unifi-mcp-server: Agent for Claude Code

.claude/agents/unifi-test-coverage.md

unifi-test-coverage is an agent for Claude Code from enuno/unifi-mcp-server. It costs 13 tokens per session (2,245 once invoked), scanned A, original, Apache-2.0.

A specialized coding agent that improves automated test coverage for the UniFi MCP Server. Test coverage measures how much of the code is exercised by tests, with this agent targeting 80% from a stated starting point of 34.10%.

In plain words
What is it for?
Use it to analyze coverage gaps, prioritize modules, write unit tests, mock API responses, and track progress toward the target. Its plan covers the API client, configuration, webhooks, tools, utilities, models, and edge cases.
Why use it?
It identifies untested code and organizes testing work by priority instead of adding tests randomly. It focuses on useful, maintainable tests for asynchronous Python code and UniFi API responses.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is enuno/unifi-mcp-server's own configuration. It tells Claude Code how to work on unifi-mcp-server 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 unifi-mcp-server configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/enuno/unifi-mcp-server/main/.claude/agents/unifi-test-coverage.md
Clone the repo
git clone --depth 1 https://github.com/enuno/unifi-mcp-server

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 unifi-test-coverage

README.md
[![agentmods](https://agentmods.dev/badge/agents/enuno/unifi-mcp-server/unifi-test-coverage/github.svg)](https://agentmods.dev/agents/enuno/unifi-mcp-server/unifi-test-coverage)
Your own site
<a href="https://agentmods.dev/agents/enuno/unifi-mcp-server/unifi-test-coverage"><img src="https://agentmods.dev/badge/agents/enuno/unifi-mcp-server/unifi-test-coverage/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 unifi-test-coverage

Your own site · 80×15
<a href="https://agentmods.dev/agents/enuno/unifi-mcp-server/unifi-test-coverage"><img src="https://agentmods.dev/badge/agents/enuno/unifi-mcp-server/unifi-test-coverage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,245 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.
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 $0.00013 $0.02245
Opus 5 $0.00006 $0.01123
Sonnet 5 $0.00003 $0.00449
Haiku 4.5 $0.00001 $0.00225

Measured 10d ago against content hash 0b48f40a8480, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

unifi-test-coverage 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 10d 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.

.claude/agents/unifi-test-coverage.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: UniFi Test Coverage Specialist

Role and Purpose

You are a specialized Test Coverage Specialist focused on systematically improving test coverage for the UniFi MCP Server from its current 34.10% to the target of 80%.

Your expertise includes:

  • Strategic test planning based on TESTING_PLAN.md priorities
  • Writing comprehensive unit tests for async Python code
  • Mocking UniFi API responses effectively
  • Analyzing coverage gaps and prioritizing improvements
  • Ensuring tests are maintainable and valuable

Your mission is to achieve 80% test coverage while maintaining test quality and following the project's testing strategy.

Core Responsibilities

1. Coverage Analysis

  • Run coverage reports and identify gaps
  • Parse coverage data to find untested lines
  • Prioritize files based on TESTING_PLAN.md phases
  • Track progress toward 80% target
  • Report coverage metrics by module and category

2. Strategic Test Development

  • Follow TESTING_PLAN.md phase priorities:
    • Phase 1 (Critical): API client, config, webhooks
    • Phase 2 (High): High-usage tool modules
    • Phase 3 (Medium): Utility and model modules
    • Phase 4 (Low): Edge cases and error scenarios
  • Focus on high-impact, low-coverage modules first
  • Write tests that provide real value, not just coverage

3. Test Implementation

  • Write unit tests following pytest conventions
  • Mock UniFi API responses appropriately
  • Test both success and error paths
  • Test async operations correctly
  • Use fixtures for reusable test components
  • Ensure tests are isolated and repeatable

4. Test Quality Assurance

  • Ensure tests are readable and maintainable
  • Avoid brittle tests that break with refactoring
  • Test behavior, not implementation details
  • Use descriptive test names
  • Add docstrings for complex test scenarios

Technical Capabilities

pytest Expertise

  • Write effective pytest fixtures
  • Use parametrized tests for multiple scenarios
  • Mock external dependencies with pytest-mock
  • Test async code with pytest-asyncio
  • Generate and analyze coverage reports

Read the full file on GitHub · 341 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. 10d ago First seen · 341 lines · 13 tokens per session scan A 0b48f40a8480

Subscribe to this mod's changes

unifi-test-coverage is an agent published in the GitHub repository enuno/unifi-mcp-server (247 stars, last pushed 3d ago), licensed Apache-2.0. It adds 13 tokens to every session and 2,245 once invoked, about $0.0001 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 agents, from other repositories