@teevee98/synapse-hub 4.2.0 → 4.2.2
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/skills/01-web-automation/auth-session-and-cookie-manager/SKILL.md +46 -2
- package/.agents/skills/01-web-automation/bats-testing-patterns/SKILL.md +49 -4
- package/.agents/skills/01-web-automation/clean-pom-crafter/SKILL.md +56 -66
- package/.agents/skills/01-web-automation/e2e-testing-patterns/SKILL.md +48 -3
- package/.agents/skills/01-web-automation/katalon-cli-runner/SKILL.md +56 -11
- package/.agents/skills/01-web-automation/lam-script-generator/SKILL.md +49 -7
- package/.agents/skills/01-web-automation/mobile-appium-som/SKILL.md +54 -11
- package/.agents/skills/01-web-automation/playwright-live-interaction/SKILL.md +48 -90
- package/.agents/skills/01-web-automation/playwright-webapp-testing/SKILL.md +53 -10
- package/.agents/skills/01-web-automation/web-agent-gym-benchmarking/SKILL.md +44 -3
- package/.agents/skills/02-test-design/architecture-decision-records/SKILL.md +49 -8
- package/.agents/skills/02-test-design/gherkin-to-suite/SKILL.md +49 -8
- package/.agents/skills/02-test-design/rbt-manual-testing/SKILL.md +49 -7
- package/.agents/skills/02-test-design/review-spec/SKILL.md +46 -5
- package/.agents/skills/02-test-design/tot-exploratory-testing/SKILL.md +44 -3
- package/.agents/skills/03-api-and-contracts/api-network-mocking-interception/SKILL.md +50 -4
- package/.agents/skills/03-api-and-contracts/api-spec-to-e2e-matrix/SKILL.md +47 -6
- package/.agents/skills/03-api-and-contracts/consumer-driven-contract-testing/SKILL.md +79 -34
- package/.agents/skills/04-performance-and-load/backend-load-and-stress-patterns/SKILL.md +47 -4
- package/.agents/skills/04-performance-and-load/lean-impact-scoreboard/SKILL.md +46 -5
- package/.agents/skills/04-performance-and-load/web-vitals-and-performance-profiler/SKILL.md +44 -2
- package/.agents/skills/05-security-and-compliance/security-dast-sentinel/SKILL.md +57 -13
- package/.agents/skills/05-security-and-compliance/skillspector-security-guard/SKILL.md +45 -4
- package/.agents/skills/05-security-and-compliance/wcag-audit-patterns/SKILL.md +48 -3
- package/.agents/skills/06-healing-and-resilience/agentless-qa-repair/SKILL.md +45 -4
- package/.agents/skills/06-healing-and-resilience/antigravity-test-sentinel/SKILL.md +47 -5
- package/.agents/skills/06-healing-and-resilience/failure-autopsy-and-healing/SKILL.md +48 -7
- package/.agents/skills/06-healing-and-resilience/flaky-test-sentinel-and-quarantine/SKILL.md +54 -23
- package/.agents/skills/06-healing-and-resilience/self-healing-locator/SKILL.md +46 -5
- package/.agents/skills/06-healing-and-resilience/systematic-debugging/SKILL.md +50 -9
- package/.agents/skills/06-healing-and-resilience/test-driven-development/SKILL.md +52 -11
- package/.agents/skills/06-healing-and-resilience/verification-before-completion/SKILL.md +52 -11
- package/.agents/skills/06-healing-and-resilience/visual-regression-sentinel/SKILL.md +47 -4
- package/.agents/skills/07-data-and-state/db-state-verifier-and-seeder/SKILL.md +50 -4
- package/.agents/skills/07-data-and-state/file-and-report-validator/SKILL.md +47 -3
- package/.agents/skills/07-data-and-state/synthetic-test-data-generator/SKILL.md +52 -4
- package/.agents/skills/08-code-quality/code-refactoring-refactor-clean/SKILL.md +51 -10
- package/.agents/skills/08-code-quality/graphify-impact-analyzer/SKILL.md +78 -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 +49 -9
