appium-mcp-auth: Skill for Claude Code

.claude/skills/verify-auth/SKILL.md

verify-auth is a skill for Claude Code from appclawhq/appium-mcp-auth. It costs 67 tokens per session (704 once invoked), scanned A, original, Apache-2.0.

A verification workflow for the appium-mcp-auth server. It runs type checking, unit tests, a production build, and a small server-startup check that tests plugin registration and the health endpoint.

In plain words
What is it for?
Use it after changes to validate the server locally and identify the first failing stage in the verification process.
Why use it?
It gives you a repeatable check that the authentication server still builds, passes its tests, starts correctly, and responds to health checks.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is appclawhq/appium-mcp-auth's own configuration. It tells Claude Code how to work on appium-mcp-auth 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 appium-mcp-auth configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node dist/cli.js --httpStream --port=$PORT --endpoint=/sse > /tmp/amauth-verify.log 2>&1 &.

Reuse

Borrowing it

Nothing to install: this file belongs to appclawhq/appium-mcp-auth. 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/appclawhq/appium-mcp-auth/main/.claude/skills/verify-auth/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/appclawhq/appium-mcp-auth

Made for: Claude Code.

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 verify-auth

README.md
[![agentmods](https://agentmods.dev/badge/skills/appclawhq/appium-mcp-auth/verify-auth/github.svg)](https://agentmods.dev/skills/appclawhq/appium-mcp-auth/verify-auth)
Your own site
<a href="https://agentmods.dev/skills/appclawhq/appium-mcp-auth/verify-auth"><img src="https://agentmods.dev/badge/skills/appclawhq/appium-mcp-auth/verify-auth/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 verify-auth

Your own site · 80×15
<a href="https://agentmods.dev/skills/appclawhq/appium-mcp-auth/verify-auth"><img src="https://agentmods.dev/badge/skills/appclawhq/appium-mcp-auth/verify-auth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 704 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00067 $0.00704
Opus 5 $0.00034 $0.00352
Sonnet 5 $0.00013 $0.00141
Haiku 4.5 $0.00007 $0.00070

Measured 9d ago against content hash 2555a59ce4cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

verify-auth scanned grade A 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -o /dev/null -w "health HTTP %{http_code}\n" http://localhost:$PORT/health
.claude/skills/verify-auth/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify appium-mcp-auth

Run the complete quality gate and report pass/fail crisply. Stop and report at the first failing stage; do not "fix" by editing appium-mcp core (forbidden — see CLAUDE.md).

Stages (run in order)

  1. Typecheck (source only):

    npm run typecheck
    
  2. Unit tests (60 tests via node:test + tsx):

    npm test
    

    Expect pass 60 / fail 0. If a test fails, show the failing assertion.

  3. Build (emit dist/):

    npm run build
    
  4. SSE smoke boot — start the real server with a throwaway key, confirm the plugin registers and the health endpoint answers, then stop it:

    export APPIUM_MCP_AUTH_API_KEYS='[{"id":"smoke","secret":"smoke-secret","subject":"smoke","scopes":["appium:use"]}]'
    export APPIUM_MCP_AUTH_AUDIT=false
    PORT=8791
    node dist/cli.js --httpStream --port=$PORT --endpoint=/sse > /tmp/amauth-verify.log 2>&1 &
    SVPID=$!
    for i in $(seq 1 40); do
      grep -q "listening on" /tmp/amauth-verify.log 2>/dev/null && break
      kill -0 $SVPID 2>/dev/null || { echo "SERVER EXITED EARLY"; break; }
      sleep 0.5
    done
    cat /tmp/amauth-verify.log
    curl -s -o /dev/null -w "health HTTP %{http_code}\n" http://localhost:$PORT/health
    kill $SVPID 2>/dev/null; wait $SVPID 2>/dev/null; rm -f /tmp/amauth-verify.log
    

Pass criteria

  • typecheck: exit 0, no output
  • tests: pass 60, fail 0
  • build: dist/ populated, exit 0
  • smoke boot log contains:
    • [PluginManager] Registered plugin "appium-mcp-auth"
    • All tools registered
    • httpStream (SSE) listening on http://localhost:8791/sse
  • health HTTP 200

Notes

  • Requires appium-mcp installed (it is a regular npm dependency) since the plugin composes into it at runtime.
  • The smoke boot needs no real device — it only starts the transport and registers tools; it does not create an Appium session.
  • If the port is busy, pick another (e.g. 8792) and reuse it consistently.
  • Report a one-line summary at the end: which stages passed and any failure.

Read the full file on GitHub · 67 lines

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. 9d ago First seen · 67 lines · 67 tokens per session scan A 2555a59ce4cb

Subscribe to this mod's changes

verify-auth is a skill published in the GitHub repository appclawhq/appium-mcp-auth (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 704 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens