: Reporting ◄── Phase 5: Verification ◄── Phase 4: Stru
41
72
  Record findings in structured formats: `confirmed` (complete local proof), `needs_validation` (unobservable deployment/cloud configuration), or `rejected`.
42
73
  5. **Phase 5: Record Verification**:
43
74
  Verify coverage state invariants: ensure every covered unit has assigned agent ownership, reviewed file paths, and local assertions.
44
- ```bash
75
+ <!-- classification: illustrative -->
76
+ ```bash
45
77
  python tools/security_coverage_ledger.py validate coverage-ledger.json
46
- ```
78
+ ```
47
79
  6. **Phase 6: Target-Neutral Reporting**:
48
80
  Generate mathematical metrics and final risk summaries:
49
- ```bash
81
+ <!-- classification: illustrative -->
82
+ ```bash
50
83
  python tools/security_coverage_ledger.py summary coverage-ledger.json
51
- ```
84
+ ```
52
85
 
53
86
  ---
54
87
 
55
- ## 1. Core Defensive Scope & OWASP Top 10
88
+ ### Core Defensive Scope & OWASP Top 10
56
89
 
57
90
  | OWASP Category | Threat Vector | Automated Defensive Check | Assertion Target |
58
91
  | :--- | :--- | :--- | :--- |
@@ -65,7 +98,7 @@ Phase 6: Reporting ◄── Phase 5: Verification ◄── Phase 4: Stru
65
98
 
66
99
  ---
67
100
 
68
- ## 2. Automated Security Headers Audit
101
+ ### Automated Security Headers Audit
69
102
 
70
103
  Automated DAST verification enforces mandatory HTTP security headers (`Strict-Transport-Security`, `Content-Security-Policy`, `X-Frame-Options`, `X-Content-Type-Options`) to prevent clickjacking, MIME sniffing, and insecure transport.
71
104
 
@@ -73,7 +106,7 @@ Automated DAST verification enforces mandatory HTTP security headers (`Strict-Tr
73
106
 
74
107
  ---
75
108
 
76
- ## 3. BOLA / IDOR Defense Check
109
+ ### BOLA / IDOR Defense Check
77
110
 
78
111
  Automated cross-tenant authorization checks verify that Tenant B cannot access Tenant A resources (returning `403` or `404`, never `200`).
79
112
 
@@ -81,14 +114,14 @@ Automated cross-tenant authorization checks verify that Tenant B cannot access T
81
114
 
82
115
  ---
83
116
 
84
- ## 4. Environment Allowlist Guard
117
+ ### Environment Allowlist Guard
85
118
 
86
119
  - Automated security checks, fuzzing (`tools/api_fuzzer.py`), and DB sandboxing (`tools/db_sandbox.py`) enforce non-production allowlists (`localhost`, `staging`, `dev`, `qa`, `sandbox`).
87
120
  - Fuzzing production hosts without `SYNAPSE_ALLOW_PROD_FUZZ=1` is automatically blocked.
88
121
 
89
122
  ---
90
123
 
91
- ## 5. Passive vs Active Scan Taxonomy & Severity Levels
124
+ ### Passive vs Active Scan Taxonomy & Severity Levels
92
125
 
93
126
  > *Adapted from the OWASP ZAP scanning model (Apache-2.0, zaproxy/zaproxy).*
94
127
 
@@ -112,8 +145,24 @@ Rules:
112
145
 
113
146
  ---
114
147
 
115
- ## 6. AI, LLM & Agentic Security Hardening (Cloudflare Defense Pattern)
148
+ ### AI, LLM & Agentic Security Hardening (Cloudflare Defense Pattern)
116
149
 
