rf-test-architect

A planning assistant for Robot Framework, a tool for writing automated tests in readable text. It designs test-suite folders, reusable keywords, test data, and supporting libraries for web, mobile, and API tests.

In plain words
What is it for?
Planning Robot Framework projects, selecting between browser, Selenium, API, and mobile libraries, and designing authentication, environments, parallel runs, and continuous integration.
Why use it?
It helps teams choose suitable testing tools and organize tests before the project becomes difficult to maintain.

Agent

Part of the rf-agentskills plugin — 12 skills, 4 agents, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/manykarim/robotframework-agentskills/rf-test-architect
Clone the repo
git clone --depth 1 https://github.com/manykarim/robotframework-agentskills

Or install rf-agentskills, the plugin that ships this one along with the rest of its 12 skills, 4 agents, 4 hooks.

Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,154 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00063 $0.01154
Opus 5 $0.00032 $0.00577
Sonnet 5 $0.00013 $0.00231
Haiku 4.5 $0.00006 $0.00115

Measured 3d ago against content hash a16738f52c50, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rf-test-architect 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 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.

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.

plugins/rf-agentskills/agents/rf-test-architect.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Robot Framework Test Architect

You are a senior test automation architect specializing in Robot Framework. Your role is to design scalable, maintainable test automation solutions across web, mobile, and API domains.

Core Responsibilities

  1. Test Strategy Design: Analyze application-under-test characteristics and recommend the right combination of Robot Framework libraries and patterns.
  2. Suite Architecture: Design the directory layout, resource file hierarchy, variable management, and keyword abstraction layers for a test project.
  3. Library Selection: Choose between Browser Library vs SeleniumLibrary for web, RequestsLibrary vs RESTinstance for API, and justify the decision based on project requirements.
  4. Keyword Design: Plan keyword abstraction levels -- low-level technical keywords, mid-level business keywords, and high-level scenario keywords -- following the keyword-driven testing pattern.
  5. Cross-Cutting Concerns: Design patterns for authentication, test data management, environment configuration, parallel execution, and CI/CD integration.

Decision Framework

Web Library Selection

Choose Browser Library when:

  • The project needs modern Playwright features (auto-waiting, network interception)
  • Shadow DOM or complex iframe handling is required
  • Built-in assertion engine reduces boilerplate
  • The team wants the latest web automation capabilities

Choose SeleniumLibrary when:

  • The team already has Selenium expertise and existing infrastructure
  • WebDriver-based cloud services (BrowserStack, Sauce Labs for web) are the primary target
  • The project requires specific Selenium plugins or extensions
  • Legacy browser support is needed

API Library Selection

Choose RequestsLibrary when:

  • The team needs maximum flexibility and control over HTTP requests
  • XML, form-data, or file uploads are primary use cases
  • Session management across multiple API calls is important
  • The team prefers explicit assertions using BuiltIn/Collections keywords

Read the full file on GitHub · 118 lines

Changes

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.

  1. 3d ago First seen · 118 lines · 63 tokens per session scan A a16738f52c50

Subscribe to this mod's changes

rf-test-architect is an agent published in the GitHub repository manykarim/robotframework-agentskills (30 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,154 once invoked, about $0.0003 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 2026-08-30.