unifi-mcp-server: Skill for Claude Code

.agents/skills/source-command-unifi-mcp-test-coverage/SKILL.md

source-command-unifi-mcp-test-coverage is a skill for Claude Code, Codex from enuno/unifi-mcp-server. It costs 24 tokens per session (700 once invoked), scanned A, original, Apache-2.0.

A test-coverage analysis for the UniFi MCP server. Test coverage shows which parts of the source code are exercised by automated tests and which parts are not.

In plain words
What is it for?
Use it to run the test suite, produce coverage reports, find files below 80% coverage, identify missing lines, and recommend the next testing areas.
Why use it?
It identifies modules and lines with insufficient testing, so developers can focus new tests where they reduce the most risk. It also compares results with the project’s planned priorities and an 80% target.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is enuno/unifi-mcp-server's own configuration. It tells Claude Code and Codex 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/.agents/skills/source-command-unifi-mcp-test-coverage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/enuno/unifi-mcp-server

Made for: Claude Code, Codex.

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 source-command-unifi-mcp-test-coverage

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/enuno/unifi-mcp-server/source-command-unifi-mcp-test-coverage"><img src="https://agentmods.dev/badge/skills/enuno/unifi-mcp-server/source-command-unifi-mcp-test-coverage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 700 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00024 $0.00700
Opus 5 $0.00012 $0.00350
Sonnet 5 $0.00005 $0.00140
Haiku 4.5 $0.00002 $0.00070

Measured 10d ago against content hash d01e527a2783, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

source-command-unifi-mcp-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.

.agents/skills/source-command-unifi-mcp-test-coverage/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

source-command-unifi-mcp-test-coverage

Use this skill when the user asks to run the migrated source command unifi-mcp-test-coverage.

Command Template

Analyze test coverage for the UniFi MCP Server and identify areas needing improvement.

This command runs comprehensive coverage analysis and provides actionable recommendations to reach the 80% coverage target.

Steps to execute:

  1. Run full test suite with detailed coverage:

    pytest --cov=src --cov-report=term-missing --cov-report=html --cov-report=json -v
    
  2. Analyze coverage by module:

    • Parse coverage.json to extract per-file coverage percentages
    • Identify modules below 80% threshold
    • Prioritize based on TESTING_PLAN.md priorities
  3. Generate coverage gap analysis:

    • List files with coverage < 80%
    • Show missing lines for each file
    • Calculate how many tests needed to reach 80%
  4. Read TESTING_PLAN.md to understand priorities:

    • Phase 1 (Critical): API client, config, webhooks
    • Phase 2 (High): Tool modules by usage frequency
    • Phase 3 (Medium): Utility modules
    • Phase 4 (Low): Edge cases and error scenarios
  5. Provide actionable recommendations:

    • Which module to focus on next
    • Specific functions/lines that need tests
    • Suggested test scenarios to add
    • Estimated effort (number of tests needed)
  6. Compare with previous coverage:

    • Show coverage trend (if available)
    • Highlight improvements or regressions

Report back with:

  • Current overall coverage percentage
  • Coverage by category:
    • API client modules
    • Tool modules (by category)
    • Model modules
    • Utility modules
    • Webhook modules
  • Top 5 files needing the most coverage
  • Recommended next steps based on TESTING_PLAN.md
  • Estimated tests needed to reach 80%

Example output:

Current Coverage: 34.10%
Target: 80%
Gap: 45.90%

Coverage by Category:
✓ Models: 86.62% (above target)
✗ API Client: 45.23% (needs +34.77%)
✗ Tools: 38.54% (needs +41.46%)
✗ Webhooks: 12.00% (needs +68.00%)

Top Priority Files (from TESTING_PLAN.md Phase 1):
1. src/api/client.py - 45.23% (55 missing lines)
   - Need tests for: rate limiting, error handling, retry logic
2. src/config/settings.py - 60.00% (20 missing lines)
   - Need tests for: environment variable loading, validation
3. src/webhooks/receiver.py - 12.00% (88 missing lines)
   - Need tests for: webhook validation, signature checking

Next Action: Focus on src/api/client.py
Estimated effort: 8-10 test cases
Expected coverage gain: +11.13%

Read the full file on GitHub · 94 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 · 94 lines · 24 tokens per session scan A d01e527a2783

Subscribe to this mod's changes

source-command-unifi-mcp-test-coverage is a skill published in the GitHub repository enuno/unifi-mcp-server (247 stars, last pushed 3d ago), licensed Apache-2.0. It adds 24 tokens to every session and 700 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.