117
150
  For systems with integrated LLMs, tool-calling agents, or MCP servers, inspect:
118
151
  - [**Attack Classes Taxonomy (`references/ATTACK-CLASSES.md`)**](references/ATTACK-CLASSES.md): Core vulnerability categories across Injection, Access Control, File Handling, Cryptography, Business Logic, and Feature Abuse.
119
152
  - [**AI & Agent Security Hunting Guide (`references/AI-AND-LLM.md`)**](references/AI-AND-LLM.md): Auditing indirect injection, persistent memory poisoning, tool-argument downstream sink execution, confused-deputy authorization, tool-schema disagreement, unbounded action loops, and MCP identity confusion.
153
+
154
+ ---
155
+
156
+ ## 4. Verification Points & DoD
157
+
158
+ 1. Target endpoints verified against authorization whitelist and consent grant.
159
+ 2. Security scan covers OWASP Top 10 vulnerabilities (SQLi, XSS, SSRF, broken auth, security headers).
160
+ 3. Findings categorized by CVSS severity with reproduction steps and remediation guidance.
161
+
162
+ ---
163
+
164
+ ## 5. Handoff Protocol
165
+
166
+ - **Deliverables:** DAST vulnerability audit reports, security header scorecards, and reproduction curl commands.
167
+ - **Next Subagent:** quality-gatekeeper
168
+ - **Output Format:** Clean POM code, structured JSON telemetry, or validated markdown handoff.
@@ -1,16 +1,45 @@
1
1
  ---
2
2
  name: skillspector-security-guard
3
3
  description: "Audit and verify AI agent skills, prompts, and MCP configurations against vulnerability vectors inspired by NVIDIA SkillSpector. Use when auditing skills and plugins for prompt-injection and security threats."
4
+ category: verification_and_resilience
5
+ version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: read-only
9
+ filesystem: read-only
4
10
  ---
5
-
6
11
  # SkillSpector Security Guard — AI Agent & MCP Security Sentinel
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:** Audit and verify AI agent skills, prompts, and MCP configurations against vulnerability vectors inspired by NVIDIA SkillSpector. Use when auditing skills and plugins for prompt-injection and security threats.
20
+ - **Activation Scope:** Domain workflows for `05-security-and-compliance` involving `skillspector-security-guard`.
21
+
22
+ ---
23
+
24
+ ## 2. Non-Goals & Boundary Constraints
25
+
26
+ - **What NOT to do:**
27
+ - Do NOT permit execution of agent skills with unconstrained shell, network, or filesystem permissions.
28
+ - Do NOT whitelist security policy violations without documented architectural justification.
29
+ - Do NOT ignore secret leakage patterns in skill references and examples.
30
+ - **Sibling Skill Boundaries:**
31
+ - security-dast-sentinel tests live application endpoints; skillspector-security-guard conducts static security audits of agent skills and manifests.
32
+
33
+ ---
34
+
35
+ ## 3. Ordered Execution Workflow
36
+
8
37
  > **Purpose:** Autonomous security vetting for AI Agent skills, prompt instructions, Model Context Protocol (MCP) servers, and automation tools.
9
38
  > **Heritage:** Inspired by and adapted from **[NVIDIA/SkillSpector](https://github.com/NVIDIA/SkillSpector)** (Apache 2.0).
10
39
 
11
40
  ---
12
41
 
13
- ## 1. Core Threat Vectors
42
+ ### Core Threat Vectors
14
43
 
15
44
  AI agent skills execute with terminal and workspace permissions. Unvetted third-party skills can introduce severe risks:
16
45
  - **Prompt Injection:** Overriding core safety instructions or forcing jailbreaks.
@@ -21,7 +50,7 @@ AI agent skills execute with terminal and workspace permissions. Unvetted third-
21
50
 
22
51
  ---
23
52
 
24
- ## 2. Threat Vector Categories
53
+ ### Threat Vector Categories
25
54
 
26
55
  | Category | Description | Severity |
27
56
  | :--- | :--- | :--- |
@@ -34,7 +63,7 @@ AI agent skills execute with terminal and workspace permissions. Unvetted third-
34
63
 
35
64
  ---
36
65
 
37
- ## 3. Defense Guard & Prohibition Context
66
+ ### Defense Guard & Prohibition Context
38
67
 
