PACTS-based agentic quality engineering fleet: 11 specialized QE agents, sublinear coverage analysis, chaos/resilience testing, and TDD skills for Claude Code
- Stars
- 535
- Version
- v4
- Copies
- 0
Overview
Waxell rates it high risk: 50 findings, highest severity high.
- Highest severity
- high
- Findings
- 50
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the plugin's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked today
Result
High risk Waxell rates it high risk: 50 findings, highest severity high.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (50)
high · 50
- high
Tool Misuse: Tool Parameter Abuse
CHANGELOG.md:71 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
CHANGELOG.md:72 · skillspector:TM1
- high
Tool Misuse: Chaining Abuse
CHANGELOG.md:72 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
CHANGELOG.md:74 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
README.md:136 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
README.md:142 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
README.md:142 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
hooks/producers.ts:104 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
hooks/producers.ts:104 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
hooks/shell.ts:31 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
hooks/shell.ts:44 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
hooks/verbs.ts:40 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
hooks/verbs.ts:40 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/attacks.ts:33 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/attacks.ts:197 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/attacks.ts:197 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/attacks.ts:216 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/attacks.ts:334 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/attacks.ts:334 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/attacks.ts:349 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/attacks.ts:359 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/attacks.ts:359 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/attacks.ts:413 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/attacks.ts:413 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/benign.ts:84 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/benign.ts:139 · skillspector:TM2
- high
Tool Misuse: Chaining Abuse
tests/corpus/benign.ts:139 · skillspector:TM2
- high
Anti-Refusal: Anti-Refusal Statement
CHANGELOG.md:79 · skillspector:AR2
- high
Anti-Refusal: Anti-Refusal Statement
tests/mod.test.ts:222 · skillspector:AR2
- high
Tool Misuse: Tool Parameter Abuse
README.md:138 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
README.md:138 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
README.md:141 · skillspector:TM1
- high
Supply Chain: Obfuscated Code
README.md:142 · skillspector:SC3
- high
Supply Chain: Obfuscated Code
hooks/verbs.ts:97 · skillspector:SC3
- high
Tool Misuse: Tool Parameter Abuse
README.md:142 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
tests/corpus/attacks.ts:283 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
README.md:144 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
README.md:149 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
tests/corpus/attacks.ts:186 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
tests/mod.test.ts:188 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
tests/mod.test.ts:189 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
README.md:149 · skillspector:TM1
- high
Anti-Refusal: Anti-Refusal Statement
hooks/guard.ts:185 · skillspector:AR1
- high
Anti-Refusal: Anti-Refusal Statement
tests/mod.test.ts:232 · skillspector:AR1
- high
Privilege Escalation: Credential Access
hooks/producers.ts:22 · skillspector:PE3
- high
Tool Misuse: Tool Parameter Abuse
hooks/writers.ts:134 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
tests/corpus/attacks.ts:67 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
tests/corpus/attacks.ts:126 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
tests/corpus/attacks.ts:127 · skillspector:TM1
- high
Tool Misuse: Tool Parameter Abuse
tests/corpus/benign.ts:29 · skillspector:TM1
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v4 (3.15.22)2026-11-215 changed High risk
- v3 (3.15.21)2026-11-1911 changed High riskgot riskier
- v2 (3.15.20)2026-11-1613 changed Review findings
- v1 (3.15.18)2026-11-03 Review findings
Files
Files
95 files, 792 KB in total. Names only; open them on GitHub.