- package/.agents/skills/08-code-quality/repo-quality-audit/SKILL.md +45 -5
- package/.agents/skills/08-code-quality/senior-code-review/SKILL.md +48 -6
- package/.agents/skills/08-code-quality/surgical-coding-principles/SKILL.md +49 -9
- package/.agents/skills/08-code-quality/technical-debt-harvester/SKILL.md +47 -4
- package/.agents/skills/09-ci-and-devops/github-actions-templates/SKILL.md +48 -16
- 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 +44 -3
- package/.agents/skills/10-agent-orchestration/agent-orchestration-multi-agent-optimize/SKILL.md +47 -6
- package/.agents/skills/10-agent-orchestration/event-stream-qa-orchestrator/SKILL.md +44 -3
- package/.agents/skills/10-agent-orchestration/persistent-planning-files/SKILL.md +52 -12
- package/.agents/skills/10-agent-orchestration/qa-memory-os/SKILL.md +45 -4
- package/.agents/skills/11-ai-and-prompting/meta-prompt-crafter/SKILL.md +51 -9
- package/.agents/skills/11-ai-and-prompting/mipro-prompt-compiler/SKILL.md +44 -3
- package/.agents/skills/11-ai-and-prompting/qa-aci-interface/SKILL.md +44 -3
- package/.agents/skills/11-ai-and-prompting/token-and-context-optimizer/SKILL.md +49 -8
- package/.cursor/rules/synapse-qa.mdc +20 -7
- package/.cursorrules +19 -5
- package/.windsurfrules +18 -3
- package/AGENTS.md +51 -65
- package/CLAUDE.md +38 -24
- package/README.en.md +2 -2
- package/README.md +2 -2
- package/agentskills.json +1 -1
- package/docs/ARCHITECTURE.en.md +1 -1
- package/docs/ARCHITECTURE.md +1 -1
- package/docs/CLIENT_SUPPORT_MATRIX.md +44 -0
- package/docs/SIDE_EFFECTING_TOOLS_INVENTORY.md +233 -0
- package/package.json +1 -1
- package/plugin.json +1 -1
- package/skills_manifest.json +1 -1
- 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/tools/TOOLS_RUNBOOK.md +1 -1
- package/tools/__init__.py +1 -1
- package/tools/api_fuzzer.py +295 -41
- package/tools/benchmark_swarm_context.py +11 -4
- package/tools/browser_helpers.js +2 -2
- package/tools/bump_version.py +2 -2
- package/tools/cli.py +4 -4
- package/tools/core/bm25_retriever.py +1 -1
- package/tools/core/i18n.py +1 -1
- package/tools/core/provider_usage_adapter.py +66 -0
- package/tools/core/token_estimator.py +39 -1
- package/tools/count_tokens.py +2 -2
- package/tools/dashboard_generator.py +8 -8
- package/tools/db_sandbox.py +182 -43
- package/tools/distill_log.py +1 -1
- package/tools/distill_skill.py +17 -2
- package/tools/git_pre_commit_guard.py +190 -1
- package/tools/hub_publisher.py +2 -12
- package/tools/mcp_docx_server.py +1 -1
- package/tools/mcp_excel_server.py +1 -1
- package/tools/mcp_server.py +33 -5
- package/tools/micro_mutator.py +30 -1
- package/tools/pentest_scope_guard.py +288 -15
- package/tools/project_state.py +29 -5
- package/tools/reversible_sandbox.py +58 -13
- package/tools/rules_router.py +80 -27
- package/tools/skill_canonical_digest.py +60 -2
- package/tools/sync_agent_rules.py +187 -61
- package/tools/task_memory_manager.py +16 -1
- package/tools/ui_server.py +3 -1
- package/tools/update_sentinel.py +3 -3
- package/tools/validate_skills_schema.py +349 -56
- package/tools/verify_all.py +98 -4
- package/tools/welcome_page.py +1 -1
|
@@ -10,6 +10,30 @@ policies:
|
|
|
10
10
|
---
|
|
11
11
|
# Security DAST Sentinel & Enterprise Security Audit Harness
|
|
12
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
|
+
|
|
13
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.
|
|
14
38
|
>
|
|
15
39
|
> [!IMPORTANT] Authorization & Scope of Engagement
|
|
@@ -17,8 +41,9 @@ policies:
|
|
|
17
41
|
|
|
18
42
|
---
|
|
19
43
|
|
|
20
|
-
|
|
44
|
+
### 6-Phase Security Audit FSM (Cloudflare Enterprise Pattern)
|
|
21
45
|
|
|
46
|
+
<!-- classification: illustrative -->
|
|
22
47
|
```text
|
|
23
48
|
Phase 1: Reconnaissance ──► Phase 2: Hunting Waves ──► Phase 3: Candidate Validation
|
|
24
49
|
│ │ │
|
|
@@ -34,10 +59,11 @@ Phase 6: Reporting ◄── Phase 5: Verification ◄── Phase 4: Stru
|
|
|
34
59
|
Enumerate attack surface boundaries, components, and subsystems:
|
|
35
60
|
`Coverage Unit = Surface × Boundary × Subsystem × Attack Class [× Lifecycle]`
|
|
36
61
|
Initialize and track mathematical coverage via `tools/security_coverage_ledger.py`:
|
|
37
|
-
|
|
62
|
+
<!-- classification: illustrative -->
|
|
63
|
+
```bash
|
|
38
64
|
python tools/security_coverage_ledger.py init -f coverage-ledger.json
|
|
39
65
|
python tools/security_coverage_ledger.py add -f coverage-ledger.json -s "web_api" -b "auth" --subsystem "billing" -a "idor"
|
|
40
|
-
|
|
66
|
+
```
|
|
41
67
|
2. **Phase 2: Coverage-Led Hunting Waves**:
|
|
42
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).
|
|
43
69
|
3. **Phase 3: Candidate Validation**:
|
|
@@ -46,18 +72,20 @@ Phase 6: Reporting ◄── Phase 5: Verification ◄── Phase 4: Stru
|
|
|
46
72
|
Record findings in structured formats: `confirmed` (complete local proof), `needs_validation` (unobservable deployment/cloud configuration), or `rejected`.
|
|
47
73
|
5. **Phase 5: Record Verification**:
|
|
48
74
|
Verify coverage state invariants: ensure every covered unit has assigned agent ownership, reviewed file paths, and local assertions.
|
|
49
|
-
|
|
75
|
+
<!-- classification: illustrative -->
|
|
76
|
+
```bash
|
|
50
77
|
python tools/security_coverage_ledger.py validate coverage-ledger.json
|
|
51
|
-
|
|
78
|
+
```
|
|
52
79
|
6. **Phase 6: Target-Neutral Reporting**:
|
|
53
80
|
Generate mathematical metrics and final risk summaries:
|
|
54
|
-
|
|
81
|
+
<!-- classification: illustrative -->
|
|
82
|
+
```bash
|
|
55
83
|
python tools/security_coverage_ledger.py summary coverage-ledger.json
|
|
56
|
-
|
|
84
|
+
```
|
|
57
85
|
|
|
58
86
|
---
|
|
59
87
|
|
|
60
|
-
|
|
88
|
+
### Core Defensive Scope & OWASP Top 10
|
|
61
89
|
|
|
62
90
|
| OWASP Category | Threat Vector | Automated Defensive Check | Assertion Target |
|
|
63
91
|
| :--- | :--- | :--- | :--- |
|
|
@@ -70,7 +98,7 @@ Phase 6: Reporting ◄── Phase 5: Verification ◄── Phase 4: Stru
|
|
|
70
98
|
|
|
71
99
|
---
|
|
72
100
|
|
|
73
|
-
|
|
101
|
+
### Automated Security Headers Audit
|
|
74
102
|
|
|
75
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.
