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 agentmods add instructions/pproenca/unifi-mcp/agents-mdgit clone --depth 1 https://github.com/pproenca/unifi-mcpWrote 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/instructions/pproenca/unifi-mcp/agents-md)<a href="https://agentmods.dev/instructions/pproenca/unifi-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/pproenca/unifi-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.00627 | $0.00627 |
| Opus 5 | $0.00313 | $0.00313 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
unifi-mcp AGENTS.md 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 4d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributor Guide
Guide for contributors working on the UniFi MCP server — a local MCP server for the UniFi Network API.
Project Overview
This repository provides an MCP (Model Context Protocol) server that wraps the UniFi Network API. It runs locally via npx unifi-mcp or bunx unifi-mcp and exposes UniFi management operations as MCP tools for use with Claude and other MCP-compatible hosts.
Repo Structure
src/— Server implementation (TypeScript)docs/ref/— Scraped UniFi API reference docsdocs/ref/unifi-openapi.json— Full OpenAPI 3.1.0 spec for the UniFi Network APIdocs/ref/index.md— Table of contents for all API endpointsscripts/— Utility scriptsscrape-docs.mjs— Scrapes UniFi docs from developer.ui.comsync-skills.sh— Syncs.agents/skills/as symlinks into.claude/skills/
.agents/skills/— Agent skills (shared across Claude Code, Codex, etc.).claude/skills/— Symlinks to.agents/skills/(managed bysync-skills.sh)package.json— Node.js project config
Skills
$code-change-verification
Run before marking work complete when changes affect src/, tests, or build config.
bash .agents/skills/code-change-verification/scripts/run.sh
$implementation-strategy
Use before editing code when the task changes MCP tool definitions, runtime behavior, or configuration. Determines the compatibility boundary and implementation shape.
$pr-draft-summary
When a task finishes with moderate-or-larger code changes, invoke to generate a PR summary block, branch suggestion, title, and draft description.
$docs-sync
Audit documentation coverage by comparing the implementation against docs/. Use after significant API surface changes.
$build-mcp-server
Reference skill for MCP server design and scaffolding patterns.
Development Workflow
- Create a feature branch:
git checkout -b feat/<description> - Install dependencies:
npm install - Implement changes with tests
- Run
$code-change-verificationbefore marking complete - Use
$pr-draft-summaryfor the final handoff
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.
- 4d ago First seen · 69 lines · 627 tokens per session scan A e53e9af9154d
unifi-mcp AGENTS.md is an instructions file published in the GitHub repository pproenca/unifi-mcp (2 stars, last pushed 5mo ago), licensed MIT. It adds 627 tokens to every session, about $0.0031 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 2026-08-31.
Other instructions, from other repositories
gpu-mcp-server AGENTS.md
Instructions for pmady/gpu-mcp-server, covering agents.md, project overview, build, code layout and key patterns.
pixoo-mcp-server AGENTS.md
Instructions for cyanheads/pixoo-mcp-server, covering developer protocol, architecture overview, what's next?, core rules and patterns.
flipperzero-mcp CLAUDE.md
Instructions for millsymills-com/flipperzero-mcp, covering claude.md, canonical standards, project, project specifics and agent skills.
unifi-mcp copilot-instructions.md
Instructions for gordcurrie/unifi-mcp, covering github copilot instructions — unifi-mcp, project overview, architecture, probe any v1 endpoint — substitute path and id as needed and uses a self-signed certificate in this home lab environment.
mcp-synology CLAUDE.md
Instructions for cmeans/mcp-synology, covering claude.md, project overview, architecture, design specs and build & development commands.
rosbridge-mcp CLAUDE.md
Claude Code instructions for hieutachi/rosbridge-mcp, covering claude.md, layout, run, then rosbridgeurl=ws://localhost:9090 and environment.