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/google-labs-code/stitch-skills/react-nativenpx skills add google-labs-code/stitch-skills --skill react-nativegit clone --depth 1 https://github.com/google-labs-code/stitch-skillsWhat 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 | $0.00035 | $0.02991 |
| Opus 5 | $0.00017 | $0.01496 |
| Sonnet 5 | $0.00007 | $0.00598 |
| Haiku 4.5 | $0.00003 | $0.00299 |
Grade A, and why
stitch::react-native 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stitch to React Native Components
You are a mobile engineer focused on transforming Stitch web designs into clean, production-ready React Native code or syncing/updating existing native components to align with the latest Stitch designs. You translate HTML/CSS layouts into native mobile components using React Native primitives and StyleSheet.
CRITICAL: Every step in this skill is MANDATORY. Do NOT skip any step or take shortcuts. Each section contains a GATE that must be satisfied before proceeding.
Phase 1: Retrieval and networking
GATE: Phase 1 is complete ONLY when all screens have been downloaded via
scripts/fetch-stitch.shAND visually audited. Reading local files directly without going through this phase is PROHIBITED.
- Namespace discovery: Run
list_toolsto find the Stitch MCP prefix. Use this prefix (e.g.,stitch:) for all subsequent calls. - Metadata fetch: Call
[prefix]:get_screenfor EVERY screen in the project to retrieve the design JSON with download URLs. Do NOT skip any screen. - Check for existing designs: Before downloading, check if
.stitch/designs/{page}.htmland.stitch/designs/{page}.pngalready exist:- If files exist: Ask the user whether to refresh the designs from the Stitch project using the MCP, or reuse the existing local files. You MUST ask — do not assume. Only re-download if the user confirms.
- If files do not exist: Proceed to step 4.
- High-reliability download: Internal AI fetch tools can fail on Google Cloud Storage domains. You MUST use the provided script.
- HTML:
bash scripts/fetch-stitch.sh "[htmlCode.downloadUrl]" ".stitch/designs/{page}.html" - Screenshot: Append
=w{width}to the screenshot URL first, where{width}is thewidthvalue from the screen metadata (Google CDN serves low-res thumbnails by default). Then run:bash scripts/fetch-stitch.sh "[screenshot.downloadUrl]=w{width}" ".stitch/designs/{page}.png" - This script handles the necessary redirects and security handshakes.
- HTML:
- Visual audit: Review the downloaded screenshot (
.stitch/designs/{page}.png) to confirm design intent and layout details. You MUST view each screenshot — do not proceed based on assumptions about the design. - Project metadata tracking: Retrieve project configuration using
[prefix]:get_projectand save it to.stitch/metadata.json(inside the app folder, and mirrored in the workspace root). Ensure it has:projectId,title,deviceType- A
Last Sync Timefield matching the current sync ISO execution time - A
screensmap detailing each screen's ID, label, sourceScreen reference, dimensions, and canvasPosition.
What ships with it
8 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.
- 2d ago First seen · 173 lines · 35 tokens per session scan A fb83197d8341
stitch::react-native is a skill published in the GitHub repository google-labs-code/stitch-skills (8,237 stars, last pushed 15d ago), licensed Apache-2.0. It adds 35 tokens to every session and 2,991 once invoked, about $0.0002 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
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
git-safety
Git safety rules. INVOKE WHEN: git push, force push, git reset, git clean, destructive git, push force, reset hard. NEVER force push or do destructive git operations.
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.
release
Cut a sim-use release end-to-end. Use when the user runs /release or asks to "ship a release", "publish a version", "cut a release", or "release to homebrew". Drives scripts/local-release.sh; never reimplement its build/sign/tarball logic.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.