ios-simulator-browser
Skill4 starsChanged 4 months agoMITView on GitHub
Stream an explicit iOS Simulator through pinned serve-sim into the T3 Code in-app browser or another agent browser. Use on Apple Silicon macOS when the user should watch simulator verification live or when browser-visible simulator evidence is needed.
6 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- mohammadchehab/isnadibotedited, first seen Nov 15, 2026
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
- openai/pluginstheir own version, first seen Oct 13, 2026
- btsouth/toolport-studioword for word, first seen Jul 28, 2026
- tsouth89/toolport-studioword for word, first seen Jul 28, 2026
- robinebers/skillstheir own version, first seen Jun 25, 2026
Other versions6 projects use a version of this.
Word for word · 2
- btsouth/toolport-studio★ 4100% same
- tsouth89/toolport-studio★ 4100% same
Edited · 1
- mohammadchehab/isnadibot★ 281% same
Wrote their own version · 3
- openai/plugins★ 7.8ksame name
- robinebers/skills★ 48same name
- MMACABRE/SKILLS★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/cursor-cloud.mdcCursor rule
- ios-debugger-agentSkill
- test-t3-appSkill
- test-t3-mobileSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 7 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use serve-sim as the shared visual feed for an iOS Simulator.
- Distinctive: line 14
When running inside T3 Code, use its product-native browser MCP to open the stream.
- Very specific: line 16
Keep serve-sim on its default 127.0.0.1 binding.
- Distinctive: line 21
Check whether an existing serve-sim stream for that UDID belongs to another task.
- Distinctive: line 34
Keep the terminal alive and open the exact local URL printed by serve-sim in the agent's browser.
- Distinctive: line 35
Verify that a live simulator frame renders.
- Distinctive: line 40
Keep the browser and Xcode tooling pinned to the same simulator UDID.
- Distinctive: line 41
Do not switch to generic desktop automation or browser-canvas clicking merely because the stream is visible.
- Distinctive: line 43
If the in-app browser explicitly reports that previews are unavailable, do not install unrelated browser automation.
- Very specific: line 47
Stop the long-running terminal and wait for its cleanup trap to finish.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
iOS Simulator Browser
Use serve-sim as the shared visual feed for an iOS Simulator. Use ios-debugger-agent and XcodeBuildMCP semantic UI tools to drive the app; do not treat browser-canvas coordinates as a substitute for missing app accessibility.
Confirm availability
serve-sim 0.1.45 requires Apple Silicon macOS, Xcode command-line tools, and Node.js 20 or newer. If the host is unsupported, continue with XcodeBuildMCP screenshots and report that live streaming was unavailable.
When running inside T3 Code, use its product-native browser MCP to open the stream. Other agent hosts may use their own browser or preview surface.
Keep serve-sim on its default 127.0.0.1 binding. Do not expose its preview to a LAN or tunnel unless the user explicitly requests that access and the network is trusted; the preview includes a token-gated shell-execution route.
Start one owned stream
- Obtain the exact simulator UDID from the iOS build or launch workflow.
- Check whether an existing serve-sim stream for that UDID belongs to another task. Reuse it only when explicitly shared; never kill another task's stream.
Otherwise, clear only a stale stream for that UDID and start the pinned version with scoped cleanup:
SIMULATOR_ID=<simulator-udid> cleanup_serve_sim() { npx --yes serve-sim@0.1.45 --kill "$SIMULATOR_ID" >/dev/null 2>&1 || true } trap cleanup_serve_sim EXIT INT TERM HUP cleanup_serve_sim npx --yes serve-sim@0.1.45 "$SIMULATOR_ID"- Keep the terminal alive and open the exact local URL printed by serve-sim in the agent's browser.
- Verify that a live simulator frame renders. A loaded wrapper page is not sufficient evidence.
Observe while driving semantically
- Let the user watch the serve-sim stream while XcodeBuildMCP performs
snapshot_ui, semantic taps, typing, gestures, and screenshots. - Keep the browser and Xcode tooling pinned to the same simulator UDID.
- Do not switch to generic desktop automation or browser-canvas clicking merely because the stream is visible.
If the in-app browser explicitly reports that previews are unavailable, do not install unrelated browser automation. Continue through XcodeBuildMCP, capture a simulator screenshot, report the unavailable live stream, and clean up the owned serve-sim process.
Finish
Stop the long-running terminal and wait for its cleanup trap to finish. If it disappeared without cleanup, run npx --yes serve-sim@0.1.45 --kill <simulator-udid> for that exact simulator. Never run an unscoped --kill.
Upstream
Adapted from OpenAI's build-ios-apps plugin version 0.1.2 (ios-simulator-browser, MIT). It invokes serve-sim 0.1.45 under its Apache-2.0 license without vendoring the package.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