39
68
  To prevent false alarms in educational documentation (e.g. *"Never run sudo"*):
40
69
  1. **Negative Imperatives:** Matches preceded by negations (`never`, `do not`, `avoid`, `forbidden`) are recognized as defensive rules.
@@ -43,8 +72,9 @@ To prevent false alarms in educational documentation (e.g. *"Never run sudo"*):
43
72
 
44
73
  ---
45
74
 
46
- ## 4. CLI Audit Commands
75
+ ### CLI Audit Commands
47
76
 
77
+ <!-- classification: illustrative -->
48
78
  ```bash
49
79
  # Scan a specific candidate skill or file
50
80
  synapse skillspector path/to/SKILL.md
@@ -55,3 +85,19 @@ synapse skillspector --scan-skills
55
85
  # Fail CI pipeline if high or critical risks are detected
56
86
  synapse skillspector --scan-skills --strict
57
87
  ```
88
+
89
+ ---
90
+
91
+ ## 4. Verification Points & DoD
92
+
93
+ 1. All skills pass permission and policy boundary enforcement (network, shell, filesystem).
94
+ 2. Zero high-entropy secrets or private credentials discovered in skill files.
95
+ 3. Manifest and skill frontmatter policies align with least-privilege standards.
96
+
97
+ ---
98
+
99
+ ## 5. Handoff Protocol
100
+
101
+ - **Deliverables:** Skill security audit report, policy violation logs, and remediation patches.
102
+ - **Next Subagent:** quality-gatekeeper
103
+ - **Output Format:** Clean POM code, structured JSON telemetry, or validated markdown handoff.
@@ -1,15 +1,44 @@
1
1
  ---
2
2
  name: wcag-audit-patterns
3
3
  description: "Audit WCAG 2.2 accessibility (A/AA), keyboard navigation, and ARIA roles. Use when auditing accessibility against WCAG 2.2 A/AA criteria."
4
+ category: architecture_and_analysis
5
+ version: "2.0.0"
6
+ policies:
7
+ network: localhost-only
8
+ shell: read-only
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # WCAG 2.2 Accessibility Audit Patterns
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:** Audit WCAG 2.2 accessibility (A/AA), keyboard navigation, and ARIA roles. Use when auditing accessibility against WCAG 2.2 A/AA criteria.
20
+ - **Activation Scope:** Domain workflows for `05-security-and-compliance` involving `wcag-audit-patterns`.
21
+
22
+ ---
23
+
24
+ ## 2. Non-Goals & Boundary Constraints
25
+
26
+ - **What NOT to do:**
27
+ - Do NOT rely exclusively on automated axe-core scans (automated tools catch only ~30-40% of WCAG criteria).
28
+ - Do NOT ignore keyboard navigation, screen reader flow, or focus management.
29
+ - Do NOT bypass color contrast checks across dark and light UI themes.
30
+ - **Sibling Skill Boundaries:**
31
+ - playwright-live-interaction probes DOM selectors; wcag-audit-patterns evaluates accessibility compliance against WCAG 2.2 A/AA criteria.
32
+
33
+ ---
34
+
35
+ ## 3. Ordered Execution Workflow
36
+
8
37
  Engineering standards for automated, continuous Web Content Accessibility Guidelines (WCAG 2.2 Level A and AA) auditing across enterprise web applications.
9
38
 
10
39
  ---
11
40
 
12
- ## 1. Core WCAG 2.2 Success Criteria Matrix
41
+ ### Core WCAG 2.2 Success Criteria Matrix
13
42
 
14
43
  | Criterion | Rule Code | Level | Requirement & Automated Assertion |
15
44
  | :--- | :--- | :--- | :--- |
@@ -27,9 +56,10 @@ Engineering standards for automated, continuous Web Content Accessibility Guidel
27
56
 
28
57
  ---
29
58
 
30
- ## 2. Playwright Automated Accessibility Testing Patterns
59
+ ### Playwright Automated Accessibility Testing Patterns
31
60
 
