Borrowing it
Nothing to install: this file belongs to enuno/unifi-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/enuno/unifi-mcp-server/main/.claude/commands/unifi-mcp-live-test.mdgit clone --depth 1 https://github.com/enuno/unifi-mcp-serverWrote 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/commands/enuno/unifi-mcp-server/unifi-mcp-live-test)<a href="https://agentmods.dev/commands/enuno/unifi-mcp-server/unifi-mcp-live-test"><img src="https://agentmods.dev/badge/commands/enuno/unifi-mcp-server/unifi-mcp-live-test/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/commands/enuno/unifi-mcp-server/unifi-mcp-live-test"><img src="https://agentmods.dev/badge/commands/enuno/unifi-mcp-server/unifi-mcp-live-test.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 | $0.00024 | $0.03786 |
| Opus 5 | $0.00012 | $0.01893 |
| Sonnet 5 | $0.00005 | $0.00757 |
| Haiku 4.5 | $0.00002 | $0.00379 |
Grade A, and why
unifi-mcp-live-test 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 12d 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.
- Bash(curl:*) How it starts
The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UniFi MCP Server - Live Environment Testing & Automated Remediation
Purpose
Automatically discover UniFi environments from .env, execute comprehensive tests, sanitize results, create GitHub issues for bugs, and automatically instruct the @claude bot to develop and submit fixes via PRs.
Key Features:
- ✅ Portable: No hardcoded IPs/hostnames; auto-discovers from
.env. - ✅ Secure: Masks credentials and sanitizes IP addresses in logs.
- ✅ Interactive: Prompts user to select which discovered environments to test.
- ✅ Automated Remediation: Creates GitHub issues, waits for Triage Bot, and assigns
@claudeto fix, test, and PR.
Phase 1: Pre-Flight Checks and Environment Discovery
1.1 Verify Prerequisites
echo "╔════════════════════════════════════════════════════╗"
echo "║ UNIFI MCP LIVE TEST & REMEDIATION - STARTING ║"
echo "╚════════════════════════════════════════════════════╝"
echo ""
# Check Node.js
if command -v node &> /dev/null; then
echo "✅ Node.js: $(node --version)"
else
echo "❌ Node.js not installed"
exit 1
fi
# Check Python/UV
if command -v python3 &> /dev/null; then
echo "✅ Python: $(python3 --version | head -1)"
else
echo "❌ Python3 not installed"
exit 1
fi
# Check GitHub CLI (Critical for Phase 4 & 5)
if command -v gh &> /dev/null; then
echo "✅ GitHub CLI: $(gh --version | head -1)"
gh auth status &> /dev/null || { echo "❌ GitHub CLI not authenticated. Run 'gh auth login' first."; exit 1; }
else
echo "❌ GitHub CLI not installed - required for automated remediation"
exit 1
fi
# Check MCP server exists
if [ -f src/main.py ]; then
echo "✅ MCP server found (src/main.py)"
else
echo "❌ src/main.py not found"
exit 1
fi
echo ""
1.2 Discover Test Environments from .env
echo "Discovering test environments from .env..."
if [ ! -f .env ]; then
echo "❌ .env file not found. Please create one based on .env.example."
exit 1
fi
# Initialize discovery variables
HAS_CLOUD=false
HAS_LOCAL=false
HAS_AUTH=false
# Check Cloud
if grep -q "^UNIFI_HOST=" .env; then
CLOUD_HOST=$(grep "^UNIFI_HOST=" .env | cut -d= -f2 | tr -d '"' | tr -d "'")
if [ ! -z "${CLOUD_HOST}" ] && [ "${CLOUD_HOST}" != "your-host-here" ]; then
echo "✅ Found Cloud API configuration: ${CLOUD_HOST}"
HAS_CLOUD=true
fi
fi
# Check Local
if grep -q "^UNIFI_LOCAL_HOST=" .env; then
LOCAL_HOST=$(grep "^UNIFI_LOCAL_HOST=" .env | cut -d= -f2 | tr -d '"' | tr -d "'")
if [ ! -z "${LOCAL_HOST}" ] && [ "${LOCAL_HOST}" != "your-host-here" ]; then
# Get SSL setting
LOCAL_SSL="false"
grep -q "^UNIFI_LOCAL_VERIFY_SSL=true" .env && LOCAL_SSL="true"
echo "✅ Found Local Gateway configuration: ${LOCAL_HOST} (SSL: ${LOCAL_SSL})"
HAS_LOCAL=true
fi
fi
# Check Auth
if (grep -q "^UNIFI_API_KEY=" .env && [ $(grep "^UNIFI_API_KEY=" .env | cut -d= -f2 | wc -c) -gt 5 ]) || \
(grep -q "^UNIFI_USERNAME=" .env && grep -q "^UNIFI_PASSWORD=" .env); then
echo "✅ Authentication configured"
HAS_AUTH=true
fi
if [ "${HAS_CLOUD}" = "false" ] && [ "${HAS_LOCAL}" = "false" ]; then
echo "❌ No valid environments found in .env"
exit 1
fi
if [ "${HAS_AUTH}" = "false" ]; then
echo "❌ No valid authentication found in .env"
exit 1
fi
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.
- 12d ago First seen · 458 lines · 24 tokens per session scan A 7028f8f21019
unifi-mcp-live-test is a command published in the GitHub repository enuno/unifi-mcp-server (250 stars, last pushed 5d ago), licensed Apache-2.0. It adds 24 tokens to every session and 3,786 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
playwright-test-heal
Run all my tests and fix the failing ones.
paul:verify
Guide manual user acceptance testing of recently built features.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.