- .claude-plugin/plugin.json
- .gitignore
- .mcp.json
- CHANGELOG.md
- README.md
- agents/qe-chaos-engineer.md
- agents/qe-coverage-specialist.md
- agents/qe-flaky-hunter.md
- agents/qe-fleet-commander.md
- agents/qe-performance-tester.md
- agents/qe-quality-gate.md
- agents/qe-regression-analyzer.md
- agents/qe-requirements-validator.md
- agents/qe-security-scanner.md
- agents/qe-tdd-specialist.md
- agents/qe-test-architect.md
- commands/aqe-analyze.md
- commands/aqe-benchmark.md
- commands/aqe-chaos.md
- commands/aqe-costs.md
- commands/aqe-execute.md
- commands/aqe-fleet-status.md
- commands/aqe-generate.md
- commands/aqe-optimize.md
- commands/aqe-report.md
- docs/adrs/0001-agentic-qe-fleet-contract.md
- hooks/braces.ts
- hooks/command.ts
- hooks/commands.ts
- hooks/context.ts
- hooks/find.ts
- hooks/glob.ts
- hooks/guard.ts
- hooks/hooks.json
- hooks/options.ts
- hooks/paths.ts
- hooks/powershell.ts
- hooks/producers.ts
- hooks/psvars.ts
- hooks/register.ts
- hooks/ruflo-noun.d.ts
- hooks/scripts.ts
- hooks/shell.ts
- hooks/status.ts
- hooks/verbs.ts
- hooks/version.ts
- hooks/writers.ts
- scripts/smoke-mod.sh
- scripts/smoke.sh
- skills/chaos-engineering-resilience/SKILL.md
- skills/chaos-engineering-resilience/evals/chaos-engineering-resilience.yaml
- skills/chaos-engineering-resilience/schemas/output.json
- skills/chaos-engineering-resilience/scripts/validate-config.json
- skills/mutation-testing/SKILL.md
- skills/mutation-testing/config.json
- skills/mutation-testing/evals/mutation-testing.yaml
- skills/mutation-testing/references/mutation-operators.md
- skills/mutation-testing/schemas/output.json
- skills/mutation-testing/scripts/validate-config.json
- skills/mutation-testing/test-data/sample-output.json
- skills/qe-chaos-resilience/SKILL.md
- skills/qe-chaos-resilience/evals/qe-chaos-resilience.yaml
- skills/qe-chaos-resilience/schemas/output.json
- skills/qe-chaos-resilience/scripts/validate-config.json
- skills/qe-coverage-analysis/SKILL.md
- skills/qe-coverage-analysis/evals/qe-coverage-analysis.yaml
- skills/qe-coverage-analysis/schemas/output.json
- skills/qe-coverage-analysis/scripts/validate-config.json
- skills/qe-quality-assessment/SKILL.md
- skills/qe-quality-assessment/evals/qe-quality-assessment.yaml
- skills/qe-quality-assessment/schemas/output.json
- skills/qe-quality-assessment/scripts/validate-config.json
- skills/qe-test-execution/SKILL.md
- skills/qe-test-execution/evals/qe-test-execution.yaml
- skills/qe-test-execution/schemas/output.json
- skills/qe-test-execution/scripts/validate-config.json
- skills/qe-test-generation/SKILL.md
- skills/qe-test-generation/config.json
- skills/qe-test-generation/evals/qe-test-generation.yaml
- skills/qe-test-generation/schemas/output.json
- skills/qe-test-generation/scripts/validate-config.json
- skills/qe-test-generation/templates/test-scaffold-jest.md
- skills/risk-based-testing/SKILL.md
- skills/risk-based-testing/evals/risk-based-testing.yaml
- skills/risk-based-testing/schemas/output.json
- skills/risk-based-testing/scripts/validate-config.json
- skills/tdd-london-chicago/SKILL.md
- skills/tdd-london-chicago/schemas/output.json
- skills/tdd-london-chicago/scripts/validate-config.json
- tests/corpus.test.ts
- tests/corpus/attacks.ts
- tests/corpus/benign.ts
- tests/mod.test.ts
- tests/status-file.test.ts
- tsconfig.json
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More data & analytics skills and plugins
paper-figuresevoscientistUse this skill to produce standalone, publication-ready PNG graphics and reproducible matplotlib scripts from tabular data (CSVs or… Review findingsData & analyticsDocuments487
huashu-excelalchaincyf数据分析全流程:体检脏表、清洗、定口径、算指标、对账、出报告。处理 Excel/CSV/系统导出数据,做透视写公式,查两个数为什么对不上,判断一个数靠不靠谱时用。核心是让算出来的数字经得起追问。幻灯片和 PPT 交给 huashu-design。 Review findingsData & analyticsDesign476
data-analysislingzhi227Generate statistical analysis code with 4-round review. Select appropriate statistical tests, interpret results, and produce analysis… Review findingsData & analyticsResearch475
paddleocr-doc-parsingfreestyleflyAdvanced document parsing with PaddleOCR. Returns complete document structure including text, tables, formulas, charts, and layout… Review findingsData & analyticsDesign474