agentmods.dev

unifi-tools: Instructions file for Claude Code

CLAUDE.md

unifi-tools CLAUDE.md is an instructions file for Claude Code from brianbell-x/unifi-tools. It costs 396 tokens per session, scanned A, original, MIT.

A contributor guide for UniFi management tools, a Python package and MCP server for controlling UniFi networks. It describes API tools, optional gateway SSH access, the command-line interface, and the bundled agent skill.

In plain words
What is it for?
Use it when adding or changing UniFi API tools, CLI commands, SSH features, agent skills, or the tests that verify their behaviour.
Why use it?
It explains where the package’s components live and how command-line commands and MCP tools must stay in sync. It also highlights testing and safety rules for management operations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions Claude Code.

This is brianbell-x/unifi-tools's own configuration. It tells Claude Code how to work on unifi-tools 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-tools configures →

not rated 15repo 1mo ago A scan 396 tokens original MIT
View source ↗ brianbell-x/unifi-tools
Reuse

Borrowing it

Nothing to install: this file belongs to brianbell-x/unifi-tools. 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/brianbell-x/unifi-tools/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/brianbell-x/unifi-tools

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-tools CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/brianbell-x/unifi-tools/claude-md/github.svg)](https://agentmods.dev/instructions/brianbell-x/unifi-tools/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/brianbell-x/unifi-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/brianbell-x/unifi-tools/claude-md/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-tools CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/brianbell-x/unifi-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/brianbell-x/unifi-tools/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 396 This file is loaded in full into every session.
When invoked 396 The same file — it is already loaded in full.
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 $0.00396 $0.00396
Opus 5.5 $0.00158 $0.00158
Sonnet 5.5 $0.00079 $0.00079
Haiku 4.5 $0.00040 $0.00040

Measured 2mo ago against content hash 6d1438a76bc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unifi-tools CLAUDE.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 2mo 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.md · 22 lines

What it actually says

UniFi Management Tools for AI Agents

One Python package (unifi-tools) exposing the official UniFi Network Integration API and an optional gateway-SSH escape hatch as both a CLI (unifi ...) and an MCP server (unifi mcp). Not an agent — tool extensions for agents.

Layout

  • src/unifi_tools/core.py — config (env > unifi init file), FastMCP instance, tool registry, API client
  • src/unifi_tools/api.py — 73 tools, complete documented surface of the Network API v10.3.58
  • src/unifi_tools/ssh.py — ssh exec / mongo read|write / provision, enabled only when UNIFI_SSH_KEY/UNIFI_SSH_PASSWORD is set
  • src/unifi_tools/cli.py — generic dispatcher: unifi_list_devices ⇄ unifi list devices; destructive commands need --yes
  • skills/unifi/ — the agent skill (read skills/unifi/SKILL.md before using the tools)
  • .claude-plugin/ — this repo is its own Claude Code plugin marketplace (plugin ships the skill)

Rules

  • Every tool registers as both CLI command and MCP tool via @tool() in core.py; uv run pytest asserts parity — run it after any tool change.
  • API ground truth is developer.ui.com (currently v10.3.58), not this codebase. Verify against docs before changing payloads.
  • SSH/MongoDB is only for what the API doesn't expose (radio config, port profiles, settings). After DB writes, force-provision (unifi provision <macs>).
  • Local dev MCP config lives in untracked .mcp.json; credentials in untracked .env / the unifi init config file.
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. 2mo ago First seen · 22 lines · 396 tokens per session scan A 6d1438a76bc6

Subscribe to this mod's changes

unifi-tools CLAUDE.md is an instructions file published in the GitHub repository brianbell-x/unifi-tools (15 stars, last pushed 1mo ago), licensed MIT. It adds 396 tokens to every session, about $0.0016 per session on Opus 5.5. 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.

Backend and APIsHardware and IoT
Related

unifi-tools CLAUDE.md compared with instructions from other repositories

unifi-tools CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
unifi-tools CLAUDE.mdbrianbell-x/unifi-toolsInstructions file151mo agoMITA396Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode