Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PramodDutta/qaskillsnpx agentmods add skills/pramoddutta/qaskills/agentic-testingWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pramoddutta/qaskills/agentic-testing)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/agentic-testing"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/agentic-testing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pramoddutta/qaskills/agentic-testing"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/agentic-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 724 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- medium Excessive Agency · line 106 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 126 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 607 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What 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 5.1 | $0.00041 | $0.06121 |
| Opus 5.5 | $0.00016 | $0.02448 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (237 stars, last pushed 7d ago), licensed MIT. It adds 41 tokens to every session and 6,121 once invoked, about $0.0002 per session on Opus 5.5. 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
sorify-update
Update an existing Sorify test case with new Playwright code while preserving its code-version history.
muggle-test
Change-driven E2E acceptance testing: detects the user's recent changes (local diff or PR), maps them to affected user flows, and runs real-browser tests on localhost or a preview/staging URL. Invoke it before inspecting anything — what changed and what it affects is its own first step; reading the diff by hand…
muggle-test-import
Bring existing tests and test artifacts INTO Muggle Test — from Playwright, Cypress, PRDs, Gherkin feature files, test-plan docs, Notion exports, or any source. TRIGGER when the user wants to import, migrate, load, or convert existing test files or docs into Muggle Test — import my playwright tests, migrate from…
sorify-generate
Generate Playwright E2E tests from a target URL, optionally using a source repository, then upload and run them in Sorify.
sorify-recording
Turn a Sorify Recorder browser session into a Playwright test and upload it to Sorify.
sorify-shared-references
Apply Sorify's shared browser exploration, source analysis, test design, and Playwright generation guidance.