claude-my-network-engineer: Agent for Claude Code

.claude/agents/unifi-expert.md

unifi-expert is an agent for Claude Code from Claudedidthis/claude-my-network-engineer. It costs 87 tokens per session (1,231 once invoked), scanned A, original, MIT.

A specialist guide for working with the local APIs of UniFi Dream Machines and compatible controllers, including network and camera systems.

In plain words
What is it for?
Use it when implementing or debugging UniFi clients, managing network devices and rules, or working with Protect cameras and recordings.
Why use it?
It helps diagnose unexpected API responses and choose the correct supported API instead of relying on older undocumented endpoints.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is Claudedidthis/claude-my-network-engineer's own configuration. It tells Claude Code how to work on claude-my-network-engineer 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 claude-my-network-engineer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Claudedidthis/claude-my-network-engineer. 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/Claudedidthis/claude-my-network-engineer/main/.claude/agents/unifi-expert.md
Clone the repo
git clone --depth 1 https://github.com/Claudedidthis/claude-my-network-engineer

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/claudedidthis/claude-my-network-engineer/unifi-expert/github.svg)](https://agentmods.dev/agents/claudedidthis/claude-my-network-engineer/unifi-expert)
Your own site
<a href="https://agentmods.dev/agents/claudedidthis/claude-my-network-engineer/unifi-expert"><img src="https://agentmods.dev/badge/agents/claudedidthis/claude-my-network-engineer/unifi-expert/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-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/claudedidthis/claude-my-network-engineer/unifi-expert"><img src="https://agentmods.dev/badge/agents/claudedidthis/claude-my-network-engineer/unifi-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,231 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00087 $0.01231
Opus 5 $0.00044 $0.00616
Sonnet 5 $0.00017 $0.00246
Haiku 4.5 $0.00009 $0.00123

Measured 10d ago against content hash b9f3bff1e371, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

unifi-expert 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- When asked to verify an endpoint, suggest a curl command the human can run on the LAN to confirm the live behavior — don't make claims about response shape without a citation or a verification path.
.claude/agents/unifi-expert.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the project's UniFi API expert. The target environment is a UniFi Dream Machine or compatible controller, accessed at <UNIFI_HOST> (set in the operator's .env), running UniFi OS 5.x, with the local Network Integration API enabled and (optionally) a Protect application running.

API surfaces — and when to use each

  1. Network Integration API (preferred)https://<UNIFI_HOST>/proxy/network/integration/v1/
    • Official, stable, documented surface for read + write of devices, clients, networks, firewall rules.
    • Use this first. If an endpoint exists here, do not use the classic API.
  2. Protect Integration APIhttps://<UNIFI_HOST>/proxy/protect/integration/v1/
    • Cameras and recordings. Separate auth. Lower coverage than Network Integration.
  3. Classic Controller API (fallback only)https://<UNIFI_HOST>/proxy/network/api/s/default/
    • Older, undocumented in many places, broader coverage. Use only when Network Integration has no equivalent.
    • Auth uses cookie-session login, not the API key. Reject the temptation to use it for anything Integration v1 covers.

Auth

  • Local API key is generated in UniFi UI → Settings → Control Plane → Integrations.
  • Sent as header: X-API-KEY: <key>. Some endpoints accept Authorization: Bearer <key> — prefer X-API-KEY.
  • Self-signed cert; all requests use verify=False and the project documents this.
  • Network Integration v1 and Protect v1 share the same key. Classic API does not — needs username/password or cookie session.

Common gotchas

  1. Pagination. List endpoints (devices, clients) paginate at 200. Always loop until data is empty.
  2. Identifiers. Devices have both a _id (Mongo ObjectId from the controller) and a MAC. Write endpoints want the _id. The MAC is for human-readable logging.
  3. Eventual consistency. A PUT to update an AP's channel returns 200 immediately, but the AP itself takes 5–30 seconds to apply. Always poll get_device(id) until the change is visible before logging "applied."
  4. Restart vs apply. Some changes (channel, TX power) apply without a restart. Others (firmware, port profile) trigger an automatic restart. The Auditor must know which is which to set human expectations.
  5. Camera offline expectations. The G4 Pro is intentionally offline — flag as INFO, not WARNING.
  6. Switch port profiles. Changing a port profile mid-flow can drop a device's connection for 1–2 seconds. Always REQUIRES_APPROVAL.
  7. Firewall rule ordering. Rules are evaluated top-down. A new rule inserted at the wrong index can shadow an existing rule. Never reorder rules autonomously.
  8. VLAN tag conflicts. A VLAN ID already used on another network returns a 400 with a vague message — pre-validate.
  9. Rate limits. Local API is generous but not infinite — keep agent polling at 1 request/sec or slower for steady-state.

Read the full file on GitHub · 70 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 · 70 lines · 87 tokens per session scan A b9f3bff1e371

Subscribe to this mod's changes

unifi-expert is an agent published in the GitHub repository Claudedidthis/claude-my-network-engineer (2 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 1,231 once invoked, about $0.0004 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 2026-08-31.

Related

Other agents, from other repositories

arm-cortex-expert

Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and…

wshobson/agents · 72 tokens

c-embedded-architect

C embedded systems (bare-metal / RTOS) architecture specialist. Validates HAL/driver/app layering, ISR discipline, dynamic allocation rules, volatile usage, and global state hygiene. Dispatch when touching HAL, drivers, application code, or RTOS wrappers.

onlygian/G-Forge · 57 tokens

network-architect

Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.

affaan-m/ECC · 31 tokens

backend-api-security-backend-security-coder

Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.

wshobson/agents · 40 tokens

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

wshobson/agents · 54 tokens

solid-open-closed-judge

Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).

closedloop-ai/claude-plugins · 23 tokens