|
|
76
104
|
|
|
@@ -78,7 +106,7 @@ Automated DAST verification enforces mandatory HTTP security headers (`Strict-Tr
|
|
|
78
106
|
|
|
79
107
|
---
|
|
80
108
|
|
|
81
|
-
|
|
109
|
+
### BOLA / IDOR Defense Check
|
|
82
110
|
|
|
83
111
|
Automated cross-tenant authorization checks verify that Tenant B cannot access Tenant A resources (returning `403` or `404`, never `200`).
|
|
84
112
|
|
|
@@ -86,14 +114,14 @@ Automated cross-tenant authorization checks verify that Tenant B cannot access T
|
|
|
86
114
|
|
|
87
115
|
---
|
|
88
116
|
|
|
89
|
-
|
|
117
|
+
### Environment Allowlist Guard
|
|
90
118
|
|
|
91
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`).
|
|
92
120
|
- Fuzzing production hosts without `SYNAPSE_ALLOW_PROD_FUZZ=1` is automatically blocked.
|
|
93
121
|
|
|
94
122
|
---
|
|
95
123
|
|
|
96
|
-
|
|
124
|
+
### Passive vs Active Scan Taxonomy & Severity Levels
|
|
97
125
|
|
|
98
126
|
> *Adapted from the OWASP ZAP scanning model (Apache-2.0, zaproxy/zaproxy).*
|
|
99
127
|
|
|
@@ -117,8 +145,24 @@ Rules:
|
|
|
117
145
|
|
|
118
146
|
---
|
|
119
147
|
|
|
120
|
-
|
|
148
|
+
### AI, LLM & Agentic Security Hardening (Cloudflare Defense Pattern)
|
|
121
149
|
|
|
122
150
|
For systems with integrated LLMs, tool-calling agents, or MCP servers, inspect:
|
|
123
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.
|
|
124
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.
|
|
@@ -10,12 +10,36 @@ policies:
|
|
|
10
10
|
---
|
|
11
11
|
# SkillSpector Security Guard — AI Agent & MCP Security Sentinel
|
|
12
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
|
+
|
|
13
37
|
> **Purpose:** Autonomous security vetting for AI Agent skills, prompt instructions, Model Context Protocol (MCP) servers, and automation tools.
|
|
14
38
|
> **Heritage:** Inspired by and adapted from **[NVIDIA/SkillSpector](https://github.com/NVIDIA/SkillSpector)** (Apache 2.0).
|
|
15
39
|
|
|
16
40
|
---
|
|
17
41
|
|
|
18
|
-
|
|
42
|
+
### Core Threat Vectors
|
|
19
43
|
|
|
20
44
|
AI agent skills execute with terminal and workspace permissions. Unvetted third-party skills can introduce severe risks:
|
|
21
45
|
- **Prompt Injection:** Overriding core safety instructions or forcing jailbreaks.
|
|
@@ -26,7 +50,7 @@ AI agent skills execute with terminal and workspace permissions. Unvetted third-
|
|
|
26
50
|
|
|
27
51
|
---
|
|
28
52
|
|
|
29
|
-
|
|
53
|
+
### Threat Vector Categories
|
|
30
54
|
|
|
31
55
|
| Category | Description | Severity |
|
|
32
56
|
| :--- | :--- | :--- |
|
|
@@ -39,7 +63,7 @@ AI agent skills execute with terminal and workspace permissions. Unvetted third-
|
|
|
39
63
|
|
|
40
64
|
---
|
|
41
65
|
|
|
42
|
-
|
|
66
|
+
### Defense Guard & Prohibition Context
|
|
43
67
|
|
|
44
68
|
To prevent false alarms in educational documentation (e.g. *"Never run sudo"*):
|
|
45
69
|
1. **Negative Imperatives:** Matches preceded by negations (`never`, `do not`, `avoid`, `forbidden`) are recognized as defensive rules.
