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 skills add legendtkl/agentic-skill-router --skill skill-102git clone --depth 1 https://github.com/legendtkl/agentic-skill-routerWrote 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/legendtkl/agentic-skill-router/skill-102)<a href="https://agentmods.dev/skills/legendtkl/agentic-skill-router/skill-102"><img src="https://agentmods.dev/badge/skills/legendtkl/agentic-skill-router/skill-102/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/legendtkl/agentic-skill-router/skill-102"><img src="https://agentmods.dev/badge/skills/legendtkl/agentic-skill-router/skill-102.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 | $0.00079 | $0.01378 |
| Opus 5 | $0.00039 | $0.00689 |
| Sonnet 5 | $0.00016 | $0.00276 |
| Haiku 4.5 | $0.00008 | $0.00138 |
Grade A, and why
skill-102 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 7d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AXe iOS Simulator Automation
AXe is a single-binary CLI for iOS Simulator automation via Apple's Accessibility APIs and HID.
Installation
brew install cameroncooke/axe/axe
Quick Start
# Get simulator UDID
axe list-simulators
UDID="<simulator-udid>"
# Basic interactions
axe tap -x 100 -y 200 --udid $UDID
axe tap --label "Safari" --udid $UDID
axe type 'Hello World!' --udid $UDID
axe gesture scroll-down --udid $UDID
axe button home --udid $UDID
axe screenshot --udid $UDID
Touch & Gestures
# Tap at coordinates
axe tap -x 100 -y 200 --udid $UDID
# Tap by accessibility identifier or label
axe tap --id "myButton" --udid $UDID
axe tap --label "Submit" --udid $UDID
# With timing controls
axe tap -x 100 -y 200 --pre-delay 1.0 --post-delay 0.5 --udid $UDID
# Swipe
axe swipe --start-x 100 --start-y 300 --end-x 300 --end-y 100 --udid $UDID
axe swipe --start-x 50 --start-y 500 --end-x 350 --end-y 500 --duration 2.0 --delta 25 --udid $UDID
# Low-level touch control
axe touch -x 150 -y 250 --down --udid $UDID
axe touch -x 150 -y 250 --up --udid $UDID
axe touch -x 150 -y 250 --down --up --delay 1.0 --udid $UDID
Gesture Presets
| Preset | Use Case |
|---|---|
scroll-up |
Content navigation |
scroll-down |
Content navigation |
scroll-left |
Horizontal scrolling |
scroll-right |
Horizontal scrolling |
swipe-from-left-edge |
Back navigation |
swipe-from-right-edge |
Forward navigation |
swipe-from-top-edge |
Dismiss/close |
swipe-from-bottom-edge |
Open/reveal |
axe gesture scroll-down --udid $UDID
axe gesture swipe-from-left-edge --udid $UDID
axe gesture scroll-up --screen-width 430 --screen-height 932 --udid $UDID
axe gesture scroll-down --pre-delay 1.0 --post-delay 0.5 --udid $UDID
Text Input
# Direct text (use single quotes for special characters)
axe type 'Hello World!' --udid $UDID
# From stdin (best for automation)
echo "Complex text" | axe type --stdin --udid $UDID
# From file
axe type --file input.txt --udid $UDID
# Individual key press by HID keycode
axe key 40 --udid $UDID # Enter key
axe key 42 --duration 1.0 --udid $UDID # Hold Backspace
# Key sequence
axe key-sequence --keycodes 11,8,15,15,18 --udid $UDID # "hello"
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.
- 7d ago First seen · 171 lines · 79 tokens per session scan A 9dd429452847
skill-102 is a skill published in the GitHub repository legendtkl/agentic-skill-router (5 stars, last pushed 3mo ago), licensed MIT. It adds 79 tokens to every session and 1,378 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
android_ui_verification
Automated end-to-end UI testing and verification on an Android Emulator using ADB.
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.
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.
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…
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…