32
61
  ### Pattern A: Integrating `@axe-core/playwright` for Comprehensive Audits
62
+ <!-- classification: illustrative -->
33
63
  ```typescript
34
64
  import { test, expect } from '@playwright/test';
35
65
  import AxeBuilder from '@axe-core/playwright';
@@ -48,6 +78,7 @@ test('verify WCAG 2.2 Level AA compliance on dashboard', async ({ page }) => {
48
78
  ```
49
79
 
50
80
  ### Pattern B: Modal Keyboard Focus Trap and Escape Verification
81
+ <!-- classification: illustrative -->
51
82
  ```typescript
52
83
  test('modal dialog traps keyboard focus and closes on Escape', async ({ page }) => {
53
84
  await page.goto('/settings');
@@ -67,6 +98,7 @@ test('modal dialog traps keyboard focus and closes on Escape', async ({ page })
67
98
  ```
68
99
 
69
100
  ### Pattern C: WCAG 2.5.8 Target Size ($24 \times 24\text{px}$) Assertion
101
+ <!-- classification: illustrative -->
70
102
  ```typescript
71
103
  test('all interactive buttons satisfy WCAG 2.5.8 24x24px target size', async ({ page }) => {
72
104
  await page.goto('/checkout');
@@ -88,6 +120,7 @@ test('all interactive buttons satisfy WCAG 2.5.8 24x24px target size', async ({
88
120
  ```
89
121
 
90
122
  ### Pattern D: Playwright Native Accessibility Object Model (AOM) Snapshot
123
+ <!-- classification: illustrative -->
91
124
  ```python
92
125
  # Python Playwright AOM Snapshot Assertion
93
126
  def test_accessible_tree_structure(page):
@@ -100,10 +133,11 @@ def test_accessible_tree_structure(page):
100
133
 
101
134
  ---
102
135
 
103
- ## 3. Automated CLI Auditing via Tooling
136
+ ### Automated CLI Auditing via Tooling
104
137
 
105
138
  Synapse Hub provides automated accessibility auditing via `tools/wcag_audit.py`:
106
139
 
140
+ <!-- classification: illustrative -->
107
141
  ```bash
108
142
  # Audit a local HTML snapshot or directory
109
143
  python tools/wcag_audit.py path/to/page.html -o docs/wcag_audit_report.md
@@ -114,3 +148,19 @@ python tools/wcag_audit.py https://staging.example.com --url -o docs/wcag_audit_
114
148
  # CLI integration via agent-qa
115
149
  agent-qa wcag-audit path/to/page.html
116
150
  ```
151
+
152
+ ---
153
+
154
+ ## 4. Verification Points & DoD
155
+
156
+ 1. Automated accessibility scans run via axe-core / Playwright with 0 Level A/AA violations.
157
+ 2. Manual check protocol verifies keyboard tab order, focus rings, and skip links.
158
+ 3. Audit report maps violations to specific WCAG 2.2 criteria with remediation code.
159
+
160
+ ---
161
+
162
+ ## 5. Handoff Protocol
163
+
164
+ - **Deliverables:** WCAG 2.2 accessibility audit report, violation element selectors, and CSS/HTML remediation snippets.
165
+ - **Next Subagent:** quality-gatekeeper
166
+ - **Output Format:** Clean POM code, structured JSON telemetry, or validated markdown handoff.