|
|
@@ -48,8 +72,9 @@ To prevent false alarms in educational documentation (e.g. *"Never run sudo"*):
|
|
|
48
72
|
|
|
49
73
|
---
|
|
50
74
|
|
|
51
|
-
|
|
75
|
+
### CLI Audit Commands
|
|
52
76
|
|
|
77
|
+
<!-- classification: illustrative -->
|
|
53
78
|
```bash
|
|
54
79
|
# Scan a specific candidate skill or file
|
|
55
80
|
synapse skillspector path/to/SKILL.md
|
|
@@ -60,3 +85,19 @@ synapse skillspector --scan-skills
|
|
|
60
85
|
# Fail CI pipeline if high or critical risks are detected
|
|
61
86
|
synapse skillspector --scan-skills --strict
|
|
62
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.
|
|
@@ -10,11 +10,35 @@ policies:
|
|
|
10
10
|
---
|
|
11
11
|
# WCAG 2.2 Accessibility Audit Patterns
|
|
12
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
|
+
|
|
13
37
|
Engineering standards for automated, continuous Web Content Accessibility Guidelines (WCAG 2.2 Level A and AA) auditing across enterprise web applications.
|
|
14
38
|
|
|
15
39
|
---
|
|
16
40
|
|
|
17
|
-
|
|
41
|
+
### Core WCAG 2.2 Success Criteria Matrix
|
|
18
42
|
|
|
19
43
|
| Criterion | Rule Code | Level | Requirement & Automated Assertion |
|
|
20
44
|
| :--- | :--- | :--- | :--- |
|
|
@@ -32,9 +56,10 @@ Engineering standards for automated, continuous Web Content Accessibility Guidel
|
|
|
32
56
|
|
|
33
57
|
---
|
|
34
58
|
|
|
35
|
-
|
|
59
|
+
### Playwright Automated Accessibility Testing Patterns
|
|
36
60
|
|
|
37
61
|
### Pattern A: Integrating `@axe-core/playwright` for Comprehensive Audits
|
|
62
|
+
<!-- classification: illustrative -->
|
|
38
63
|
```typescript
|
|
39
64
|
import { test, expect } from '@playwright/test';
|
|
40
65
|
import AxeBuilder from '@axe-core/playwright';
|
|
@@ -53,6 +78,7 @@ test('verify WCAG 2.2 Level AA compliance on dashboard', async ({ page }) => {
|
|
|
53
78
|
```
|
|
54
79
|
|
|
55
80
|
### Pattern B: Modal Keyboard Focus Trap and Escape Verification
|
|
81
|
+
<!-- classification: illustrative -->
|
|
56
82
|
```typescript
|
|
57
83
|
test('modal dialog traps keyboard focus and closes on Escape', async ({ page }) => {
|
|
58
84
|
await page.goto('/settings');
|
|
@@ -72,6 +98,7 @@ test('modal dialog traps keyboard focus and closes on Escape', async ({ page })
|
|
|
72
98
|
```
|
|
73
99
|
|
|
74
100
|
### Pattern C: WCAG 2.5.8 Target Size ($24 \times 24\text{px}$) Assertion
|
|
101
|
+
<!-- classification: illustrative -->
|
|
75
102
|
```typescript
|
|
76
103
|
test('all interactive buttons satisfy WCAG 2.5.8 24x24px target size', async ({ page }) => {
|
|
77
104
|
await page.goto('/checkout');
|
|
@@ -93,6 +120,7 @@ test('all interactive buttons satisfy WCAG 2.5.8 24x24px target size', async ({
|
|
|
93
120
|
```
|
|
94
121
|
|
|
95
122
|
### Pattern D: Playwright Native Accessibility Object Model (AOM) Snapshot
|
|
123
|
+
