Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/pramoddutta/qaskills/agentic-testingnpx skills add PramodDutta/qaskills --skill agentic-testinggit clone --depth 1 https://github.com/PramodDutta/qaskillsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.06121 |
| Opus 5 | $0.00020 | $0.03061 |
| Sonnet 5 | $0.00008 | $0.01224 |
| Haiku 4.5 | $0.00004 | $0.00612 |
Grade A, and why
Agentic Testing Patterns scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execSync } from 'child_process'; How it starts
The opening of the file, as written. The whole thing — 734 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Testing Patterns Skill
You are an expert in agentic testing methodology where AI agents autonomously plan, generate, execute, and maintain test suites. When the user asks you to implement agentic testing workflows, create autonomous test pipelines, or build AI-driven quality assurance systems, follow these detailed instructions.
Core Principles
- Agent autonomy with human oversight -- Agents should operate independently for routine tasks but escalate to humans for ambiguous requirements, security-sensitive tests, and novel failure patterns.
- Intent-driven test specification -- Tests are specified as high-level intents (what to verify) rather than step-by-step instructions. Agents determine the optimal implementation strategy.
- Continuous learning from failures -- Every test failure feeds back into the agent's knowledge base. Agents improve their test generation and maintenance strategies over time.
- Risk-based test prioritization -- Agents analyze code changes, historical failure data, and business impact to determine which tests to run and in what order.
- Multi-agent collaboration -- Different agents specialize in different tasks: one plans, one generates, one executes, one analyzes results. They communicate through structured protocols.
- Observable and auditable -- Every agent decision must be logged with reasoning. Humans must be able to trace why a test was generated, modified, or skipped.
- Graceful degradation -- When AI services are unavailable, the system falls back to deterministic test execution. Agent-generated tests must be valid standalone tests.
Project Structure
agentic-tests/
agents/
coordinator/
coordinator-agent.ts
task-queue.ts
priority-engine.ts
analyzer/
code-change-analyzer.ts
failure-pattern-detector.ts
coverage-gap-finder.ts
generator/
test-generator.ts
fixture-generator.ts
mock-generator.ts
executor/
test-runner.ts
parallel-executor.ts
result-collector.ts
reporter/
insight-generator.ts
trend-analyzer.ts
alert-system.ts
knowledge/
failure-patterns.json
selector-mappings.json
test-templates/
unit-template.ts
integration-template.ts
e2e-template.ts
pipelines/
ci-pipeline.ts
pr-review-pipeline.ts
nightly-pipeline.ts
deployment-pipeline.ts
config/
agent-config.ts
pipeline-config.ts
model-config.ts
tests/
agent-tests/
coordinator.test.ts
analyzer.test.ts
generator.test.ts
monitoring/
agent-metrics.ts
cost-dashboard.ts
quality-tracker.ts
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 734 lines · 41 tokens per session scan A a64aed95c3ae
Agentic Testing Patterns is a skill published in the GitHub repository PramodDutta/qaskills (214 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 6,121 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ui-automation
WHartTest UI 自动化管理工具。用于创建、编辑、删除 UI 测试模块、页面、元素、页面步骤和测试用例。支持执行记录查询和错误分析。当需要将浏览器技能获取到的页面元素保存到平台、创建 UI 自动化用例、执行测试或分析执行结果时使用。元素采集默认优先 browser-use，无法覆盖时再用 playwright-skill 兜底。.
api-automation
WHartTest 接口自动化管理工具。用于按真实后端接口管理接口模块、数据库配置、环境与变量、自定义函数、接口定义与调试、单接口用例 ApiInterfaceCase、场景用例 ApiTestCase、任务套件、执行报告与同步配置。当需要创建、查询、修改、执行 API 自动化资源，区分单接口测试和场景用例，或排查执行、同步、任务套件问题时使用。.
drawio
Generate draw.io diagrams as .drawio files, optionally export to PNG/SVG/PDF with embedded XML.
playwright-cli
基于微软官方 @playwright/cli 的交互式浏览器自动化技能。通过标准化命令行会话实现极高稳定性的浏览器操作，防止挂起超时。.
playwright-skill
浏览器自动化执行工具。用于执行 Web 页面测试、表单填写、登录验证、截图等浏览器操作。.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.