@@ -1,16 +1,45 @@
1
1
  ---
2
2
  name: agentless-qa-repair
3
3
  description: "Repair broken test scripts and Page Classes using an Agentless 3-phase flow: localization, candidate synthesis, and minimal diff validation. Use when repairing test failures without multi-agent chat bloat."
4
+ category: verification_and_resilience
5
+ version: "1.0.0"
6
+ policies:
7
+ network: none
8
+ shell: workspace-sandbox
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Agentless QA Repair Skill — Ultra-Low-Token 3-Phase Failure Healing
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:** Repair broken test scripts and Page Classes using an Agentless 3-phase flow: localization, candidate synthesis, and minimal diff validation. Use when repairing test failures without multi-agent chat bloat.
20
+ - **Activation Scope:** Domain workflows for `06-healing-and-resilience` involving `agentless-qa-repair`.
21
+
22
+ ---
23
+
24
+ ## 2. Non-Goals & Boundary Constraints
25
+
26
+ - **What NOT to do:**
27
+ - Do NOT initiate costly multi-turn agent chat loops for straightforward syntax or locator failures.
28
+ - Do NOT accept patch candidates that violate Clean POM or introduce speculative refactoring.
29
+ - Do NOT apply patches without verifying test execution passes with exit code 0.
30
+ - **Sibling Skill Boundaries:**
31
+ - failure-autopsy-and-healing performs deep diagnostic autopsies; agentless-qa-repair applies single-pass 3-phase minimal diff repair.
32
+
33
+ ---
34
+
35
+ ## 3. Ordered Execution Workflow
36
+
8
37
  > **Paradigm Attribution:** Inspired by **UIUC OpenAutoCoder Agentless**.
9
- > **Core Principle:** The best fix is the smallest working diff without round-trip chat loops. Solve 80% of daily test automation defects with a single-pass 3-stage pipeline under 2,500 tokens.
38
+ > **Core Principle:** The best fix is the smallest working diff without round-trip chat loops. Heuristic guidelines target rapid resolution of common test automation defects with a focused 3-stage pipeline under compact token budgets.
10
39
 
11
40
  ---
12
41
 
13
- ## 1. The 3-Phase Deterministic Pipeline
42
+ ### The 3-Phase Deterministic Pipeline
14
43
 
15
44
  Rather than spawning multi-turn swarm conversations that cost 40,000–80,000 tokens per failure, `agentless-qa-repair` executes in three deterministic stages:
16
45
 
@@ -39,10 +68,11 @@ flowchart LR
39
68
 
40
69
  ---
41
70
 
42
- ## 2. CLI Tool Usage
71
+ ### CLI Tool Usage
43
72
 
44
73
  Autonomous trigger via `tools/agentless_patcher.py`:
45
74
 
75
+ <!-- classification: illustrative -->
46
76
  ```bash
47
77
  # End-to-end 3-stage healing
48
78
  python tools/agentless_patcher.py heal-failure \
@@ -62,8 +92,24 @@ python tools/agentless_patcher.py generate-candidates \
62
92
 