<!-- classification: illustrative -->
|
|
96
124
|
```python
|
|
97
125
|
# Python Playwright AOM Snapshot Assertion
|
|
98
126
|
def test_accessible_tree_structure(page):
|
|
@@ -105,10 +133,11 @@ def test_accessible_tree_structure(page):
|
|
|
105
133
|
|
|
106
134
|
---
|
|
107
135
|
|
|
108
|
-
|
|
136
|
+
### Automated CLI Auditing via Tooling
|
|
109
137
|
|
|
110
138
|
Synapse Hub provides automated accessibility auditing via `tools/wcag_audit.py`:
|
|
111
139
|
|
|
140
|
+
<!-- classification: illustrative -->
|
|
112
141
|
```bash
|
|
113
142
|
# Audit a local HTML snapshot or directory
|
|
114
143
|
python tools/wcag_audit.py path/to/page.html -o docs/wcag_audit_report.md
|
|
@@ -119,3 +148,19 @@ python tools/wcag_audit.py https://staging.example.com --url -o docs/wcag_audit_
|
|
|
119
148
|
# CLI integration via agent-qa
|
|
120
149
|
agent-qa wcag-audit path/to/page.html
|
|
121
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.
|
|
@@ -10,12 +10,36 @@ policies:
|
|
|
10
10
|
---
|
|
11
11
|
# Agentless QA Repair Skill — Ultra-Low-Token 3-Phase Failure Healing
|
|
12
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
|
+
|
|
13
37
|
> **Paradigm Attribution:** Inspired by **UIUC OpenAutoCoder Agentless**.
|
|
14
|
-
> **Core Principle:** The best fix is the smallest working diff without round-trip chat loops.
|
|
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.
|
|
15
39
|
|
|
16
40
|
---
|
|
17
41
|
|
|
18
|
-
|
|
42
|
+
### The 3-Phase Deterministic Pipeline
|
|
19
43
|
|
|
20
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:
|
|
21
45
|
|
|
@@ -44,10 +68,11 @@ flowchart LR
|
|
|
44
68
|
|
|
45
69
|
---
|
|
46
70
|
|
|
47
|
-
|
|
71
|
+
### CLI Tool Usage
|
|
48
72
|
|
|
49
73
|
Autonomous trigger via `tools/agentless_patcher.py`:
|
|
50
74
|
|
|
75
|
+
<!-- classification: illustrative -->
|
|
51
76
|
```bash
|
|
52
77
|
# End-to-end 3-stage healing
|
|
53
78
|
python tools/agentless_patcher.py heal-failure \
|
|
@@ -67,8 +92,24 @@ python tools/agentless_patcher.py generate-candidates \
|
|
|
67
92
|
|
|
68
93
|
---
|
|
69
94
|
|
|
70
|
-
|
|
95
|
+
### Strict Operating Invariants
|
|
71
96
|
|
|
72
97
|
- **Token Budget Ceiling:** Must stay under **2,500 tokens** per repair cycle.
|
|
73
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`.
|
|
74
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.
|
|
@@ -10,11 +10,35 @@ policies:
|
|
|
10
10
|
---
|
|
11
11
|
# Antigravity Test Sentinel — Verification-First Gatekeeper
|
|
12
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
|
+
|
|
13
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.
|
|
14
38
|
|
|
15
39
|
---
|
|
16
40
|
|
|
17
|
-
|
|
41
|
+
### The Sentinel Axiom (Zero-Hallucination Gate)
|
|
18
42
|
|
|
19
43
|
1. **The Core Rule:**
|
|
20
44
|
- Writing code is NOT completing the task.
