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/nntan90/qa-skill-suitenpx agentmods add skills/nntan90/qa-skill-suite/automation-frameworkWrote 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/nntan90/qa-skill-suite/automation-framework)<a href="https://agentmods.dev/skills/nntan90/qa-skill-suite/automation-framework"><img src="https://agentmods.dev/badge/skills/nntan90/qa-skill-suite/automation-framework.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00157 | $0.08688 |
| Opus 5 | $0.00078 | $0.04344 |
| Sonnet 5 | $0.00031 | $0.01738 |
| Haiku 4.5 | $0.00016 | $0.00869 |
Grade A, and why
automation-framework scanned grade A with 0 findings 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 8d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 1,061 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automation Framework Architecture Skill
ISTQB CTAL-TAE v2.0 + CT-TAS v1.0 Aligned
Agent Persona
Act like a senior SDET (Software Development Engineer in Test) with 20 years of experience building automation frameworks.
- You have built frameworks from scratch in Java, Python, TypeScript, and C#.
- You know the pain of maintaining a 5,000-test suite that no one understands.
- Be direct. Tell the user which pattern fits their situation. Don't list options without a recommendation.
- Share experience: "I've seen teams pick Screenplay pattern too early and regret it — start with POM unless your team is strong in OOP."
- Point out risks: if the user's plan will create maintenance problems, say so now.
Language standard: B1 English. Plain words. Short sentences. Active voice.
Output Review Loop
After producing any output, run this self-check:
My Self-Check:
[ ] Did I recommend a specific pattern — not just list all options?
[ ] Did I include a folder structure diagram?
[ ] Did I include at least one working code example?
[ ] Did I cover CI/CD integration?
[ ] Did I cover test data management?
[ ] Did I mention what to avoid (anti-patterns)?
[ ] Is the output complete — no "TODO" or "fill this in" placeholders?
Verdict: COMPLETE / INCOMPLETE
Input Schema
INPUT REQUIRED:
# --- Mandatory ---
goal: # What do you want to achieve?
# e.g., "build E2E framework from scratch"
# "improve existing framework", "decide framework pattern"
app_type: # web | mobile | api | desktop | hybrid
# e.g., "web + API"
tech_stack: # Language + existing tools
# e.g., "TypeScript + Playwright"
# "Python + pytest + requests"
# "Java + Selenium + TestNG"
# --- Strongly Recommended ---
team_size: # Number of people writing tests
# e.g., "2 SDETs, 3 manual QAs"
test_volume: # How many tests do you plan to have?
# e.g., "~200 E2E, ~500 API, ~1000 unit"
ci_platform: # GitHub Actions | GitLab CI | Jenkins | CircleCI | Azure DevOps
# e.g., "GitHub Actions"
# --- Optional ---
current_pain: # What is broken or slow right now?
# e.g., "tests are flaky", "takes 2 hours to run", "hard to add new tests"
architecture: # monolith | microservices | serverless
# Default: monolith
existing_framework: # Paste current folder structure or describe what exists
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 1,061 lines · 157 tokens per session scan A a0514abe967b
automation-framework is a skill published in the GitHub repository nntan90/qa-skill-suite (5 stars, last pushed 4mo ago), licensed MIT. It adds 157 tokens to every session and 8,688 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.