63
93
  ---
64
94
 
65
- ## 3. Strict Operating Invariants
95
+ ### Strict Operating Invariants
66
96
 
67
97
  - **Token Budget Ceiling:** Must stay under **2,500 tokens** per repair cycle.
68
98
  - **Zero Raw Selectors in Test Scripts:** If the failing file is located in `tests/`, `Scripts/`, or matches `*.spec.ts`, the fix must redirect selector adjustments into the corresponding Page Class extending `BasePage`.
69
99
  - **Minimal Working Diff:** Always choose the patch with the fewest altered lines that passes verification.
100
+
101
+ ---
102
+
103
+ ## 4. Verification Points & DoD
104
+
105
+ 1. Failing code localized to enclosing method and tight line span.
106
+ 2. Synthesized patch candidate adheres to Clean POM (zero raw locators in scripts).
107
+ 3. Repaired test executes cleanly with verified pass.
108
+
109
+ ---
110
+
111
+ ## 5. Handoff Protocol
112
+
113
+ - **Deliverables:** Minimal unified diff patch, failure localization report, and test execution verification log.
114
+ - **Next Subagent:** failure-analyst / quality-gatekeeper
115
+ - **Output Format:** Clean POM code, structured JSON telemetry, or validated markdown handoff.
@@ -1,15 +1,44 @@
1
1
  ---
2
2
  name: antigravity-test-sentinel
3
3
  description: "Enforce verification-first discipline: blocks task completion until tests and quality gates pass. Use when enforcing Definition-of-Done quality gates before completing a code or test task."
4
+ category: verification_and_resilience
5
+ version: "2.0.0"
6
+ policies:
7
+ network: none
8
+ shell: workspace-sandbox
9
+ filesystem: workspace-sandbox
4
10
  ---
5
-
6
11
  # Antigravity Test Sentinel — Verification-First Gatekeeper
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:** Enforce verification-first discipline: blocks task completion until tests and quality gates pass. Use when enforcing Definition-of-Done quality gates before completing a code or test task.
20
+ - **Activation Scope:** Domain workflows for `06-healing-and-resilience` involving `antigravity-test-sentinel`.
21
+
22
+ ---
23
+
24
+ ## 2. Non-Goals & Boundary Constraints
25
+
26
+ - **What NOT to do:**
27
+ - Do NOT declare tasks or tests complete without fresh, verifiable command execution output.
28
+ - Do NOT accept cached, fabricated, or stale test execution evidence.
29
+ - Do NOT bypass the 10 Quality Gates DoD when operating in Hub mode.
30
+ - **Sibling Skill Boundaries:**
31
+ - verification-before-completion checks evidence; antigravity-test-sentinel enforces the zero-hallucination verification gate and Sentinel status header.
32
+
33
+ ---
34
+
35
+ ## 3. Ordered Execution Workflow
36
+
8
37
  The **Antigravity Test Sentinel** enforces absolute engineering integrity across test creation, script refactoring, and bug fixes. It acts as an autonomous circuit breaker that physically prohibits the AI Agent from concluding a task without verifiable proof of test execution success.
9
38
 
10
39
  ---
11
40
 
12
- ## 1. The Sentinel Axiom (Zero-Hallucination Gate)
41
+ ### The Sentinel Axiom (Zero-Hallucination Gate)
13
42
 
14
43
  1. **The Core Rule:**
15
44
  - Writing code is NOT completing the task.
@@ -23,7 +52,7 @@ The **Antigravity Test Sentinel** enforces absolute engineering integrity across
23
52
 
24
53
  ---
25
54
 
26
- ## 2. Gate-Lock Protocol
55
+ ### Gate-Lock Protocol
27
56
 
28
57
  Whenever an Agent modifies any test script, Page Class, locator, or helper method:
29
58
 
@@ -40,9 +69,10 @@ flowchart TD
40
69
 
41
70
  1. **Step 1: Execute Runner Command:**
42
71
  - Run the targeted test case or test suite via headless CLI runner or verification gate:
43
- ```bash
72
+ <!-- classification: illustrative -->
73
+ ```bash
44
74
  synapse verify
45
- ```
75
+ ```
46
76
  2. **Step 2: Inspect Exit Code:**
47
77
  - If the process terminates with exit code != 0, the task is **LOCKED**.
48
78
  - The Agent must not ask the user for confirmation or declare success.
@@ -54,10 +84,27 @@ flowchart TD
54
84
 
55
85
  ---
56
86
 
57
- ## 3. Sentinel Status Header
87
+ ### Sentinel Status Header
58
88
 
59
89
  In accordance with Antigravity operating discipline, include the sentinel verification status in the session summary:
60
90
 
91
+ <!-- classification: illustrative -->
61
92
  ```text
62
93
  > 🛡️ SENTINEL STATUS: VERIFIED (Exit Code: 0 | 10/10 Gates PASS)
63
94
  ```
95
+
96
+ ---
97
+
98
+ ## 4. Verification Points & DoD
99
+
100
+ 1. Every verification claim backed by fresh terminal execution logs.
101
+ 2. All 10 Quality Gates evaluated and confirmed PASS.
102
+ 3. Zero fake passes, zero swallowed exceptions, and zero mock shortcuts.
103
+
104
+ ---
105
+
106
+ ## 5. Handoff Protocol
107
+
108
+ - **Deliverables:** Sentinel verification header, gate execution summary, and final acceptance verdict.
109
+ - **Next Subagent:** quality-gatekeeper
110
+ - **Output Format:** Clean POM code, structured JSON telemetry, or validated markdown handoff.