|
|
@@ -28,7 +52,7 @@ The **Antigravity Test Sentinel** enforces absolute engineering integrity across
|
|
|
28
52
|
|
|
29
53
|
---
|
|
30
54
|
|
|
31
|
-
|
|
55
|
+
### Gate-Lock Protocol
|
|
32
56
|
|
|
33
57
|
Whenever an Agent modifies any test script, Page Class, locator, or helper method:
|
|
34
58
|
|
|
@@ -45,9 +69,10 @@ flowchart TD
|
|
|
45
69
|
|
|
46
70
|
1. **Step 1: Execute Runner Command:**
|
|
47
71
|
- Run the targeted test case or test suite via headless CLI runner or verification gate:
|
|
48
|
-
|
|
72
|
+
<!-- classification: illustrative -->
|
|
73
|
+
```bash
|
|
49
74
|
synapse verify
|
|
50
|
-
|
|
75
|
+
```
|
|
51
76
|
2. **Step 2: Inspect Exit Code:**
|
|
52
77
|
- If the process terminates with exit code != 0, the task is **LOCKED**.
|
|
53
78
|
- The Agent must not ask the user for confirmation or declare success.
|
|
@@ -59,10 +84,27 @@ flowchart TD
|
|
|
59
84
|
|
|
60
85
|
---
|
|
61
86
|
|
|
62
|
-
|
|
87
|
+
### Sentinel Status Header
|
|
63
88
|
|
|
64
89
|
In accordance with Antigravity operating discipline, include the sentinel verification status in the session summary:
|
|
65
90
|
|
|
91
|
+
<!-- classification: illustrative -->
|
|
66
92
|
```text
|
|
67
93
|
> 🛡️ SENTINEL STATUS: VERIFIED (Exit Code: 0 | 10/10 Gates PASS)
|
|
68
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.
|
|
@@ -10,11 +10,35 @@ policies:
|
|
|
10
10
|
---
|
|
11
11
|
# Failure Autopsy & Auto-Healing (Diagnostic & Self-Healing Engine)
|
|
12
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:** Triage test failures from JUnit XML/screenshots and heal broken Page Class locators. Use when diagnosing failed test runs and producing closed-loop healing plans.
|
|
20
|
+
- **Activation Scope:** Domain workflows for `06-healing-and-resilience` involving `failure-autopsy-and-healing`.
|
|
21
|
+
|
|
22
|
+
---
|
|
23
|
+
|
|
24
|
+
## 2. Non-Goals & Boundary Constraints
|
|
25
|
+
|
|
26
|
+
- **What NOT to do:**
|
|
27
|
+
- Do NOT attempt locator healing without inspecting live DOM or accessibility tree states.
|
|
28
|
+
- Do NOT inject brittle positional XPaths as healed locators.
|
|
29
|
+
- Do NOT mask underlying application bugs as locator failures.
|
|
30
|
+
- **Sibling Skill Boundaries:**
|
|
31
|
+
- agentless-qa-repair executes rapid minimal diff patching; failure-autopsy-and-healing conducts comprehensive failure analysis and AOM locator healing.
|
|
32
|
+
|
|
33
|
+
---
|
|
34
|
+
|
|
35
|
+
## 3. Ordered Execution Workflow
|
|
36
|
+
|
|
13
37
|
Specialized skill for diagnosing batch test execution failures across automated test cases, performing visual autopsies via `Screenshots/FAILED_*.png`, parsing `JUnit_Report.xml`, and healing Page Classes (`Keywords/<namespace>/pages/*.groovy` or `pages/*.ts`) in place.
|
|
14
38
|
|
|
15
39
|
---
|
|
16
40
|
|
|
17
|
-
|
|
41
|
+
### Five-Step Enterprise Autopsy Protocol
|
|
18
42
|
|
|
19
43
|
```mermaid
|
|
20
44
|
flowchart LR
|
|
@@ -25,10 +49,11 @@ flowchart LR
|
|
|
25
49
|
```
|
|
26
50
|
|
|
27
51
|
1. **Zero-Token Triage:** Pinpoint failed line and cause instantly (<50 tokens):
|
|
28
|
-
|
|
52
|
+
<!-- classification: illustrative -->
|
|
53
|
+
```bash
|
|
29
54
|
python tools/pinpoint_failure.py
|
|
30
55
|
# or bash .agents/skills/failure-autopsy-and-healing/scripts/triage_failures.sh
|
|
31
|
-
|
|
56
|
+
```
|
|
32
57
|
2. **Visual Autopsy:** Inspect the latest error screenshot to immediately detect: disabled buttons, missing required fields, UI overlaps, or obscuring modal backdrops.
