airi: Skill for Codex

.agents/skills/use-vishot-with-capacitor/SKILL.md

use-vishot-with-capacitor is a skill for Codex from moeru-ai/airi. It costs 54 tokens per session (876 once invoked), scanned A, original, MIT.

A set of Vishot instructions for capturing screens from Capacitor applications. Capacitor lets web applications run inside mobile app shells, called WebViews.

In plain words
What is it for?
Use it to capture routes and states in a Capacitor app across mobile sizes, orientations, themes, locales, and platform modes.
Why use it?
A mobile app's web page and its native device interface may need different kinds of evidence. These instructions capture the WebView at a chosen mobile size and add native evidence only when needed.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions Codex; $skill-name invocation.

This is moeru-ai/airi's own configuration. It tells Codex how to work on airi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything airi configures →

About the project

AIRI is a self-hosted virtual AI companion that gives an AI character a voice, visual presence, memory, and the ability to interact with games and coding activity. People use it as a personal digital companion on the web, macOS, or Windows, including for voice chat and gameplay. The catalogue add-ons provide workflows for working with the AIRI project.

moeru-ai/airi · 49,050 stars · on GitHub · airi.moeru.ai

Reuse

Borrowing it

Nothing to install: this file belongs to moeru-ai/airi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/moeru-ai/airi/main/.agents/skills/use-vishot-with-capacitor/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/moeru-ai/airi

Made for: Codex.

Wrote 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.

agentmods badge for use-vishot-with-capacitor

README.md
[![agentmods](https://agentmods.dev/badge/skills/moeru-ai/airi/use-vishot-with-capacitor/github.svg)](https://agentmods.dev/skills/moeru-ai/airi/use-vishot-with-capacitor)
Your own site
<a href="https://agentmods.dev/skills/moeru-ai/airi/use-vishot-with-capacitor"><img src="https://agentmods.dev/badge/skills/moeru-ai/airi/use-vishot-with-capacitor/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.

agentmods 80×15 button for use-vishot-with-capacitor

Your own site · 80×15
<a href="https://agentmods.dev/skills/moeru-ai/airi/use-vishot-with-capacitor"><img src="https://agentmods.dev/badge/skills/moeru-ai/airi/use-vishot-with-capacitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 876 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00876
Opus 5 $0.00027 $0.00438
Sonnet 5 $0.00011 $0.00175
Haiku 4.5 $0.00005 $0.00088

Measured 13d ago against content hash e00d0d7e7311, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

use-vishot-with-capacitor 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 13d 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.

.agents/skills/use-vishot-with-capacitor/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use Vishot with Capacitor

Capture the locally served WebView through Vishot by default. Add native evidence only when the requested state depends on native UI or platform behavior.

WebView Workflow

  1. Identify the route, state, platform mode, orientation, viewport, theme, locale, and output directory supplied by the caller.

  2. Ensure Vishot's Playwright Chromium runtime exists. If Vishot reports a missing executable, run pnpm exec playwright install chromium once and retry.

  3. Start the app's web development command. In AIRI, use VITE_SKIP_MKCERT=1 pnpm -F @proj-airi/stage-pocket dev:web for a local HTTP origin.

  4. Wait until the development server reports that it is listening, then let Vishot handle WebView reload stability with an explicit --settle-ms 2500. Vishot intentionally has no default delay because it serves projects with different readiness contracts.

  5. Capture the route at the requested mobile viewport:

    pnpm exec vishot render \
      --target browser \
      http://127.0.0.1:5273/settings \
      --width 390 \
      --height 844 \
      --settle-ms 2500 \
      --output-dir /absolute/output/settings
    
  6. Repeat for each requested state and viewport. Inspect each output before returning it.

  7. Return its stable ID, title, platform/viewport details, and absolute path to $use-vishot or the caller.

Scenario Readiness and Locators

  • Implement readiness for the specific route, viewport, platform mode, and UI state. Desktop text and controls may be hidden, renamed, or moved into mobile navigation, so do not reuse an expected string without inspecting the rendered mobile state.
  • Wait in this order: let Vishot establish URL and reload stability, confirm the final route, wait for a state-specific visible locator, confirm loading indicators, sheets, permission explanations, or startup overlays are resolved, then let Vishot keep its final settle window for remaining bundling, refresh, animation, or rendering.
  • Use text only when it is visible, unique, stable for the selected locale, and intrinsic to the intended state. Avoid generic headings, placeholders, network-derived values, and text that belongs only to another viewport or platform.
  • Prefer semantic locators such as getByRole('button', { name }) and getByLabel(). For an icon-only control, locate the owning button by its icon and click the button, not the icon node:

Read the full file on GitHub · 53 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.

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.

  1. 13d ago First seen · 53 lines · 54 tokens per session scan A e00d0d7e7311

Subscribe to this mod's changes

use-vishot-with-capacitor is a skill published in the GitHub repository moeru-ai/airi (49,050 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 876 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.

Related

Other skills, from other repositories

android_ui_verification

Automated end-to-end UI testing and verification on an Android Emulator using ADB.

sickn33/agentic-awesome-skills · 22 tokens

ios-simulator

Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.

callstack/agent-device · 69 tokens

solopi-ai

A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.

alipay/SoloPi · 127 tokens

eas-simulator

EAS service (paid). Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud. Read before running any eas simulator: commands - it has the current syntax for this experimental API. Use whenever the user needs a simulator they can't run locally - 'run my app on a cloud simulator', 'use eas…

expo/skills · 249 tokens

flutter-add-widget-test

Implement a component-level test using WidgetTester to verify UI rendering and user interactions (tapping, scrolling, entering text). Use when validating that a specific widget displays correct data and responds to events as expected.

flutter/agent-plugins · 48 tokens

test-native-extension

Validate a third-party control repo across four automated layers plus one printed manual recipe. Layer 1 asserts native-source structure (Android getName() and iOS +moduleName to manifest nativeModule; @ReactMethod / RCTEXPORTMETHOD to methods; no @ReactModule) plus load/init readiness (ReactPackage public no-arg…

microsoft/power-platform-skills · 211 tokens