Borrowing it
Nothing to install: this file belongs to vanillagreencom/kendex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vanillagreencom/kendex/main/.agents/skills/xcode-run/SKILL.mdgit clone --depth 1 https://github.com/vanillagreencom/kendexWrote 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/vanillagreencom/kendex/xcode-run)<a href="https://agentmods.dev/skills/vanillagreencom/kendex/xcode-run"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/xcode-run/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/vanillagreencom/kendex/xcode-run"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/xcode-run.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 | $0.00028 | $0.00806 |
| Opus 5.5 | $0.00011 | $0.00322 |
| Sonnet 5.5 | $0.00006 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade C, and why
xcode-run scanned grade C with 1 finding 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 21d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- kendex:project-instructions:start --> 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.
Project Instructions
Problems with a kendex-owned skill go through kendex report; check ownership in the file first.
Xcode run
Install this skill in project scope and consent to its repository effects. kendex runs scripts/install.sh to add templates/mac-run.yml as .github/workflows/mac-run.yml. The installer preserves an existing workflow. Commit the workflow to the default branch so GitHub can dispatch it.
Consumer configuration
Edit the top-level env values in .github/workflows/mac-run.yml:
| Value | Meaning |
|---|---|
XCODE_SCHEME |
A shared Xcode scheme. Replace the App placeholder. |
XCODE_DESTINATION |
An Xcode destination available on macos-latest. Replace the example with a simulator supported by the selected Xcode. Screenshots require a concrete simulator, not a generic destination. |
The workflow runs xcodebuild from the repository root. A workspace, multiple projects or a project in a subdirectory needs the corresponding path or working directory in the installed workflow. The screenshot scheme must build one simulator application target. The workflow reads its app path and simulator identifier from xcodebuild -showBuildSettings -json. It reads the bundle identifier from the built app's Info.plist.
Dispatch
workflow_dispatch is the only trigger. Its only input is step:
step |
Operation |
|---|---|
build |
xcodebuild build. This is the default. |
test |
xcodebuild test. The scheme must have a test action. |
screenshots |
Boot the selected simulator, build, install and launch the app, then capture screenshots/launch.png. |
gh workflow run mac-run.yml -f step=build
gh workflow run mac-run.yml -f step=test
gh workflow run mac-run.yml -f step=screenshots
Screenshots capture the launch view after a short wait. They do not navigate the app or assert that its UI is ready.
What ships with it
2 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.
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.
- 21d ago Changed · -1 lines bc8314ac56a6
- 27d ago First seen · 75 lines · 28 tokens per session scan C 02fbfbfcfc3b
xcode-run is a skill published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 806 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other skills, from other repositories
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…
text-search
Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.
rp
Always read this skill when the user mentions "rp" or "repoprompt", or before accessing a repository outside the current RepoPrompt workspace. Covers workspace discovery, binding, root verification, and workspace hygiene.
peekie-attachments
Extract and list test attachments (screenshots, logs, blobs) from an Xcode .xcresult bundle via peekie attachments. Trigger when the user asks about attached files in a bundle — e.g. "extract failure screenshots from /tmp/Tests.xcresult to /tmp/out", "save attachments for a single test", "what's attached to my failing…
peekie-tests
Parse and format test results from an Xcode .xcresult bundle via peekie tests. Trigger when the user asks anything about test outcomes from a bundle — e.g. "did the tests pass in /tmp/Tests.xcresult?", "show me failing tests from this build", "what tests failed?", "which tests were skipped?", "give me a JSON list of…
peekie-coverage
Extract code coverage from an Xcode .xcresult bundle via peekie coverage. Trigger when the user asks about coverage from a bundle — e.g. "what's the coverage in /tmp/Tests.xcresult?", "coverage per module please", "covered vs total lines for each file", "give me overall coverage as a percentage I can print in CI", "is…