A method for writing JSON probe scripts that drive the Eclipse development environment through its user interface. SWTBot is a testing tool for automating Eclipse workbench actions without writing Java for each test case.

Creating, updating, and running probes that open Eclipse views, click or type in controls, wait for results, check elements, and capture screenshots.

It makes repeatable end-to-end checks possible for visible Eclipse behavior, including interactions that ordinary code tests do not cover.

ui-action — Skill by microsoft

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 skills/microsoft/copilot-for-eclipse/ui-action

Any agent

npx skills add microsoft/copilot-for-eclipse --skill ui-action

Clone the repo

git clone --depth 1 https://github.com/microsoft/copilot-for-eclipse

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,142 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.

Model	Per session	Once invoked
Fable 5	$0.00057	$0.01142
Opus 5	$0.00028	$0.00571
Sonnet 5	$0.00011	$0.00228
Haiku 4.5	$0.00006	$0.00114

Measured 2d ago against content hash 09d822a5e774, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-action 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.

.github/skills/ui-action/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SWTBot Probe Scripts

Use this skill to create or update JSON probes for com.microsoft.copilot.eclipse.swtbot.test. Probes drive the workbench through SWTBot actions and run as Tycho tests; no Java is compiled per test case.

Quick start

Create one focused JSON script at com.microsoft.copilot.eclipse.swtbot.test/probe-scripts/<plan-slug>-<tc-id>.json.

Start by settling the workbench and opening the view under test:

[
  { "action": "waitForIdle" },
  { "action": "screenshot", "id": "01-startup" },
  { "action": "showView", "idRef": "com.microsoft.copilot.eclipse.ui.chat.ChatView" },
  { "action": "waitForIdle" },
  { "action": "screenshot", "id": "02-chat-open" }
]

Add user-level steps only, such as click, typeIn, clearElement, pressKey, invokeCommand, waitFor, waitForMethod, assertExists, screenshot, or dumpUi. Prefer widgetId locators for widgets the plugin owns.
Run from the repository root:
```
./mvnw clean verify -Dprobe.script=probe-scripts/<name>.json
```
Use root clean verify as the default. Tycho can reuse stale bundle jars when only the SWTBot module is run, making source edits appear ignored. Use xvfb-run -a on Linux headless.
Read com.microsoft.copilot.eclipse.swtbot.test/target/probe-results/results.json, workspace.log, screenshots/, and ui-dumps/.

If -Dprobe.script is unset, ProbeRunner skips itself so ordinary ./mvnw verify runs are unaffected.

Authoring workflow

Convert one scenario/test case into one probe. Split unrelated behaviors so each failure screenshot has one meaning.
Drive the UI the way a user does. invokeCommand is allowed for registered Eclipse command IDs; do not call OSGi services, private methods, or test-only shortcuts.
Pair screenshots with machine-checked assertions. Screenshots never fail a step; assertExists, waitFor, and waitForMethod decide pass/fail.
Wait for asynchronous UI state before acting. For chat, wait for the model-picker selected model before Send, then wait for user-turn and model-info-label.
When a locator fails, insert dumpUi before the failure and inspect ui-dumps/*.xml for widget class names and SWTBot widget IDs.
For unauthenticated chat probes, assert the "Sign in to GitHub" UI. Do not poll internal auth managers.

Read the full file on GitHub · 87 lines

Files

What ships with it

1 file 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.

REFERENCE.md 8.4 KB

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.

2d ago First seen · 87 lines · 57 tokens per session scan A 09d822a5e774

Subscribe to this mod's changes

ui-action is a skill published in the GitHub repository microsoft/copilot-for-eclipse (122 stars, last pushed 6d ago), licensed MIT. It adds 57 tokens to every session and 1,142 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.

Debugging Frontend Testing

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens