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 ComeOnOliver/skillshub --skill axiom-axe-refgit clone --depth 1 https://github.com/ComeOnOliver/skillshubWrote 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/comeonoliver/skillshub/axiom-axe-ref)<a href="https://agentmods.dev/skills/comeonoliver/skillshub/axiom-axe-ref"><img src="https://agentmods.dev/badge/skills/comeonoliver/skillshub/axiom-axe-ref/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/comeonoliver/skillshub/axiom-axe-ref"><img src="https://agentmods.dev/badge/skills/comeonoliver/skillshub/axiom-axe-ref.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 | $0.00045 | $0.02875 |
| Opus 5 | $0.00023 | $0.01437 |
| Sonnet 5 | $0.00009 | $0.00575 |
| Haiku 4.5 | $0.00005 | $0.00287 |
Grade A, and why
axiom-axe-ref 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 6d 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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AXe Reference (iOS Simulator UI Automation)
AXe is a CLI tool for interacting with iOS Simulators using Apple's Accessibility APIs and HID functionality. Single binary, no daemon required.
Installation
brew install cameroncooke/axe/axe
# Verify installation
axe --version
Critical Best Practice: describe_ui First
ALWAYS run describe_ui before UI interactions. Never guess coordinates from screenshots.
Best practice: Use describe-ui to get precise element coordinates prior to using x/y parameters (don't guess from screenshots).
# 1. FIRST: Get the UI tree with frame coordinates
axe describe-ui --udid $UDID
# 2. THEN: Tap by accessibility ID (preferred)
axe tap --id "loginButton" --udid $UDID
# 3. OR: Tap by label
axe tap --label "Login" --udid $UDID
# 4. LAST RESORT: Tap by coordinates from describe-ui output
axe tap -x 200 -y 400 --udid $UDID
Priority order for targeting elements:
--id(accessibilityIdentifier) - most stable--label(accessibility label) - stable but may change with localization-x -ycoordinates fromdescribe-ui- fragile, use only when no identifier
Core Concept: Accessibility-First
AXe's key advantage: Tap elements by accessibility identifier or label, not just coordinates.
# Coordinate-based (fragile - breaks with layout changes)
axe tap -x 200 -y 400 --udid $UDID
# Accessibility-based (stable - survives UI changes)
axe tap --id "loginButton" --udid $UDID
axe tap --label "Login" --udid $UDID
Always prefer --id or --label over coordinates.
Getting the Simulator UDID
AXe requires the simulator UDID for most commands:
# Get booted simulator UDID
UDID=$(xcrun simctl list devices -j | jq -r '.devices | to_entries[] | .value[] | select(.state == "Booted") | .udid' | head -1)
# List all simulators
axe list-simulators
Touch & Tap Commands
Tap by Accessibility Identifier (Recommended)
# Tap element with accessibilityIdentifier
axe tap --id "loginButton" --udid $UDID
# Tap element with accessibility label
axe tap --label "Submit" --udid $UDID
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.
- 6d ago First seen · 411 lines · 45 tokens per session scan A bfee34f9e926
axiom-axe-ref is a skill published in the GitHub repository ComeOnOliver/skillshub (63 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 2,875 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 2026-09-03.
Other skills, from other repositories
atf-testing
Build ServiceNow Automated Test Framework tests and suites — impersonation, form steps, assertions, server-side script steps, test parameters, and execution via snowcreateatftest / snowexecuteatftest.
acceptance
A skill for writing, running, and repairing human-written acceptance checks stored in an `acceptance/ACCEPTANCE.md` file. Acceptance checks are executable tests of whether the finished result matches the requested outcome.
rpi-explore-release
Run independent fresh-context exploratory charters against a fixed authorized release candidate, preserving the eight-maneuver safety and evidence contract.
mobile-testing
Write and run mobile tests including widget tests, integration tests, and golden tests. Use when implementing test strategies for Flutter or React Native apps.
playwright-stability
Make a Playwright E2E suite stable and realistic — kill flaky tests and authenticate like a real user via storageState (login once, reuse). Use when E2E tests are flaky, slow, re-login in every test, mock auth instead of using it, or when hardening a suite before relying on it.
mobile-app-testing
Record real-device (iOS Simulator / Android emulator) test flows for your app (web or native) via tapflow's MCP server, replay them with tapflow's own CLI, and stream results into an installed e2e-dashboard.