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/ui5/plugins-coding-agents/modernize-test-starternpx skills add UI5/plugins-coding-agents --skill modernize-test-startergit clone --depth 1 https://github.com/UI5/plugins-coding-agentsWhat 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 | $0.00244 | $0.04844 |
| Opus 5 | $0.00122 | $0.02422 |
| Sonnet 5 | $0.00049 | $0.00969 |
| Haiku 4.5 | $0.00024 | $0.00484 |
Grade A, and why
modernize-test-starter 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 2d 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modernize to Test Starter
This skill modernizes a UI5 project's entire test infrastructure — both unit tests and OPA5 integration tests — to the Test Starter concept.
Reference: Blog post: Simplify Your Test Setup
Why Modernize
The Test Starter replaces per-test HTML bootstrapping with a single generic test page and a declarative testsuite.qunit.js configuration. Benefits: eliminates boilerplate HTML/JS, handles QUnit/Sinon/coverage setup automatically, ensures CSP compliance, provides consistent configuration, enables per-test isolation and parallel execution.
NEVER Skip Test Starter Modernization
OPA5 test HTML files are ALWAYS convertible — they follow a mechanical pattern. Invalid excuses: "complex mock server" (lives in host, not entry point), "sap.ui.define monkey-patching" (same), "FLP sandbox bootstrap" (same), "too many files" (batch-process), "too complex" (invalid).
| Type | Example | Action |
|---|---|---|
| Test Driver | opa/<Area>/<TestName>.qunit.html |
CONVERT to Test Starter |
| Test Host | test<ServiceName>.html |
KEEP AS-IS (app-under-test in iframe) |
| Test Suite | testsuite.qunit.html |
REPLACE with testsuite.qunit.js |
| Dev Sandbox | flpSandbox.html |
IGNORE |
The only real technical challenge: OPA5 entry points may use jQuery.sap.require() for QUnit bootstrap libs — replace with sap.ui.require or note that Test Starter loads them automatically.
Pre-requisites
Read manifest.json → sap.app/id. This is your namespace:
<NAMESPACE>— dots → slashes (e.g.,my.app→my/app)<NAMESPACE-WITH-DOTS>— raw value with dots
Phase 0: Detection
0.1 Check for unit tests
Look for webapp/test/unit/ containing unitTests.qunit.html, unitTests.qunit.js, allTests.js, AllTests.js, or allTests.qunit.js. Identify all legacy aggregator files — JS files whose only purpose is loading other test modules via sap.ui.require/sap.ui.define with no actual test logic (QUnit.module, QUnit.test, assert.*). Their contents will be inlined into unitTests.qunit.js and the files deleted.
What ships with it
11 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.
- references/linter-invisible-patterns.md 791 B
- references/pattern-a-modernization.md 6.8 KB
- references/pattern-b-modernization.md 9.2 KB
- references/pattern-u-iframe-migration.md 28 KB
- references/testsuite-configuration.md 8.2 KB
- scripts/check-dangling-entries.js 9.5 KB runs code
- scripts/check-dangling-entries.test.js 7.1 KB runs code
- scripts/detect-cross-window-imports.js 11 KB runs code
- scripts/detect-cross-window-imports.test.js 8.6 KB runs code
- scripts/parse-testsuite.js 25 KB runs code
- scripts/parse-testsuite.test.js 14 KB runs code
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.
- 2d ago First seen · 374 lines · 244 tokens per session scan A ab286f304a88
modernize-test-starter is a skill published in the GitHub repository UI5/plugins-coding-agents (34 stars, last pushed today), licensed Apache-2.0. It adds 244 tokens to every session and 4,844 once invoked, about $0.0012 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.
Other skills, from other repositories
plugin-init
初始化 Zhin.js 插件项目。Use when asked to create a new plugin, scaffold plugin structure, or set up a plugin project. 引导生成符合 Plugin Runtime 规范的目录结构、package.json、plugin.ts、约定能力目录和 README。.
plugin-publish
发布 Zhin.js 插件到 npm 和 Zhin 插件市场。Use when asked to publish a plugin, prepare for release, check publish readiness, or submit to the Zhin plugin marketplace. 引导完成发布前检查、版本管理和提交流程。.
plugin-develop
Implement Zhin.js plugin features with Plugin Runtime: defineCommand, defineAgentTool, middleware, pages. Use when asked to add a command, register a tool, wire cron, extend middleware, or build a console page. Triggers: 插件开发, add command, 加命令, 写插件功能, defineCommand.
wordpress-plugin-fundamentals
Modern WordPress plugin development with PHP 8.3+, OOP architecture, hooks system, database interactions, and Settings API.
view-chain-layout
The layout rules for a z2ui5clui5viewbuilder chain - one call per line, four spaces per tree level, the end( ) column, which factory( ) shape goes with which chain shape, blank lines, and the linter rule that checks them. Identical in abap2UI5, abap2UI5/samples, abap2UI5/samples-controls and abap2UI5/samples-stack.…
agent-development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…