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 skills add TinusJ/swing-mcp --skill swing-ui-testinggit clone --depth 1 https://github.com/TinusJ/swing-mcpWrote 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/tinusj/swing-mcp/swing-ui-testing)<a href="https://agentmods.dev/skills/tinusj/swing-mcp/swing-ui-testing"><img src="https://agentmods.dev/badge/skills/tinusj/swing-mcp/swing-ui-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/tinusj/swing-mcp/swing-ui-testing"><img src="https://agentmods.dev/badge/skills/tinusj/swing-mcp/swing-ui-testing.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.01194 |
| Opus 5.5 | $0.00020 | $0.00478 |
| Sonnet 5.5 | $0.00010 | $0.00239 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
swing-ui-testing 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 2mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Concepts
Deterministic synchronisation: Never rely on sleeps. Use wait_for with an explicit condition (COMPONENT_TEXT, COMPONENT_VISIBLE, COMPONENT_ENABLED, COMPONENT_EXISTS, COMPONENT_GONE, WINDOW_TITLE, WINDOW_COUNT, EDT_IDLE) and a timeoutMs to make test steps deterministic.
Fresh snapshots: Component UIDs come from take_snapshot and can go stale after any action that changes the UI. Re-snapshot before asserting on state, and whenever an interaction fails to find a component.
Assert via the model, not pixels: Prefer get_component_details, get_table_data, and get_list_items for assertions — they read the actual Swing model state. Use take_screenshot only for visual verification.
Workflow Patterns
1. Test session setup and teardown
launch_appwith the application's full java command (useattach_to_apponly when the app must keep running after the test).wait_forwithWINDOW_TITLE(orWINDOW_COUNT) to ensure the main window is up before interacting.- Run the scenario steps.
stop_appto end the session, even on failure, so the launched JVM is cleaned up.
2. Form filling and validation
take_snapshot(optionallyfilter: "ENABLED_ONLY") to find input fields and buttons.filleach text field, spinner, or editable combo box; usetype_textwhen the form relies on key listeners or per-keystroke validation.select_optionfor combo boxes andclickfor checkboxes/radio buttons.- Submit with
clickon the confirm button, orpress_keywithENTER. - Verify:
wait_fora success condition, then check resulting state withget_component_details(e.g. an error label's text, or a button becoming enabled/disabled).
3. Tables, lists, and trees
- Verify data:
get_table_datawithstartRow/endRowto assert column names and cell values;get_list_itemsforJListitems or visibleJTreerows. - Select:
select_table_cell(row/col),select_option(index or visible text),select_tree_nodewith aRoot > Folder > Leafpath. - Row actions: after selecting, use
clickwithclickType: "DOUBLE"to open, orselect_context_menu_itemfor the row's context menu. - Long content:
scrollinside theJScrollPaneto reach off-screen rows before interacting via mouse emulation.
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.
- 2mo ago First seen · 74 lines · 51 tokens per session scan A 1bedc72f1c2b
swing-ui-testing is a skill published in the GitHub repository TinusJ/swing-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 1,194 once invoked, about $0.0002 per session on Opus 5.5. 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
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.