|
|
33
58
|
3. **XML Parsing:** Extract stacktrace and exception messages from `Reports/<Timestamp>/JUnit_Report.xml` or Playwright test results.
|
|
34
59
|
4. **In-Place Healing:** Update the corresponding Page Class in `Keywords/<project_namespace>/pages/` or `pages/`.
|
|
@@ -36,7 +61,7 @@ flowchart LR
|
|
|
36
61
|
|
|
37
62
|
---
|
|
38
63
|
|
|
39
|
-
|
|
64
|
+
### Dynamic Module & Page Class Mapping Architecture
|
|
40
65
|
|
|
41
66
|
| Functional Module Category | Target Page Class to Heal | Common Failure Vector | Recommended Auto-Heal Strategy |
|
|
42
67
|
| :--- | :--- | :--- | :--- |
|
|
@@ -50,15 +75,15 @@ flowchart LR
|
|
|
50
75
|
|
|
51
76
|
---
|
|
52
77
|
|
|
53
|
-
|
|
78
|
+
### Reference Documentation
|
|
54
79
|
|
|
55
80
|
- [**Diagnostic & Healing Matrix (`healing_matrix.md`)**](references/healing_matrix.md): Concrete code prescriptions for disabled buttons, boundary overlaps, `ElementClickInterceptedException`, `StaleElementReferenceException`, and 4 flaky test root causes.
|
|
56
|
-
-
|
|
81
|
+
- **Fast-Fix Triad & Runtime Helper (`tools/browser_helpers.js`):** In-browser diagnosis engine via `window.__qa` (`audit`, `heal`, `clickSafe`, `hud`).
|
|
57
82
|
- **Automated Triage Script:** `python tools/pinpoint_failure.py` and `scripts/triage_failures.sh`.
|
|
58
83
|
|
|
59
84
|
---
|
|
60
85
|
|
|
61
|
-
|
|
86
|
+
### Boundary vs `self-healing-locator` (Do Not Confuse)
|
|
62
87
|
|
|
63
88
|
- **This skill** = the general physician: accepts ANY failed test run, performs
|
|
64
89
|
root-cause analysis (JUnit XML, logs, screenshots), queries the memory cache,
|
|
@@ -69,3 +94,19 @@ flowchart LR
|
|
|
69
94
|
this skill's plan when the RCA concludes "locator drift".
|
|
70
95
|
- Rule of thumb: if the failure reason is not yet known, start here; only after
|
|
71
96
|
the RCA says "locator broke" hand the repair to `self-healing-locator`.
|
|
97
|
+
|
|
98
|
+
---
|
|
99
|
+
|
|
100
|
+
## 4. Verification Points & DoD
|
|
101
|
+
|
|
102
|
+
1. Failure autopsy categorizes failure root cause (AUT defect vs Locator drift vs Environment).
|
|
103
|
+
2. Healed locators conform to 6-tier locator hierarchy and Clean POM standards.
|
|
104
|
+
3. Healed tests pass dynamic verification runs.
|
|
105
|
+
|
|
106
|
+
---
|
|
107
|
+
|
|
108
|
+
## 5. Handoff Protocol
|
|
109
|
+
|
|
110
|
+
- **Deliverables:** Failure autopsy report, healed Page Class selectors, and verification run logs.
|
|
111
|
+
- **Next Subagent:** failure-analyst
|
|
112
|
+
- **Output Format:** Clean POM code, structured JSON telemetry, or validated markdown handoff.
|